WO2021109952A1 - Video editing method, apparatus and server, and computer readable storage medium - Google Patents

Video editing method, apparatus and server, and computer readable storage medium Download PDF

Info

Publication number
WO2021109952A1
WO2021109952A1 PCT/CN2020/132585 CN2020132585W WO2021109952A1 WO 2021109952 A1 WO2021109952 A1 WO 2021109952A1 CN 2020132585 W CN2020132585 W CN 2020132585W WO 2021109952 A1 WO2021109952 A1 WO 2021109952A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
target
data
value
preset
Prior art date
Application number
PCT/CN2020/132585
Other languages
French (fr)
Chinese (zh)
Inventor
杜中强
谢春燕
张意烽
申武
Original Assignee
成都市喜爱科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 成都市喜爱科技有限公司 filed Critical 成都市喜爱科技有限公司
Publication of WO2021109952A1 publication Critical patent/WO2021109952A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/232—Content retrieval operation locally within server, e.g. reading video streams from disk arrays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23424—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
    • H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments

Definitions

  • This application relates to the field of video processing technology, and in particular to a video editing method, device, server, and computer-readable storage medium.
  • the amusement park will install shooting equipment on the amusement equipment, and use the shooting equipment to shoot the video during the tourists riding on the amusement equipment, and after the shooting is completed, the highlights will be edited from the shot video and the highlights will be added. Stitched into a combined video to help visitors leave the wonderful moments in the play process.
  • the original video is manually watched, and the wonderful moments are selected to edit the combined video. This process requires a lot of manpower and time, resulting in low efficiency.
  • One of the objectives of the present application includes providing a video editing method, device, server, and computer-readable storage medium to improve the inefficiency caused by manual selection of a perfect video moment for video editing.
  • the present application provides a video editing method applied to a server, the server is in communication connection with a shooting device, the shooting device is installed on a sports device, and the shooting device includes a sports data collection device ,
  • the method includes: receiving the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the motion data collection device; according to the motion data, from the original Select at least one video segment from the video; insert the at least one video segment into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes at least one video segment and at least one Template fragment.
  • the motion data includes a plurality of data values and a collection time point corresponding to each data value; the step of selecting at least one video segment from the original video according to the motion data, The method includes: obtaining a target selection condition corresponding to the exercise data; according to the target selection condition, locating a target data value from the exercise data, and obtaining a target time point corresponding to the target data value; based on the target time Point, select from the original video before the target time point and/or after the target time point, and continue a video clip with a preset duration to obtain the at least one video clip.
  • the server pre-stores a plurality of device identifications and selection conditions corresponding to each of the device identifications; the step of obtaining the target selection conditions corresponding to the exercise data includes: The motion data is analyzed to determine the target device identifier corresponding to the motion data; according to the target device identifier, the target selection condition corresponding to the motion data is determined from a plurality of selection conditions.
  • the exercise data includes air pressure data
  • the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each of the air pressure data values
  • the target selection condition includes the air pressure data value reaching Preset air pressure value
  • the step of locating a target data value from the exercise data according to the target selection condition and obtaining the target time point corresponding to the target data value includes: locating from the air pressure data A target air pressure data value that reaches the preset air pressure value is output; and a target time point corresponding to the target air pressure data value is acquired.
  • the exercise data includes air pressure data
  • the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each air pressure data value
  • the target selection condition includes two adjacent air pressure data values.
  • the air pressure change rate of the air pressure data value reaches the preset air pressure change rate; the step of locating a target data value from the exercise data according to the target selection condition, and obtaining the target time point corresponding to the target data value
  • the method includes: determining, from the plurality of air pressure data values, two adjacent air pressure data values whose air pressure change rate reaches the preset air pressure change rate; and setting the latter of the two adjacent air pressure data values as a target Air pressure data value; obtaining the target time point corresponding to the target air pressure data value.
  • the motion data includes position data
  • the position data includes a plurality of position data values and a collection time point corresponding to each position data value
  • the target selection condition includes a position data value corresponding The preset position
  • the step of locating a target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value includes: locating from the position data The target position data value corresponding to the preset position; and the target time point corresponding to the target position data value is acquired.
  • the motion data includes acceleration data
  • the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each acceleration data value
  • the target selection condition includes that the acceleration data value reaches Preset acceleration value
  • the step of locating a target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value includes: locating from the acceleration data A target acceleration data value that reaches the preset acceleration value is obtained; and a target time point corresponding to the target acceleration data value is obtained.
  • the motion data includes acceleration data
  • the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each acceleration data value
  • the target selection condition includes a continuous preset
  • the difference between the number of acceleration data values and the gravitational acceleration is greater than a preset value
  • the target data value is located from the motion data according to the target selection condition, and the target time point corresponding to the target data value is obtained
  • the step includes: determining, from the plurality of acceleration data values, that the difference with the acceleration of gravity is greater than a preset value and a continuous preset number of acceleration data values; and combining the preset number of acceleration data The last of the values is used as the target acceleration data value; the target time point corresponding to the target acceleration data value is obtained.
  • the motion data includes angular velocity data
  • the angular velocity data includes a plurality of angular velocity data values and a collection time point corresponding to each angular velocity data value
  • the target selection condition includes that the angular velocity data reaches a predetermined value.
  • Set the angular velocity value; the step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes: locating from the angular velocity data A target angular velocity data value that reaches the preset angular velocity value; and a target time point corresponding to the target angular velocity data value is acquired.
  • the motion data includes angular velocity data
  • the angular velocity data includes a plurality of angular velocity data values and a collection time point corresponding to each angular velocity data value
  • the target selection condition includes at least one angular velocity data
  • the accumulated value of the value within a preset time reaches a preset value; the step of locating a target data value from the exercise data according to the target selection condition, and obtaining the target time point corresponding to the target data value
  • the method includes: determining, from the plurality of angular velocity data values, at least one angular velocity data value at which the accumulated value within the preset time reaches the preset value; and using the last one of the at least one angular velocity data value as the target angular velocity data Value; obtain the target time point corresponding to the target angular velocity data value.
  • the server establishes a human face database in advance, and before the step of selecting at least one video segment from the original video according to the motion data, the method further includes: The video performs face recognition, and the corresponding relationship between the face and the original video is obtained and stored in the face database.
  • the face database includes a correspondence relationship between a face and an original video, and a correspondence relationship between an original video and a synthesized video
  • the server is also communicatively connected to the mobile terminal
  • the at least one After the video clip is inserted into the preset video template to obtain the composite video the method further includes: obtaining a video obtaining request sent by the mobile terminal, wherein the video obtaining request includes a face image; Perform face recognition on the face image to obtain the target face corresponding to the face image; determine the target composite video corresponding to the target face based on the face database; send the target composite video to the A mobile terminal, so that the mobile terminal displays the target composite video.
  • the server establishes a face database in advance, and the server is also communicatively connected to the mobile terminal; before the step of selecting at least one video segment from the original video according to the motion data, The method further includes: performing face recognition on the original video to obtain the corresponding relationship between the face and the original video and store it in the face database; obtaining the video acquisition request sent by the mobile terminal, wherein: The video acquisition request includes a face image; face recognition is performed on the face image to obtain a target face corresponding to the face image; based on the face database, a target corresponding to the target face is determined Original video, and use the target original video as the original video, and perform the step of selecting at least one video segment from the original video according to the motion data; and inserting the at least one video segment into In the preset video template, after the step of obtaining the composite video, the method further includes: sending the composite video corresponding to the target original video to the mobile terminal, so that the mobile terminal displays the target original video corresponding to the target original video. Composite video.
  • the original video is obtained by preprocessing the captured video content by the shooting device; wherein, the step of preprocessing the captured video content by the shooting device includes: the shooting The device performs face detection on the video content to obtain the face area of each video frame in the video content; the shooting device calculates how much the face area of each video frame is in each video frame And delete the video frames with the aspect ratio less than the preset ratio to obtain the original video.
  • the original video is obtained by preprocessing the captured video content by the shooting device; wherein, the step of preprocessing the captured video content by the shooting device includes: the shooting The device performs face detection on the video content to obtain the face area of each video frame in the video content; the shooting device obtains the face pixel size corresponding to the face area of each video frame, and deletes it A video frame whose face pixel size is smaller than a preset minimum face pixel size is used to obtain the original video.
  • the step of preprocessing the captured video content by the photographing device further includes: the photographing device deletes overexposed or blurred video frames in the video content.
  • the video template further includes a credit card and a credit card, the at least one template segment is arranged between the credit card and the credit card;
  • the composite video further includes the credit card and the credit card,
  • the at least one video segment and the at least one template segment are arranged between the title and the trailer;
  • the template segment includes at least one of a template video, a special effect picture, and a subtitle.
  • the present application also provides a video editing device applied to a server, the server is in communication connection with a shooting device, the shooting device is installed on the sports equipment and includes a sports data collection device, the The device includes: a receiving module configured to receive the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the sports data collection device; and the selection module is configured to be based on the Motion data, selecting at least one video segment from the original video; a processing module configured to insert the at least one video segment into a preset video template to obtain a composite video, the video template including at least one template segment, The composite video includes at least one video segment and at least one template segment.
  • the present application also provides a server, the server includes: one or more processors; a memory configured to store one or more programs, when the one or more programs are When the one or more processors are executed, the one or more processors are caused to implement the above-mentioned video editing method.
  • the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned video editing method is realized.
  • the present application provides a video editing method, device, server, and computer-readable storage medium.
  • the original video is captured by a shooting device, and the motion data of the sports device is collected by the motion data collection device.
  • the server receives the shooting After the original video and motion data sent by the device, at least one video segment is selected from the original video according to the motion data, and at least one video segment is inserted into the preset video template to obtain a composite video, which is automatically selected according to the motion data of the sports device.
  • the highlights in the original video are generated into a composite video, which eliminates the need for human participation, which improves the efficiency of video editing.
  • Fig. 1 shows a schematic diagram of an application scenario of a video editing method provided by an embodiment of the present application.
  • Fig. 2 shows a schematic flowchart of a video editing method provided by an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of sub-steps of step S102 in the video editing method shown in FIG. 2.
  • Fig. 4 shows an example diagram of a composite video provided by an embodiment of the present application.
  • Fig. 5 shows another example diagram of a composite video provided by an embodiment of the present application.
  • Fig. 6 shows another schematic flowchart of a video editing method provided by an embodiment of the present application.
  • Fig. 7 shows another schematic flowchart of a video editing method provided by an embodiment of the present application.
  • Fig. 8 shows a block diagram of functional modules of a video editing device provided by an embodiment of the present application.
  • Fig. 9 shows a block diagram of functional modules of a server provided in an embodiment of the present application.
  • Icon 10-server; 20-shooting equipment; 30-mobile terminal; 21-sports data acquisition device; 11-processor; 12-memory; 13-bus; 100-video editing device; 101-receiving module; 102-selection Module; 103-processing module.
  • FIG. 1 shows a schematic diagram of an application scenario of a video editing method provided by an embodiment of the present application, including a server 10, at least one photographing device 20, and at least one mobile terminal 30.
  • Each photographing device 20 communicates with the server through a network. 10. Communication connection.
  • Each mobile terminal 30 is connected to the server 10 through a network to realize data communication or interaction between the server 10 and the photographing device 20, and between the server 10 and the mobile terminal 30.
  • the photographing equipment 20 is installed on sports equipment.
  • the sports equipment can be equipment for extreme sports or other amusement items.
  • the extreme sports can include extreme cycling, low-altitude parachuting, high-speed racing, diving, downhill skiing, etc.
  • the amusement items can be Including roller coasters, kite flying vehicles, pirate ships, torrents, carousels, etc. The following embodiments take the equipment of amusement projects as an example for description.
  • At least one shooting device 20 is installed on each sports equipment.
  • the shooting device 20 can be a sports camera, a camera, a device equipped with a camera module, etc.; each shooting device 20 includes a sports data collection device 21, a sports data collection device 21 is configured to collect motion data of the motion device when the motion device of the fixed photographing device 20 moves.
  • the motion data collection device 21 may include, but is not limited to, a barometer, a gyroscope, an acceleration sensor, a speed sensor, a gravity sensor, etc.
  • the shooting device 20 is configured to shoot a video for the tourists when the tourists ride on the amusement device to play, and send the original video and the movement data collected by the movement data collecting device 21 to the server 10.
  • the shooting device 20 Since the video content actually shot by the shooting device 20 on the amusement device has a long time and a large amount of data, it may also contain some fragments with poor effects, for example, there are no human faces or incomplete faces in the picture. Therefore, in order to shorten the time and To reduce the amount of data transmission, the shooting device 20 needs to preprocess the actually shot video content to obtain the original video, that is, the original video is obtained after the shooting device 20 preprocesses the actually shot video content.
  • the process of preprocessing the captured video content by the shooting device 20 may include: first, the shooting device 20 performs face detection on the video content to obtain the face area of each video frame in the video content; then, shooting The device 20 calculates the aspect ratio of the face area of each video frame in each video frame, and deletes the video frames whose aspect ratio is less than a preset ratio (for example, 10%) to obtain the original video. That is, the shooting device 20 deletes the video frames whose face ratio is lower than the preset ratio in the screen according to a preset ratio (for example, 10%), so as to cut out no face or face incompleteness or face angle. Video clips of poor waiting.
  • a preset ratio for example, 10%
  • the process of preprocessing the captured video content by the shooting device 20 may include: first, the shooting device 20 performs face detection on the video content to obtain the face area of each video frame in the video content; then, shooting The device 20 obtains the face pixel size corresponding to the face area of each video frame, and deletes the video frame whose face pixel size is less than the preset minimum face pixel size to obtain the original video. That is, the shooting device 20 preprocesses the captured video content according to the preset minimum face pixel size.
  • the face frame that the shooting device 20 can detect is a square
  • the minimum side length of the square is the short video frame.
  • the minimum value is not less than 48 pixels, for example, if the video frame is 4096*3200 pixels, the minimum face pixel size is 66*66 pixels, and the face pixel size is lower than the minimum face pixel size Video frame deletion.
  • the process of preprocessing the captured video content by the shooting device 20 may also include quality screening, that is, the shooting device 20 deletes overexposed or blurred video frames in the video content.
  • the server 10 is configured to receive the original video and motion data sent by the shooting device 20, select highlights from the original video according to the motion data, and insert the highlights into a preset video template to obtain a composite video; at the same time, the server 10 is also configured Upon receiving the video acquisition request sent by the mobile terminal 30, the target composite video corresponding to the video acquisition request is acquired, and the target composite video is sent to the mobile terminal 30.
  • the server 10 may be a single server or a server group.
  • the mobile terminal 30 is configured to receive the target composite video sent by the server 10, and display the target composite video for the user to select.
  • the mobile terminal 30 may be, but is not limited to, a smart phone, a tablet computer, a portable notebook computer, a desktop computer, and the like.
  • a third-party application (Application, APP) is installed in the mobile terminal 30.
  • the third-party application can run a small program, and the user can interact with the server 10 through the small program. For example, after the user rides on the amusement device, You can watch or download your own play videos through this small program.
  • the applet can obtain the user's face image, and match the face image with the composite video in the server 10 to obtain The target composite video with the user as the protagonist is displayed, and the target composite video is displayed for the user to watch, download, etc.
  • an application can also be installed in the mobile terminal 30, so that the user can interact with the server 10 through the application to realize the viewing and downloading of the target composite video with the user as the protagonist.
  • FIG. 2 shows a schematic flowchart of a video editing method provided by an embodiment of the present application.
  • the video editing method is applied to the server 10 and may include the following steps:
  • S101 Receive the original video sent by the shooting equipment and the motion data of the sports equipment, where the motion data is collected by the motion data collection device.
  • the shooting device 20 is fixedly installed on the sports equipment, and it is ensured that one shooting device 20 can capture the video of at least one user riding on the sports equipment.
  • the sports equipment is a roller coaster
  • one shooting device 20 is provided for each row of seats. This allows the shooting device 20 to collect a row of users' play videos.
  • the shooting device 20 is always on.
  • the shooting device 20 captures the user's original video
  • the motion data collection device 21 collects the motion data of the sports device.
  • the original video and the time of the motion data correspond, that is, the same
  • the original video frame and the motion data value at a time point are corresponding.
  • the original video is obtained by preprocessing the captured video content by the shooting device 20, and the original video is based on at least one specific user as the protagonist. For example, a row of seats of a roller coaster is provided with a shooting device 20, and for one of the shooting devices 20 The original video taken, and the original video takes one or two users in a row of seats corresponding to the shooting device 20 as the protagonists.
  • the original video can be a complete video or several independent small videos. Generally, the length of the original video can be 30s-1min.
  • S102 Select at least one video segment from the original video according to the motion data.
  • the motion data collected by the motion data collection device 21 may be one or more of air pressure data, position data, acceleration data, velocity data, angular velocity data, gravity data, etc., and at the same time, the motion data includes multiple data values. And the collection time point corresponding to each data value.
  • the video clips selected from the original videos can include, but are not limited to, the video clips when the sports equipment just starts to move or the video clips that can reflect the characteristics of the sports equipment. For example, if the sports equipment is a roller coaster, a pirate ship, etc. Equipment, you can select the video clip when the roller coaster climbs to the apex and starts to dive; if the sports equipment is amusement equipment with large acceleration changes such as rapids, jumpers, etc., you can select the video clip at the sudden acceleration; the sports equipment is a carousel Rotating amusement equipment such as, flying chairs, etc., you can select video clips when arriving at a designated location (for example, a location with beautiful scenery, a wide field of view, etc.). Obviously, these video clips can be selected according to the movement data during the running of the sports device. For example, if the sports device is a roller coaster, the video clips with the largest or smallest gravity value can be selected.
  • the method of selecting at least one video segment from the original video may include: firstly, obtaining a data value in the motion data that reaches a set value, or comparing with the previous/next data value. A data value that changes significantly; then, the acquisition time point corresponding to the data value is obtained as a reference point, and a video clip of a certain length of time (for example, 5-15s, etc.) before and/or after the reference point is selected from the original video.
  • the set value can be a set air pressure value, a set acceleration value, a set angular velocity value, etc.
  • the server 10 receives the original video and motion data sent by the shooting device 20, if a certain data value in the motion data satisfies the air pressure
  • the video clip is selected according to the time point corresponding to the data value.
  • S102 may include:
  • the target selection condition refers to the condition for locating the target data value from the motion data.
  • the acquisition time point corresponding to the target data value can be used as a reference point, and the original A video clip of a certain length of time (for example, 5-15s, etc.) before and/or after the reference point is selected in the video.
  • the process of obtaining target selection conditions corresponding to the exercise data may include:
  • the server 10 pre-stores multiple device identifications and selection conditions corresponding to each device identification.
  • the device identifications are configured to represent sports equipment, different sports equipments correspond to different equipment identifications, and the same sports equipment corresponds to the same equipment identification.
  • the equipment identification of the roller coaster is 1
  • the equipment identification of torrential advancement is 2
  • the equipment identification of the carousel is 3, etc.
  • the corresponding selection conditions are: the air pressure data value reaches the preset air pressure value
  • the acceleration data value reaches the preset acceleration
  • the value, position data value corresponds to the preset position, etc., as shown in Table 1 below:
  • the air pressure data value reaches the preset air pressure value 2
  • the acceleration data value reaches the preset acceleration value 3
  • the position data value corresponds to the preset position
  • the server 10 After the server 10 receives the original video and motion data sent by the shooting device 20, it first analyzes the motion data and determines the target device identifier corresponding to the motion data, for example, the target device identifier is 2.
  • the target selection condition corresponding to the motion data is determined from the multiple selection conditions.
  • the server 10 After the server 10 obtains the target device identifier corresponding to the motion data, it can obtain the target selection condition corresponding to the target device identifier. For example, if the target device identifier is 2, the target selection condition is that the acceleration data value reaches the preset acceleration value.
  • the process of obtaining target selection conditions corresponding to the exercise data may include:
  • the server 10 pre-stores multiple equipment types and selection conditions corresponding to each equipment type.
  • the equipment type refers to the type of each sports equipment.
  • Amusement equipment in the amusement park can be classified in advance to obtain all equipment types, for example, amusement park
  • the amusement equipment in, including roller coasters, pirate ships, torrents, jumping machines, carousels and flying chairs, you can get 3 types of equipment: equipment with large changes in height, equipment with large acceleration changes, and rotating equipment; then, set each A selection condition corresponding to each type of equipment, for example, equipment with large height changes, equipment with large acceleration changes, and rotating equipment.
  • the selection conditions corresponding to the three types of equipment are: air pressure data value reaches the preset air pressure value, acceleration The data value reaches the preset acceleration value, the position data value corresponds to the preset position, etc., as shown in Table 2 below:
  • the air pressure data value reaches the preset air pressure value Equipment with large acceleration changes
  • the acceleration data value reaches the preset acceleration value Rotating equipment
  • the position data value corresponds to the preset position
  • the server 10 After the server 10 obtains the motion data sent by the photographing device 20, it may obtain the target device type corresponding to the motion data based on the device types that have been classified.
  • the target selection condition corresponding to the motion data is determined from the multiple selection conditions.
  • the server 10 After the server 10 obtains the target device type corresponding to the exercise data, it can obtain the target selection condition corresponding to the target device type. For example, if the target device type is a device with a large altitude change, the target selection condition is that the air pressure data value reaches the preset air pressure. value.
  • the selection conditions corresponding to some equipment identifications or equipment types can include multiple, for example, the equipment identification of a roller coaster is 1, the equipment type is a device with a large height change, and the corresponding selection condition is: the air pressure data value reaches the expected value. Set the air pressure value, the gravity data value to reach the preset gravity value, and the acceleration data value to reach the preset acceleration value, etc. At the same time, in order to avoid abnormalities, when there are multiple selection conditions, you can set the priority for each selection condition according to the corresponding device ID or device type.
  • the device ID of a roller coaster is 1, and the corresponding selection condition is: air pressure
  • the data value reaches the preset air pressure value
  • the gravity data value reaches the preset gravity value
  • the acceleration data value reaches the preset acceleration value
  • the priority is sequentially reduced, and the target selection conditions are determined according to the priority during execution.
  • S1022 According to the target selection condition, locate the target data value from the motion data, and obtain the target time point corresponding to the target data value.
  • the target selection condition may include that the air pressure data value reaches the preset air pressure value, or the air pressure change rate of two adjacent air pressure data values reaches the preset air pressure change rate, or the position data value corresponds to the preset position, or the acceleration data value
  • the preset acceleration value is reached, or the difference between the consecutive preset number of acceleration data values and the gravitational acceleration is greater than the preset value, or the angular velocity data reaches the preset angular velocity value, or the accumulation of at least one angular velocity data value within the preset time The value reaches the preset value, etc.
  • the air pressure data may be collected by a barometer.
  • the air pressure data includes multiple air pressure data values and the collection time point corresponding to each air pressure data value.
  • the target selection condition is: the air pressure data value reaches The preset air pressure value, in this case, optionally, S1022 may include:
  • S1022-1 Locate a target air pressure data value that reaches a preset air pressure value from the air pressure data.
  • the preset air pressure value can be the air pressure value at which the sports equipment runs to the highest point or the lowest point, or the air pressure value when the sports equipment just starts to run.
  • S1022-2 Obtain a target time point corresponding to the target air pressure data value.
  • the air pressure data may be collected by a barometer.
  • the air pressure data includes multiple air pressure data values and the collection time points corresponding to each air pressure data value.
  • the target selection condition is: two adjacent ones
  • the air pressure change rate of the air pressure data value reaches the preset air pressure change rate.
  • S1022 may include:
  • S1022-3 Determine two adjacent air pressure data values whose air pressure change rate reaches a preset air pressure change rate from the multiple air pressure data values.
  • the air pressure change rate may be the increase value of the next air pressure data value compared to the previous air pressure data value in two adjacent air pressure data values.
  • the barometer collects data every 0.2s, so the collection time point at which the barometric pressure value changes the most can be used as the target time point, which usually corresponds to the lower position in the middle of the downslope.
  • the sports equipment is a roller coaster
  • each row of shooting devices 20 arranged on the roller coaster can determine the target time point in this way.
  • taking the maximum collection time point as the target time point can effectively avoid the situation that the roller coaster stops due to a failure of the roller coaster, which causes the target time point to be abnormal.
  • the air pressure data value detected by the barometer can be used to determine the target air pressure data value.
  • the barometer detects that the air pressure has decreased by 0.18 hpa within 10 seconds (equivalent to the rise of the roller coaster 2m), the reduced air pressure data value will be used as the target air pressure data value.
  • the position data when the motion data includes position data, the position data may be collected by a gyroscope.
  • the position data includes multiple position data values and the collection time points corresponding to each position data value.
  • the target selection condition is: the position data value corresponds to the preset Set the location.
  • S1022 may include:
  • S1022-6 Locate the target position data value corresponding to the preset position from the position data.
  • the preset location can be a location with beautiful scenery or a wide field of view that is convenient for taking pictures, or it can be a location when the sports equipment just starts running.
  • the acceleration data when the motion data includes acceleration data, the acceleration data may be collected by an acceleration sensor, and the acceleration data includes multiple acceleration data values and the collection time point corresponding to each acceleration data value.
  • the target selection condition is: the acceleration data value reaches the preset value. Set the acceleration value.
  • S1022 may include:
  • S1022-8 Locate a target acceleration data value that reaches a preset acceleration value from the acceleration data.
  • the preset acceleration may be the acceleration value when the sports equipment suddenly accelerates or decelerates, or it may be the acceleration value when the sports equipment just starts to run.
  • the acceleration data when the motion data includes acceleration data, the acceleration data may be collected by an acceleration sensor.
  • the acceleration data includes multiple acceleration data values and the collection time point corresponding to each acceleration data value.
  • the target selection condition is: a continuous preset number The difference between each of the acceleration data values and the acceleration of gravity is greater than the preset value.
  • S1022 may include:
  • S1022-10 From the multiple acceleration data values, it is determined that the difference between the acceleration data and the gravitational acceleration is greater than the preset value and the continuous preset number of acceleration data values are determined.
  • the maximum difference between the acceleration data value detected by the acceleration sensor and the gravitational acceleration g exceeds 1m/s 2 and reaches 6 times in a row.
  • the acceleration data corresponding to the sixth time will be regarded as the target acceleration data value.
  • the angular velocity data may be collected by a gyroscope.
  • the angular velocity data includes multiple angular velocity data values and the collection time point corresponding to each angular velocity data value.
  • the target selection condition is: the angular velocity data reaches a preset value
  • the angular velocity value optionally, in this case, S1022 may include:
  • the preset angular velocity value can be the angular velocity value of the sports equipment running to the farthest or the nearest to the rotating shaft, or it can be the air pressure value when the sports equipment just starts to operate.
  • the angular velocity data may be collected by a gyroscope.
  • the angular velocity data includes multiple angular velocity data values and the collection time point corresponding to each angular velocity data value.
  • the target selection condition is: at least one angular velocity data value The accumulated value within the preset time reaches the preset value.
  • S1022 may include:
  • S1022-15 Determine, from the multiple angular velocity data values, at least one angular velocity data value at which the accumulated value within the preset time reaches the preset value.
  • the last of the at least one angular velocity data value is used as the target angular velocity data value.
  • the angular velocity data value change detected by the gyroscope can be used to determine the target angular velocity data value.
  • the angular velocity data value of the carousel detected by the gyroscope is 20s If the accumulated value of at least one angular velocity data value reaches 1.2 rad/s, the last angular velocity data value within 20s is taken as the target angular velocity data value.
  • S1023 Based on the target time point, select a video clip with a preset duration before and/or after the target time point from the original video, to obtain at least one video clip.
  • the target data value that meets the preset conditions is located from the motion data, and after the target time point (for example, 12:01) corresponding to the target data value is obtained, due to the collection time of the motion data and the original video The shooting time is corresponding. Therefore, according to the target time point (for example, 12:01), the target time point (for example, 12:01) or before the target time point (for example, 12:01) can be selected from the original video.
  • a video clip of a preset duration for example, 10s
  • the preset duration can usually be set to 1 to 5s, and the cumulative duration of at least one video segment can be 10-20s, which can be flexibly set according to the actual situation, and is not limited here.
  • S103 Insert at least one video segment into a preset video template to obtain a composite video, where the video template includes at least one template segment, and the composite video includes at least one video segment and at least one template segment.
  • the number of the M blanks is consistent with the number of the selected at least one video clip
  • the cumulative duration of the M blanks is consistent with the cumulative duration of the selected at least one video clip, so that at least one video clip can be Insert into the M blanks to obtain a composite video.
  • the template fragments may be, but are not limited to, template videos, special effects pictures, subtitles, etc.
  • the template videos may be aerial videos of amusement parks or amusement equipment, for example, scenery videos of amusement parks, aerial videos of roller coaster tracks, and so on.
  • the M blanks in the video template can be set according to the rhythm of the background music, for example, please refer to Figure 4, according to the rhythm of the background music, determine at least one transition point, and set the video template according to the transition point For the blank position, one transition point corresponds to one blank.
  • the composite video includes at least one video segment and at least one template segment.
  • the composite video may also include a credit and at least one template segment, and the at least one video segment and at least one template segment are arranged between the credit and the trailer.
  • At least one video segment and at least one template segment in the composite video can be set at intervals, where the interval setting can be a one-to-one interval setting, for example, video segment 1, video segment 2, video segment 3, template segment in Figure 4 1.
  • Template fragment 2 one-to-one interval setting; it can also be one-to-many, many-to-one, many-to-many interval setting, for example, please refer to Figure 5, video fragment 1, video fragment 2, template fragment 1 one-to-two interval Set up.
  • the specific way of setting the interval can be flexibly set according to the actual situation, which is not limited here.
  • Fig. 6 is another flow diagram of the video editing method provided by this application. Please refer to Fig. 6. Before S102, the video editing method further includes:
  • S111 Perform face recognition on the original video, obtain the corresponding relationship between the face and the original video, and store it in the face database.
  • the server 10 may perform face recognition on the original video, for example, using a pre-trained face recognition model for face recognition to obtain the correspondence between the face and the original video .
  • the face can be represented by a multi-dimensional vector, for example, a 128-dimensional vector.
  • the server 10 can perform face detection on this piece of original video, and select the frame with the largest proportion of faces as the reference frame;
  • the reference frame performs face recognition, and other frames are matched with the reference frame. If they do not match, they are discarded.
  • the new original video frame sent by the photographing device 20 is subsequently received, and the reference frame can also be matched with the reference frame.
  • face matching repeat the above steps to establish a binding relationship between the original video and the face, that is, one face corresponds to one original video.
  • the reference frame is not static. If there is a video frame corresponding to the same face as the reference frame, and the proportion of the face of the video frame is greater than the proportion of the face of the reference frame, then the video frame will be used as the new reference frame .
  • the server 10 sequentially performs video editing, that is, executes S102 to S103 to obtain the synthesized video corresponding to each original video, that is, the synthesized video corresponding to each human face, and combines the original video and the synthesized video.
  • the corresponding relationship of the video is also stored in the face database, that is, the face database includes the corresponding relationship between the face and the original video, and the corresponding relationship between the original video and the synthesized video.
  • the video editing method further includes:
  • S112 Acquire a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image.
  • the applet or application program will first prompt the user to upload a face image, and the user can take a selfie through the mobile terminal 30 and upload the face image to the server 10 through the applet or application program.
  • S113 Perform face recognition on the face image to obtain a target face corresponding to the face image.
  • the server 10 after the server 10 receives the video acquisition request sent by the user through the mobile terminal 30, it can perform a face search on the face image in the video acquisition request, and determine the target composite video corresponding to the face in the face image. .
  • the server 10 may perform face recognition on the face image, for example, use a pre-trained face recognition model to perform face recognition to obtain a target face corresponding to the face image.
  • Vector representation for example, a 128-dimensional vector.
  • the server 10 performs face recognition on the face image sent by the mobile terminal 30, and after obtaining the target face corresponding to the face image, it may be based on the target face and the face and original face stored in the face database in advance.
  • the corresponding relationship of the video and the corresponding relationship between the original video and the synthesized video determine the target synthesized video corresponding to the target face.
  • S115 Send the target composite video to the mobile terminal, so that the mobile terminal displays the target composite video.
  • the server 10 can send the target composite video to the mobile terminal 30, for example, to a small program running under a third-party application installed in the mobile terminal 30, or to a small program installed in the mobile terminal 30.
  • the server 10 can send the target composite video to the mobile terminal 30, for example, to a small program running under a third-party application installed in the mobile terminal 30, or to a small program installed in the mobile terminal 30.
  • users can watch or download their own target composite video.
  • FIG. 7 is a schematic diagram of another flow chart of the video editing method provided by this application. Please refer to FIG. 7.
  • the video editing method further includes:
  • S121 Perform face recognition on the original video to obtain the correspondence between the face and the original video and store it in the face database, that is, the face database includes the correspondence between the face and the original video.
  • S122 Acquire a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image.
  • S123 Perform face recognition on the face image to obtain a target face vector corresponding to the face image.
  • the video editing method further includes:
  • S125 Send the composite video corresponding to the target original video to the mobile terminal, so that the mobile terminal displays the composite video corresponding to the target original video.
  • this application can automatically select highlights in the original video to generate a synthesized video based on the motion data of the sports equipment, thereby eliminating the need for manual participation and improving the efficiency of video editing;
  • the filming device 20 preprocesses the actual filmed video content to obtain the original video, thereby shortening the time period and reducing the amount of data transmission, and reducing the requirements for bandwidth and storage space;
  • the original video content shot by the shooting device 20 is single, boring, and not beautiful enough.
  • the server 10 selects highlights from the original video according to the motion data, and inserts the highlights into the preset video template to obtain rich and interesting images.
  • the composite video of background music, special effects pictures, landscape pictures, etc. makes the video content rich and vivid.
  • FIG. 8 shows a block diagram of functional modules of a video editing apparatus 100 provided by an embodiment of the present application.
  • the video editing device 100 is applied to the server 10, and the video editing device 100 includes: a receiving module 101, a selecting module 102 and a processing module 103.
  • the receiving module 101 is configured to receive the original video sent by the shooting device and the motion data of the sports device, where the motion data is collected by the sports data collection device.
  • the original video is obtained by preprocessing the captured video content by the shooting device 20; wherein, the step of preprocessing the captured video content by the shooting device 20 includes: the shooting device performs face detection on the video content to obtain The face area of each video frame in the video content; the shooting device calculates the aspect ratio of the face area of each video frame in each video frame, and deletes the video frames whose aspect ratio is less than the preset ratio to obtain the original video.
  • the original video is obtained by preprocessing the captured video content by the shooting device 20; wherein, the step of preprocessing the captured video content by the shooting device 20 includes: the shooting device performs face detection on the video content to obtain The face area of each video frame in the video content; the shooting device obtains the face pixel size corresponding to the face area of each video frame, and deletes the video frame whose face pixel size is less than the preset minimum face pixel size to obtain Original video.
  • the step of preprocessing the captured video content by the shooting device 20 further includes: the shooting device deletes overexposed or blurred video frames in the video content.
  • the selecting module 102 is configured to select at least one video segment from the original video according to the motion data.
  • the exercise data includes a plurality of data values and a collection time point corresponding to each data value; the selection module 102 is configured to: obtain target selection conditions corresponding to the exercise data; and locate the target data from the exercise data according to the target selection conditions And obtain the target time point corresponding to the target data value; based on the target time point, select a video clip with a preset duration before and/or after the target time point from the original video to obtain at least one video clip.
  • the server 10 pre-stores multiple device identifications and selection conditions corresponding to each device identification; the selection module 102 executes the method of acquiring the target selection conditions corresponding to the exercise data, including: analyzing the exercise data to determine the exercise data Corresponding target device identification; according to the target device identification, the target selection condition corresponding to the motion data is determined from a plurality of selection conditions.
  • the exercise data includes air pressure data
  • the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each air pressure data value
  • the target selection condition includes that the air pressure data value reaches a preset air pressure value
  • the selection module 102 executes the method of locating the target data value from the exercise data according to the target selection conditions, and obtaining the target time point corresponding to the target data value, including: locating the target air pressure data value that reaches the preset air pressure value from the air pressure data ; Obtain the target time point corresponding to the target air pressure data value.
  • the exercise data includes air pressure data
  • the air pressure data includes a plurality of air pressure data values and the collection time point corresponding to each air pressure data value
  • the target selection condition includes that the air pressure change rate of two adjacent air pressure data values reaches a preset air pressure change rate
  • the selection module 102 executes the method of locating the target data value from the exercise data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: determining the air pressure change from a plurality of air pressure data values The two adjacent air pressure data values whose rate reaches the preset air pressure change rate; the latter of the two adjacent air pressure data values is used as the target air pressure data value; and the target time point corresponding to the target air pressure data value is obtained.
  • the motion data includes position data
  • the position data includes a plurality of position data values and a collection time point corresponding to each position data value
  • the target selection condition includes a position data value corresponding to a preset position
  • the selection module 102 executes the selection according to the target selection condition .
  • the method of locating the target data value from the motion data and obtaining the target time point corresponding to the target data value includes: locating the target position data value corresponding to the preset position from the position data; obtaining the target corresponding to the target position data value Point in time.
  • the motion data includes acceleration data
  • the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each acceleration data value
  • the target selection condition includes that the acceleration data value reaches a preset acceleration value
  • the selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: locating the target acceleration data value that reaches the preset acceleration value from the acceleration data ; Obtain the target time point corresponding to the target acceleration data value.
  • the motion data includes acceleration data
  • the acceleration data includes a plurality of acceleration data values and the collection time point corresponding to each acceleration data value
  • the target selection condition includes a continuous preset number of acceleration data values and the difference between the acceleration data and the acceleration of gravity. Greater than the preset value
  • the selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: determining the difference between the acceleration data and the gravitational acceleration The difference is greater than the preset value and a continuous preset number of acceleration data values; the last of the preset number of acceleration data values is used as the target acceleration data value; and the target time point corresponding to the target acceleration data value is obtained.
  • the motion data includes angular velocity data
  • the angular velocity data includes multiple angular velocity data values and a collection time point corresponding to each angular velocity data value
  • the target selection condition includes that the angular velocity data reaches a preset angular velocity value
  • the selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: locating the target angular velocity that reaches the preset angular velocity value from the angular velocity data Data value: Get the target time point corresponding to the target angular velocity data value.
  • the motion data includes angular velocity data
  • the angular velocity data includes a plurality of angular velocity data values and the collection time point corresponding to each angular velocity data value
  • the target selection condition includes that the accumulated value of at least one angular velocity data value within a preset time reaches a preset value value
  • the selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: determining the preset time from a plurality of angular velocity data values At least one angular velocity data value whose accumulated value reaches the preset value; the last one of the at least one angular velocity data value is used as the target angular velocity data value; and the target time point corresponding to the target angular velocity data value is obtained.
  • the processing module 103 is configured to insert at least one video segment into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes at least one video segment and at least one template segment.
  • the video template further includes a credit card and a credit card, and at least one template segment is set between the credit card and the credit card;
  • the composite video further includes a credit card and a credit card, and at least one video segment and at least one template fragment are located between the credit card and the credit card.
  • the template segment includes at least one of a template video, a special effect picture, and a subtitle.
  • the server 10 establishes a face database in advance, and the processing module 103 is further configured to perform face recognition on the original video to obtain the corresponding relationship between the face and the original video and store it in the face database.
  • the face database includes the correspondence between the face and the original video, and the correspondence between the original video and the synthesized video;
  • the processing module 103 is also configured to: acquire a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image; perform face recognition on the face image to obtain a target face corresponding to the face image; based on the face database, Determine the target composite video corresponding to the target face; send the target composite video to the mobile terminal so that the mobile terminal displays the target composite video.
  • the server establishes a face database in advance
  • the processing module 103 is further configured to: perform face recognition on the original video to obtain the correspondence between the face and the original video and store it in the face database; obtain the video sent by the mobile terminal.
  • Request where the video acquisition request includes a face image; face recognition is performed on the face image to obtain the target face corresponding to the face image; based on the face database, the target original video corresponding to the target face is determined, and the target The original video is used as the original video, and the step of selecting at least one video segment from the original video according to the motion data is performed; the composite video corresponding to the target original video is sent to the mobile terminal, so that the mobile terminal displays the composite video corresponding to the target original video .
  • FIG. 9 shows a block diagram of functional modules of the server 10 provided by an embodiment of the present application.
  • the server 10 includes a processor 11, a memory 12 and a bus 13, and the processor 11 is connected to the memory 12 through the bus 13.
  • the memory 12 is configured to store programs, such as the video editing device 100 shown in FIG. 8.
  • the video editing device 100 includes at least one operating system that can be stored in the memory 12 in the form of software or firmware or solidified in the server 10. , The software function module in the OS).
  • the processor 11 executes the program to implement the video editing method disclosed in the foregoing embodiment.
  • the memory 12 may include a high-speed random access memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM).
  • RAM Random Access Memory
  • NVM non-volatile memory
  • the processor 11 may be an integrated circuit chip with signal processing capability. In the implementation process, the steps of the above method can be completed by an integrated logic circuit of hardware in the processor 11 or instructions in the form of software.
  • the aforementioned processor 11 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a microcontroller unit (Microcontroller Unit, MCU), a complex programmable logic device (Complex Programmable Logic Device, CPLD), and an on-site programmable logic device (CPLD). Programmable gate array (Field-Programmable Gate Array, FPGA), embedded ARM and other chips.
  • CPU Central Processing Unit
  • MCU microcontroller Unit
  • CPLD Complex Programmable Logic Device
  • CPLD on-site programmable logic device
  • Programmable gate array Field-Programmable Gate Array, FPGA
  • embedded ARM embedded ARM
  • the embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by the processor 11 to implement the video editing method disclosed in the above-mentioned embodiment.
  • the present application provides a video editing method, device, server, and computer-readable storage medium.
  • the method includes: receiving the original video sent by the shooting device and the motion data of the sports device, where the motion data is sports It is collected by a data collection device; at least one video segment is selected from the original video according to the motion data; at least one video segment is inserted into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes at least One video segment and at least one template segment.
  • the present application can automatically select highlights in the original video to generate a composite video according to the motion data of the sports equipment, thereby eliminating the need for manual participation and improving the efficiency of video editing.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of the code, and the module, program segment, or part of the code contains one or more functions for realizing the specified logical function. Executable instructions. It should also be noted that in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
  • the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes.
  • ROM read-only memory
  • RAM random access memory
  • relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply one of these entities or operations. There is any such actual relationship or order between.
  • the terms “include”, “include” or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the sentence "including a" does not exclude the existence of other identical elements in the process, method, article, or equipment that includes the element
  • This application provides a video editing method, device, server, and computer-readable storage medium.
  • the method includes: receiving the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the sports data collection device ; According to the motion data, select at least one video segment from the original video; insert at least one video segment into a preset video template to obtain a composite video, the video template includes at least one template segment, the composite video includes at least one video segment and at least A template fragment.
  • the present application can automatically select highlights in the original video to generate a composite video according to the motion data of the sports equipment, thereby eliminating the need for manual participation and improving the efficiency of video editing.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

The present application relates to the technical field of video processing, and provided therein are a video editing method, apparatus and server, and a computer-readable storage medium. The method comprises: receiving an original video sent by an image capture device and motion data of a moving device, the motion data being collected by a motion data collection apparatus; according to the motion data, selecting at least one video clip from the original video; inserting the at least one video clip into a preset video template to obtain a synthesized video, the video template comprising at least one template clip, and the synthesized video comprising the at least one video clip and the at least one template clip. In the present application, a highlight in the original video is automatically selected according to the motion data of the moving device so as to generate a synthesized video, thus there is no need for manual participation, and the efficiency of video editing is improved.

Description

视频编辑方法、装置、服务器及计算机可读存储介质Video editing method, device, server and computer readable storage medium
相关申请的交叉引用Cross-references to related applications
本申请要求于2019年12月05日提交的中国专利局的申请号为CN201911231580.4、名称为“视频编辑方法、装置、服务器及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed on December 05, 2019, with the Chinese Patent Office's application number CN201911231580.4 and titled "Video Editing Method, Device, Server, and Storage Medium", the entire content of which is incorporated by reference Incorporated in this application.
技术领域Technical field
本申请涉及视频处理技术领域，具体涉及一种视频编辑方法、装置、服务器及计算机可读存储介质。This application relates to the field of video processing technology, and in particular to a video editing method, device, server, and computer-readable storage medium.
背景技术Background technique
目前，游乐园会在游乐设备上安装拍摄设备，并在游客乘坐游乐设备的过程中，采用拍摄设备拍摄视频，并在拍摄完成后，从拍摄的视频中剪辑出的精彩片段，并将精彩片段拼接为一个组合视频，以此来帮助游客留下游玩过程中的精彩瞬间。但是，目前都是通过人工对原始视频进行观看，并且选取精彩瞬间剪辑成组合视频，这一过程需要耗费大量的人力和时间，导致效率低下。At present, the amusement park will install shooting equipment on the amusement equipment, and use the shooting equipment to shoot the video during the tourists riding on the amusement equipment, and after the shooting is completed, the highlights will be edited from the shot video and the highlights will be added. Stitched into a combined video to help visitors leave the wonderful moments in the play process. However, at present, the original video is manually watched, and the wonderful moments are selected to edit the combined video. This process requires a lot of manpower and time, resulting in low efficiency.
发明内容Summary of the invention
本申请的目的之一包括提供一种视频编辑方法、装置、服务器及计算机可读存储介质，以改善人工选取精彩视频瞬间进行视频编辑导致的效率低下等问题。One of the objectives of the present application includes providing a video editing method, device, server, and computer-readable storage medium to improve the inefficiency caused by manual selection of a wonderful video moment for video editing.
为了实现上述目的，本申请实施例采用的技术方案如下：In order to achieve the foregoing objectives, the technical solutions adopted in the embodiments of this application are as follows:
在本申请的第一方面，本申请提供了一种视频编辑方法，应用于服务器，所述服务器与拍摄设备通信连接，所述拍摄设备安装于运动设备上，所述拍摄设备包括运动数据采集装置，所述方法包括：接收所述拍摄设备发送的原始视频及所述运动设备的运动数据，其中，所述运动数据是所述运动数据采集装置采集的；依据所述运动数据，从所述原始视频中选取至少一个视频片段；将所述至少一个视频片段***到预设的视频模板中，得到合成视频，所述视频模板包括至少一个模板片段，所述合成视频包括至少一个视频片段和至少一个模板片段。In the first aspect of the present application, the present application provides a video editing method applied to a server, the server is in communication connection with a shooting device, the shooting device is installed on a sports device, and the shooting device includes a sports data collection device , The method includes: receiving the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the motion data collection device; according to the motion data, from the original Select at least one video segment from the video; insert the at least one video segment into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes at least one video segment and at least one Template fragment.
在一些可能的实施方式中，所述运动数据包括多个数据值及每个数据值对应的采集时间点；所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤，包括：获取所述运动数据对应的目标选取条件；按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点；基于所述目标时间点，从所述原始视频中选取所述目标时间点前和/或所述目标时间点后，持续预设时长的视频片段，得到所述至少一个视频片段。In some possible implementation manners, the motion data includes a plurality of data values and a collection time point corresponding to each data value; the step of selecting at least one video segment from the original video according to the motion data, The method includes: obtaining a target selection condition corresponding to the exercise data; according to the target selection condition, locating a target data value from the exercise data, and obtaining a target time point corresponding to the target data value; based on the target time Point, select from the original video before the target time point and/or after the target time point, and continue a video clip with a preset duration to obtain the at least one video clip.
在一些可能的实施方式中，所述服务器预先存储有多个设备标识及每个所述设备标识对应的选取条件；所述获取所述运动数据对应的目标选取条件的步骤，包括：对所述运动数据进行分析，确定出所述运动数据对应的目标设备标识；根据所述目标设备标识，从多个选取条件中确定出所述运动数据对应的目标选取条件。In some possible implementation manners, the server pre-stores a plurality of device identifications and selection conditions corresponding to each of the device identifications; the step of obtaining the target selection conditions corresponding to the exercise data includes: The motion data is analyzed to determine the target device identifier corresponding to the motion data; according to the target device identifier, the target selection condition corresponding to the motion data is determined from a plurality of selection conditions.
在一些可能的实施方式中，所述运动数据包括气压数据，所述气压数据包括多个气压数据值及每个所述气压数据值对应的采集时间点，所述目标选取条件包括气压数据值达到预设气压值；所述 按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述气压数据中定位出达到所述预设气压值的目标气压数据值；获取所述目标气压数据值对应的目标时间点。In some possible implementation manners, the exercise data includes air pressure data, the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each of the air pressure data values, and the target selection condition includes the air pressure data value reaching Preset air pressure value; the step of locating a target data value from the exercise data according to the target selection condition and obtaining the target time point corresponding to the target data value includes: locating from the air pressure data A target air pressure data value that reaches the preset air pressure value is output; and a target time point corresponding to the target air pressure data value is acquired.
在一些可能的实施方式中，所述运动数据包括气压数据，所述气压数据包括多个气压数据值及每个所述气压数据值对应的采集时间点，所述目标选取条件包括相邻两个气压数据值的气压变化率达到预设气压变化率；所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述多个气压数据值中，确定出气压变化率达到所述预设气压变化率的两个相邻气压数据值；将所述两个相邻气压数据值中的后一个作为目标气压数据值；获取所述目标气压数据值对应的目标时间点。In some possible implementation manners, the exercise data includes air pressure data, the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each air pressure data value, and the target selection condition includes two adjacent air pressure data values. The air pressure change rate of the air pressure data value reaches the preset air pressure change rate; the step of locating a target data value from the exercise data according to the target selection condition, and obtaining the target time point corresponding to the target data value, The method includes: determining, from the plurality of air pressure data values, two adjacent air pressure data values whose air pressure change rate reaches the preset air pressure change rate; and setting the latter of the two adjacent air pressure data values as a target Air pressure data value; obtaining the target time point corresponding to the target air pressure data value.
在一些可能的实施方式中，所述运动数据包括位置数据，所述位置数据包括多个位置数据值及每个所述位置数据值对应的采集时间点，所述目标选取条件包括位置数据值对应预设位置；所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述位置数据中定位出对应所述预设位置的目标位置数据值；获取所述目标位置数据值对应的目标时间点。In some possible implementation manners, the motion data includes position data, the position data includes a plurality of position data values and a collection time point corresponding to each position data value, and the target selection condition includes a position data value corresponding The preset position; the step of locating a target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, includes: locating from the position data The target position data value corresponding to the preset position; and the target time point corresponding to the target position data value is acquired.
在一些可能的实施方式中，所述运动数据包括加速度数据，所述加速度数据包括多个加速度数据值及每个所述加速度数据值对应的采集时间点，所述目标选取条件包括加速度数据值达到预设加速度值；所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述加速度数据中定位出达到所述预设加速度值的目标加速度数据值；获取所述目标加速度数据值对应的目标时间点。In some possible implementation manners, the motion data includes acceleration data, the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each acceleration data value, and the target selection condition includes that the acceleration data value reaches Preset acceleration value; the step of locating a target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, includes: locating from the acceleration data A target acceleration data value that reaches the preset acceleration value is obtained; and a target time point corresponding to the target acceleration data value is obtained.
在一些可能的实施方式中，所述运动数据包括加速度数据，所述加速度数据包括多个加速度数据值及每个所述加速度数据值对应的采集时间点，所述目标选取条件包括连续的预设数目个加速度数据值与重力加速度的差值均大于预设值；所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述多个加速度数据值中，确定出与所述重力加速度的差值均大于预设值且连续的预设数目个加速度数据值；将所述预设数目个加速度数据值中的最后一个作为目标加速度数据值；获取所述目标加速度数据值对应的目标时间点。In some possible implementation manners, the motion data includes acceleration data, the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each acceleration data value, and the target selection condition includes a continuous preset The difference between the number of acceleration data values and the gravitational acceleration is greater than a preset value; the target data value is located from the motion data according to the target selection condition, and the target time point corresponding to the target data value is obtained The step includes: determining, from the plurality of acceleration data values, that the difference with the acceleration of gravity is greater than a preset value and a continuous preset number of acceleration data values; and combining the preset number of acceleration data The last of the values is used as the target acceleration data value; the target time point corresponding to the target acceleration data value is obtained.
在一些可能的实施方式中，所述运动数据包括角速度数据，所述角速度数据包括多个角速度数据值及每个所述角速度数据值对应的采集时间点，所述目标选取条件包括角速度数据达到预设角速度值；所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述角速度数据中定位出达到所述预设角速度值的目标角速度数据值；获取所述目标角速度数据值对应的目标时间点。In some possible implementation manners, the motion data includes angular velocity data, the angular velocity data includes a plurality of angular velocity data values and a collection time point corresponding to each angular velocity data value, and the target selection condition includes that the angular velocity data reaches a predetermined value. Set the angular velocity value; the step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes: locating from the angular velocity data A target angular velocity data value that reaches the preset angular velocity value; and a target time point corresponding to the target angular velocity data value is acquired.
在一些可能的实施方式中，所述运动数据包括角速度数据，所述角速度数据包括多个角速度数据值及每个所述角速度数据值对应的采集时间点，所述目标选取条件包括至少一个角速度数据值在预设时间内的累加值达到预设值；所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：从所述多个角速度数据值中，确定出所述预设时间内的累加值达到预设值的至少一个角速度数据值；将所述至少一个角速度数据值中的最后一个作为目标角速度数据值；获取所述目标角速度数据值对应的目标时间点。In some possible implementation manners, the motion data includes angular velocity data, the angular velocity data includes a plurality of angular velocity data values and a collection time point corresponding to each angular velocity data value, and the target selection condition includes at least one angular velocity data The accumulated value of the value within a preset time reaches a preset value; the step of locating a target data value from the exercise data according to the target selection condition, and obtaining the target time point corresponding to the target data value, The method includes: determining, from the plurality of angular velocity data values, at least one angular velocity data value at which the accumulated value within the preset time reaches the preset value; and using the last one of the at least one angular velocity data value as the target angular velocity data Value; obtain the target time point corresponding to the target angular velocity data value.
在一些可能的实施方式中，所述服务器预先建立有人脸数据库，所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤之前，所述方法还包括：对所述原始视频进行人脸识别，得到人脸和所述原始视频的对应关系并存储到所述人脸数据库中。In some possible implementation manners, the server establishes a human face database in advance, and before the step of selecting at least one video segment from the original video according to the motion data, the method further includes: The video performs face recognition, and the corresponding relationship between the face and the original video is obtained and stored in the face database.
在一些可能的实施方式中，所述人脸数据库包括人脸和原始视频的对应关系、以及原始视频和合成视频的对应关系，所述服务器还与移动终端通信连接；所述将所述至少一个视频片段***到预设的视频模板中，得到合成视频的步骤之后，所述方法还包括：获取所述移动终端发送的视频获取请求，其中，所述视频获取请求包括人脸图像；对所述人脸图像进行人脸识别，得到所述人脸图像对应的目标人脸；基于所述人脸数据库，确定出所述目标人脸对应的目标合成视频；将所述目标合成视频发送至所述移动终端，以使所述移动终端显示所述目标合成视频。In some possible implementation manners, the face database includes a correspondence relationship between a face and an original video, and a correspondence relationship between an original video and a synthesized video, and the server is also communicatively connected to the mobile terminal; and the at least one After the video clip is inserted into the preset video template to obtain the composite video, the method further includes: obtaining a video obtaining request sent by the mobile terminal, wherein the video obtaining request includes a face image; Perform face recognition on the face image to obtain the target face corresponding to the face image; determine the target composite video corresponding to the target face based on the face database; send the target composite video to the A mobile terminal, so that the mobile terminal displays the target composite video.
在一些可能的实施方式中，所述服务器预先建立有人脸数据库，所述服务器还与移动终端通信连接；所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤之前，所述方法还包括：对所述原始视频进行人脸识别，得到人脸和所述原始视频的对应关系并存储到所述人脸数据库中；获取所述移动终端发送的视频获取请求，其中，所述视频获取请求包括人脸图像；对所述人脸图像进行人脸识别，得到所述人脸图像对应的目标人脸；基于所述人脸数据库，确定出所述目标人脸对应的目标原始视频，并将所述目标原始视频作为所述原始视频，执行所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤；所述将所述至少一个视频片段***到预设的视频模板中，得到合成视频的步骤之后，所述方法还包括：将所述目标原始视频对应的合成视频发送至所述移动终端，以使所述移动终端显示所述目标原始视频对应的合成视频。In some possible implementation manners, the server establishes a face database in advance, and the server is also communicatively connected to the mobile terminal; before the step of selecting at least one video segment from the original video according to the motion data, The method further includes: performing face recognition on the original video to obtain the corresponding relationship between the face and the original video and store it in the face database; obtaining the video acquisition request sent by the mobile terminal, wherein: The video acquisition request includes a face image; face recognition is performed on the face image to obtain a target face corresponding to the face image; based on the face database, a target corresponding to the target face is determined Original video, and use the target original video as the original video, and perform the step of selecting at least one video segment from the original video according to the motion data; and inserting the at least one video segment into In the preset video template, after the step of obtaining the composite video, the method further includes: sending the composite video corresponding to the target original video to the mobile terminal, so that the mobile terminal displays the target original video corresponding to the target original video. Composite video.
在一些可能的实施方式中，所述原始视频是所述拍摄设备对拍摄的视频内容进行预处理得到的；其中，所述拍摄设备对拍摄的视频内容进行预处理的步骤，包括：所述拍摄设备对所述视频内容进行人脸检测，得到所述视频内容中每一视频帧的人脸区域；所述拍摄设备计算所述每一视频帧的人脸区域在所述每一视频帧中的画面比例，并删除所述画面比例小于预设比例的视频帧，得到所述原始视频。In some possible implementation manners, the original video is obtained by preprocessing the captured video content by the shooting device; wherein, the step of preprocessing the captured video content by the shooting device includes: the shooting The device performs face detection on the video content to obtain the face area of each video frame in the video content; the shooting device calculates how much the face area of each video frame is in each video frame And delete the video frames with the aspect ratio less than the preset ratio to obtain the original video.
在一些可能的实施方式中，所述原始视频是所述拍摄设备对拍摄的视频内容进行预处理得到的；其中，所述拍摄设备对拍摄的视频内容进行预处理的步骤，包括：所述拍摄设备对所述视频内容进行人脸检测，得到所述视频内容中每一视频帧的人脸区域；所述拍摄设备获取所述每一视频帧的人脸区域对应的人脸像素尺寸，并删除所述人脸像素尺寸小于预设的最小人脸像素尺寸的视频帧，得到所述原始视频。In some possible implementation manners, the original video is obtained by preprocessing the captured video content by the shooting device; wherein, the step of preprocessing the captured video content by the shooting device includes: the shooting The device performs face detection on the video content to obtain the face area of each video frame in the video content; the shooting device obtains the face pixel size corresponding to the face area of each video frame, and deletes it A video frame whose face pixel size is smaller than a preset minimum face pixel size is used to obtain the original video.
在一些可能的实施方式中，所述拍摄设备对拍摄的视频内容进行预处理的步骤，还包括：所述拍摄设备删除所述视频内容中曝光过度或者模糊的视频帧。In some possible implementation manners, the step of preprocessing the captured video content by the photographing device further includes: the photographing device deletes overexposed or blurred video frames in the video content.
在一些可能的实施方式中，所述视频模板还包括片头和片尾，所述至少一个模板片段设置于所述片头和所述片尾之间；所述合成视频还包括所述片头和所述片尾，所述至少一个视频片段和所述至少一个模板片段设置于所述片头和所述片尾之间；所述模板片段包括模板视频、特效画面、字幕中的至少一种。In some possible implementation manners, the video template further includes a credit card and a credit card, the at least one template segment is arranged between the credit card and the credit card; the composite video further includes the credit card and the credit card, The at least one video segment and the at least one template segment are arranged between the title and the trailer; the template segment includes at least one of a template video, a special effect picture, and a subtitle.
在本申请的第二方面，本申请还提供了一种视频编辑装置，应用于服务器，所述服务器与拍摄设备通信连接，所述拍摄设备安装于运动设备上且包括运动数据采集装置，所述装置包括：接收模块，配置成接收所述拍摄设备发送的原始视频及所述运动设备的运动数据，其中，所述运动数据是 所述运动数据采集装置采集的；选取模块，配置成依据所述运动数据，从所述原始视频中选取至少一个视频片段；处理模块，配置成将所述至少一个视频片段***到预设的视频模板中，得到合成视频，所述视频模板包括至少一个模板片段，所述合成视频包括至少一个视频片段和至少一个模板片段。In the second aspect of the present application, the present application also provides a video editing device applied to a server, the server is in communication connection with a shooting device, the shooting device is installed on the sports equipment and includes a sports data collection device, the The device includes: a receiving module configured to receive the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the sports data collection device; and the selection module is configured to be based on the Motion data, selecting at least one video segment from the original video; a processing module configured to insert the at least one video segment into a preset video template to obtain a composite video, the video template including at least one template segment, The composite video includes at least one video segment and at least one template segment.
在本申请的第三方面，本申请还提供了一种服务器，所述服务器包括：一个或多个处理器；存储器，配置成存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现上述的视频编辑方法。In the third aspect of the present application, the present application also provides a server, the server includes: one or more processors; a memory configured to store one or more programs, when the one or more programs are When the one or more processors are executed, the one or more processors are caused to implement the above-mentioned video editing method.
在本申请的第四方面，本申请还提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述的视频编辑方法。In the fourth aspect of the present application, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned video editing method is realized.
基于上述任一方面，本申请提供的一种视频编辑方法、装置、服务器及计算机可读存储介质，通过拍摄设备拍摄原始视频，通过运动数据采集装置采集运动设备的运动数据，服务器在接收到拍摄设备发送的原始视频和运动数据后，根据运动数据从原始视频中选取出至少一个视频片段，并将至少一个视频片段***到预设的视频模板中得到合成视频，根据运动设备的运动数据自动选取原始视频中的精彩片段生成合成视频，从而无需人工参与，提高了视频编辑的效率。Based on any of the above aspects, the present application provides a video editing method, device, server, and computer-readable storage medium. The original video is captured by a shooting device, and the motion data of the sports device is collected by the motion data collection device. The server receives the shooting After the original video and motion data sent by the device, at least one video segment is selected from the original video according to the motion data, and at least one video segment is inserted into the preset video template to obtain a composite video, which is automatically selected according to the motion data of the sports device The highlights in the original video are generated into a composite video, which eliminates the need for human participation, which improves the efficiency of video editing.
为使本申请的上述目的、特征和优点能更明显易懂，下文特举可选实施例，并配合所附附图，作详细说明如下。In order to make the above objectives, features, and advantages of the present application more comprehensible, optional embodiments accompanied with accompanying drawings are described in detail below.
附图说明Description of the drawings
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application, and therefore do not It should be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative work.
图1示出了本申请实施例提供的视频编辑方法的应用场景示意图。Fig. 1 shows a schematic diagram of an application scenario of a video editing method provided by an embodiment of the present application.
图2示出了本申请实施例提供的视频编辑方法的一种流程示意图。Fig. 2 shows a schematic flowchart of a video editing method provided by an embodiment of the present application.
图3为图2示出的视频编辑方法中步骤S102的子步骤流程示意图。FIG. 3 is a schematic flowchart of sub-steps of step S102 in the video editing method shown in FIG. 2.
图4示出了本申请实施例提供的合成视频的一种示例图。Fig. 4 shows an example diagram of a composite video provided by an embodiment of the present application.
图5示出了本申请实施例提供的合成视频的另一种示例图。Fig. 5 shows another example diagram of a composite video provided by an embodiment of the present application.
图6示出了本申请实施例提供的视频编辑方法的另一种流程示意图。Fig. 6 shows another schematic flowchart of a video editing method provided by an embodiment of the present application.
图7示出了本申请实施例提供的视频编辑方法的另一种流程示意图。Fig. 7 shows another schematic flowchart of a video editing method provided by an embodiment of the present application.
图8示出了本申请实施例提供的视频编辑装置的功能模块框图。Fig. 8 shows a block diagram of functional modules of a video editing device provided by an embodiment of the present application.
图9示出了本申请实施例提供的服务器的功能模块框图。Fig. 9 shows a block diagram of functional modules of a server provided in an embodiment of the present application.
图标：10-服务器；20-拍摄设备；30-移动终端；21-运动数据采集装置；11-处理器；12-存储器；13-总线；100-视频编辑装置；101-接收模块；102-选取模块；103-处理模块。Icon: 10-server; 20-shooting equipment; 30-mobile terminal; 21-sports data acquisition device; 11-processor; 12-memory; 13-bus; 100-video editing device; 101-receiving module; 102-selection Module; 103-processing module.
具体实施方式Detailed ways
下面将结合本申请实施例中附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本申请 的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。基于本申请的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。The following describes the technical solutions in the embodiments of the present application clearly and completely with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present application.
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。同时，在本申请的描述中，术语“第一”、“第二”等仅用于区分描述，而不能理解为指示或暗示相对重要性。It should be noted that similar reference numerals and letters indicate similar items in the following figures. Therefore, once a certain item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.
请参照图1，图1示出了本申请实施例提供的视频编辑方法的应用场景示意图，包括服务器10、至少一个拍摄设备20及至少一个移动终端30，每个拍摄设备20均通过网络与服务器10通信连接，每个移动终端30均通过网络与服务器10通信连接，以实现服务器10与拍摄设备20之间、服务器10与移动终端30之间的数据通信或交互。Please refer to FIG. 1, which shows a schematic diagram of an application scenario of a video editing method provided by an embodiment of the present application, including a server 10, at least one photographing device 20, and at least one mobile terminal 30. Each photographing device 20 communicates with the server through a network. 10. Communication connection. Each mobile terminal 30 is connected to the server 10 through a network to realize data communication or interaction between the server 10 and the photographing device 20, and between the server 10 and the mobile terminal 30.
拍摄设备20安装于运动设备上，运动设备可以是极限运动项目的设备或者其他游乐项目等的设备，极限运动项目可以包括极限单车、低空跳伞、高速赛车、潜水、速降滑雪等，游乐项目可以包括过山车、风筝飞行器、海盗船、激流勇进、旋转木马等，下述实施例以游乐项目的设备为例进行说明。The photographing equipment 20 is installed on sports equipment. The sports equipment can be equipment for extreme sports or other amusement items. The extreme sports can include extreme cycling, low-altitude parachuting, high-speed racing, diving, downhill skiing, etc. The amusement items can be Including roller coasters, kite flying vehicles, pirate ships, torrents, carousels, etc. The following embodiments take the equipment of amusement projects as an example for description.
每个运动设备上均安装有至少一个拍摄设备20，拍摄设备20可以是运动相机、摄像头、安装有摄像头模组的设备等；每个拍摄设备20均包括运动数据采集装置21，运动数据采集装置21配置成当固定拍摄设备20的运动设备运动时采集运动设备的运动数据，运动数据采集装置21可以包括，但不限于气压计、陀螺仪、加速度传感器、速度传感器、重力传感器等。At least one shooting device 20 is installed on each sports equipment. The shooting device 20 can be a sports camera, a camera, a device equipped with a camera module, etc.; each shooting device 20 includes a sports data collection device 21, a sports data collection device 21 is configured to collect motion data of the motion device when the motion device of the fixed photographing device 20 moves. The motion data collection device 21 may include, but is not limited to, a barometer, a gyroscope, an acceleration sensor, a speed sensor, a gravity sensor, etc.
拍摄设备20配置成当游客乘坐游乐设备进行游玩时，为游客拍摄视频，并将拍摄的原始视频和运动数据采集装置21采集的运动数据发送至服务器10。The shooting device 20 is configured to shoot a video for the tourists when the tourists ride on the amusement device to play, and send the original video and the movement data collected by the movement data collecting device 21 to the server 10.
由于拍摄设备20在游乐设备上真实拍摄的视频内容时长较长、数据量大，同时可能包含部分效果不好的片段，例如，画面中没有人脸或者人脸不全等，因此，为了缩短时长且减小数据传输量，拍摄设备20需要将真实拍摄的视频内容进行预处理得到原始视频，也就是说，原始视频是拍摄设备20对真实拍摄的视频内容进行预处理后得到的。Since the video content actually shot by the shooting device 20 on the amusement device has a long time and a large amount of data, it may also contain some fragments with poor effects, for example, there are no human faces or incomplete faces in the picture. Therefore, in order to shorten the time and To reduce the amount of data transmission, the shooting device 20 needs to preprocess the actually shot video content to obtain the original video, that is, the original video is obtained after the shooting device 20 preprocesses the actually shot video content.
可选地，拍摄设备20对拍摄的视频内容进行预处理的过程，可以包括：首先，拍摄设备20对视频内容进行人脸检测，得到视频内容中每一视频帧的人脸区域；然后，拍摄设备20计算每一视频帧的人脸区域在每一视频帧中的画面比例，并删除画面比例小于预设比例(例如，10％)的视频帧，得到原始视频。也就是，拍摄设备20按照预设比例(例如，10％)，将人脸在画面中的比例低于该预设比例的视频帧删除，从而剪辑掉没有人脸或者人脸不全或者人脸角度不佳等的视频片段。Optionally, the process of preprocessing the captured video content by the shooting device 20 may include: first, the shooting device 20 performs face detection on the video content to obtain the face area of each video frame in the video content; then, shooting The device 20 calculates the aspect ratio of the face area of each video frame in each video frame, and deletes the video frames whose aspect ratio is less than a preset ratio (for example, 10%) to obtain the original video. That is, the shooting device 20 deletes the video frames whose face ratio is lower than the preset ratio in the screen according to a preset ratio (for example, 10%), so as to cut out no face or face incompleteness or face angle. Video clips of poor waiting.
可选地，拍摄设备20对拍摄的视频内容进行预处理的过程，可以包括：首先，拍摄设备20对视频内容进行人脸检测，得到视频内容中每一视频帧的人脸区域；然后，拍摄设备20获取每一视频帧的人脸区域对应的人脸像素尺寸，并删除人脸像素尺寸小于预设的最小人脸像素尺寸的视频帧，得到原始视频。也就是，拍摄设备20按照预设的最小人脸像素尺寸对拍摄的视频内容进行预处理，通常，拍摄设备20能够检测到的人脸框为一个正方形，正方形边长的最小值为视频帧短边长度的1/48，最小值不低于48像素，例如，视频帧为4096*3200像素，则最小人脸像素尺寸为66*66像素，将人脸像素尺寸低于最小人脸像素尺寸的视频帧删除。Optionally, the process of preprocessing the captured video content by the shooting device 20 may include: first, the shooting device 20 performs face detection on the video content to obtain the face area of each video frame in the video content; then, shooting The device 20 obtains the face pixel size corresponding to the face area of each video frame, and deletes the video frame whose face pixel size is less than the preset minimum face pixel size to obtain the original video. That is, the shooting device 20 preprocesses the captured video content according to the preset minimum face pixel size. Generally, the face frame that the shooting device 20 can detect is a square, and the minimum side length of the square is the short video frame. 1/48 of the side length, the minimum value is not less than 48 pixels, for example, if the video frame is 4096*3200 pixels, the minimum face pixel size is 66*66 pixels, and the face pixel size is lower than the minimum face pixel size Video frame deletion.
可选地，拍摄设备20对拍摄的视频内容进行预处理的过程，还可以包括质量筛选，也就是，拍 摄设备20删除视频内容中曝光过度或者模糊的视频帧。Optionally, the process of preprocessing the captured video content by the shooting device 20 may also include quality screening, that is, the shooting device 20 deletes overexposed or blurred video frames in the video content.
服务器10配置成接收拍摄设备20发送的原始视频和运动数据，并依据运动数据从原始视频中选取精彩片段，并将精彩片段***到预设的视频模板中得到合成视频；同时，服务器10还配置成在接收到移动终端30发送的视频获取请求时，获取与该视频获取请求对应的目标合成视频，并将目标合成视频发送至移动终端30。服务器10可以是单个服务器，也可以是服务器组。The server 10 is configured to receive the original video and motion data sent by the shooting device 20, select highlights from the original video according to the motion data, and insert the highlights into a preset video template to obtain a composite video; at the same time, the server 10 is also configured Upon receiving the video acquisition request sent by the mobile terminal 30, the target composite video corresponding to the video acquisition request is acquired, and the target composite video is sent to the mobile terminal 30. The server 10 may be a single server or a server group.
移动终端30配置成接收服务器10发送的目标合成视频，并对目标合成视频进行显示，以供用户选择。移动终端30可以是，但不限于智能手机、平板电脑、便携式笔记本电脑、台式电脑等。The mobile terminal 30 is configured to receive the target composite video sent by the server 10, and display the target composite video for the user to select. The mobile terminal 30 may be, but is not limited to, a smart phone, a tablet computer, a portable notebook computer, a desktop computer, and the like.
移动终端30中安装有第三方应用程序(Application，APP)，该第三方应用程序中可以运行有小程序，用户可以通过该小程序与服务器10进行交互，例如，用户在乘坐了游乐设备以后，可以通过该小程序观看或者下载自己的游玩视频。可选地，当用户通过移动终端30安装的第三方应用程序进入该小程序时，该小程序可以获取用户的人脸图像，并根据人脸图像与服务器10中的合成视频进行匹配，从而获取以用户为主角的目标合成视频，并显示该目标合成视频供用户观看、下载等。A third-party application (Application, APP) is installed in the mobile terminal 30. The third-party application can run a small program, and the user can interact with the server 10 through the small program. For example, after the user rides on the amusement device, You can watch or download your own play videos through this small program. Optionally, when the user enters the applet through a third-party application installed on the mobile terminal 30, the applet can obtain the user's face image, and match the face image with the composite video in the server 10 to obtain The target composite video with the user as the protagonist is displayed, and the target composite video is displayed for the user to watch, download, etc.
另外，还可以在移动终端30中安装应用程序，使得用户可以通过该应用程序与服务器10进行交互，实现以用户为主角的目标合成视频的观看、下载等。In addition, an application can also be installed in the mobile terminal 30, so that the user can interact with the server 10 through the application to realize the viewing and downloading of the target composite video with the user as the protagonist.
请参照图2，图2示出了本申请实施例提供的视频编辑方法的一种流程示意图，该视频编辑方法应用于服务器10，可以包括以下步骤：Please refer to FIG. 2. FIG. 2 shows a schematic flowchart of a video editing method provided by an embodiment of the present application. The video editing method is applied to the server 10 and may include the following steps:
S101，接收拍摄设备发送的原始视频及运动设备的运动数据，其中，运动数据是运动数据采集装置采集的。S101: Receive the original video sent by the shooting equipment and the motion data of the sports equipment, where the motion data is collected by the motion data collection device.
可选地，拍摄设备20固定安装在运动设备上，且确保一个拍摄设备20可以采集至少一个用户乘坐运动设备的视频，例如，运动设备为过山车，则每一排座位对应设置一个拍摄设备20，使得该拍摄设备20可以采集一排用户的游玩视频。拍摄设备20始终处于开启状态，当运动设备运动时，拍摄设备20拍摄用户的原始视频，运动数据采集装置21采集运动设备的运动数据，原始视频和运动数据的时间是对应的，也就是，同一个时间点的原始视频帧和运动数据值是对应的。Optionally, the shooting device 20 is fixedly installed on the sports equipment, and it is ensured that one shooting device 20 can capture the video of at least one user riding on the sports equipment. For example, if the sports equipment is a roller coaster, one shooting device 20 is provided for each row of seats. This allows the shooting device 20 to collect a row of users' play videos. The shooting device 20 is always on. When the sports device moves, the shooting device 20 captures the user's original video, and the motion data collection device 21 collects the motion data of the sports device. The original video and the time of the motion data correspond, that is, the same The original video frame and the motion data value at a time point are corresponding.
原始视频是拍摄设备20对拍摄的视频内容进行预处理得到的，且原始视频是以特定的至少一个用户为主角的，例如，过山车的一排座位设置一个拍摄设备20，对于其中一个拍摄设备20拍摄的原始视频，该原始视频是以该拍摄设备20对应的一排座位的一个或两个用户为主角的。原始视频可以是一段完整的视频，也可以是几段独立的小视频，通常，原始视频的时长可以是30s-1min。The original video is obtained by preprocessing the captured video content by the shooting device 20, and the original video is based on at least one specific user as the protagonist. For example, a row of seats of a roller coaster is provided with a shooting device 20, and for one of the shooting devices 20 The original video taken, and the original video takes one or two users in a row of seats corresponding to the shooting device 20 as the protagonists. The original video can be a complete video or several independent small videos. Generally, the length of the original video can be 30s-1min.
S102，依据运动数据，从原始视频中选取至少一个视频片段。S102: Select at least one video segment from the original video according to the motion data.
可选地，运动数据采集装置21采集的运动数据可以是气压数据、位置数据、加速度数据、速度数据、角速度数据、重力数据等中的一种或多种，同时，运动数据包括多个数据值及每个数据值对应的采集时间点。Optionally, the motion data collected by the motion data collection device 21 may be one or more of air pressure data, position data, acceleration data, velocity data, angular velocity data, gravity data, etc., and at the same time, the motion data includes multiple data values. And the collection time point corresponding to each data value.
从原始视频中选取的视频片段可以包括，但不限于运动设备刚开始运动时的视频片段或者能体现运动设备特点的视频片段等，例如，若运动设备为过山车、海盗船等高度变化较大的游乐设备，则可以选取过山车爬升到顶点开始俯冲时的视频片段；若运动设备为激流勇进、跳楼机等加速度变化较大的游乐设备，则可以选取突然加速时的视频片段；运动设备为旋转木马、飞椅等转动类的游乐设备，则可以选取到达指定位置(例如，风景美、视野开阔等的位置)时的视频片段等。显然，这些视频片段可以根据运动设备运行过程中的运动数据进行选取，例如，若运动设备为过山车，则 可以选取重力值最大或重力值最小时的视频片段等。The video clips selected from the original videos can include, but are not limited to, the video clips when the sports equipment just starts to move or the video clips that can reflect the characteristics of the sports equipment. For example, if the sports equipment is a roller coaster, a pirate ship, etc. Equipment, you can select the video clip when the roller coaster climbs to the apex and starts to dive; if the sports equipment is amusement equipment with large acceleration changes such as rapids, jumpers, etc., you can select the video clip at the sudden acceleration; the sports equipment is a carousel Rotating amusement equipment such as, flying chairs, etc., you can select video clips when arriving at a designated location (for example, a location with beautiful scenery, a wide field of view, etc.). Obviously, these video clips can be selected according to the movement data during the running of the sports device. For example, if the sports device is a roller coaster, the video clips with the largest or smallest gravity value can be selected.
可选地，依据运动数据，从原始视频中选取至少一个视频片段的方式，可以包括：首先，获取运动数据中达到设定值的数据值，或者与前一个/后一个数据值相比，出现大幅变化的数据值；然后，获取该数据值对应的采集时间点作为参考点，并从原始视频中选取参考点之前和/或之后一定时长(例如，5～15s等)的视频片段。Optionally, according to the motion data, the method of selecting at least one video segment from the original video may include: firstly, obtaining a data value in the motion data that reaches a set value, or comparing with the previous/next data value. A data value that changes significantly; then, the acquisition time point corresponding to the data value is obtained as a reference point, and a video clip of a certain length of time (for example, 5-15s, etc.) before and/or after the reference point is selected from the original video.
设定值可以是设定气压值、设定加速度值、设定角速度值等，例如，服务器10接收到拍摄设备20发送的原始视频和运动数据后，若运动数据中的某一数据值满足气压数据至达到设定气压值、或者加速度数据值达到设定加速度值、或者角速度数据值达到设定角速度值等，则根据该数据值对应的时间点进行视频片段选取。The set value can be a set air pressure value, a set acceleration value, a set angular velocity value, etc. For example, after the server 10 receives the original video and motion data sent by the shooting device 20, if a certain data value in the motion data satisfies the air pressure When the data reaches the set air pressure value, or the acceleration data value reaches the set acceleration value, or the angular velocity data value reaches the set angular velocity value, etc., the video clip is selected according to the time point corresponding to the data value.
可选地，请参照图3，S102可以包括：Optionally, referring to FIG. 3, S102 may include:
S1021，获取运动数据对应的目标选取条件。S1021: Obtain target selection conditions corresponding to the exercise data.
可选地，目标选取条件是指从运动数据中定位出目标数据值的条件，按照目标选取条件定位出目标数据值之后，可以将该目标数据值对应的采集时间点作为参考点，并从原始视频中选取参考点之前和/或之后一定时长(例如，5～15s等)的视频片段。Optionally, the target selection condition refers to the condition for locating the target data value from the motion data. After locating the target data value according to the target selection condition, the acquisition time point corresponding to the target data value can be used as a reference point, and the original A video clip of a certain length of time (for example, 5-15s, etc.) before and/or after the reference point is selected in the video.
可选地，获取运动数据对应的目标选取条件的过程，可以包括：Optionally, the process of obtaining target selection conditions corresponding to the exercise data may include:
首先，对运动数据进行分析，确定出运动数据对应的目标设备标识。First, analyze the exercise data to determine the target device identification corresponding to the exercise data.
服务器10预先存储有多个设备标识及每个设备标识对应的选取条件，设备标识配置成表征运动设备，不同运动设备对应不同设备标识，同一运动设备对应同一设备标识。例如，过山车的设备标识为1、激流勇进的设备标识为2、旋转木马的设备标识为3等，对应的选取条件依次为：气压数据值达到预设气压值、加速度数据值达到预设加速度值、位置数据值对应预设位置等，如下表1所示：The server 10 pre-stores multiple device identifications and selection conditions corresponding to each device identification. The device identifications are configured to represent sports equipment, different sports equipments correspond to different equipment identifications, and the same sports equipment corresponds to the same equipment identification. For example, the equipment identification of the roller coaster is 1, the equipment identification of torrential advancement is 2, the equipment identification of the carousel is 3, etc., and the corresponding selection conditions are: the air pressure data value reaches the preset air pressure value, and the acceleration data value reaches the preset acceleration The value, position data value corresponds to the preset position, etc., as shown in Table 1 below:
表1Table 1
设备标识Equipment Identity 选取条件Selection criteria
11 气压数据值达到预设气压值The air pressure data value reaches the preset air pressure value
22 加速度数据值达到预设加速度值The acceleration data value reaches the preset acceleration value
33 位置数据值对应预设位置The position data value corresponds to the preset position
服务器10接收到拍摄设备20发送的原始视频和运动数据后，首先对运动数据进行分析，确定出该运动数据对应的目标设备标识，例如，目标设备标识为2。After the server 10 receives the original video and motion data sent by the shooting device 20, it first analyzes the motion data and determines the target device identifier corresponding to the motion data, for example, the target device identifier is 2.
然后，根据目标设备标识，从多个选取条件中确定出运动数据对应的目标选取条件。Then, according to the target device identifier, the target selection condition corresponding to the motion data is determined from the multiple selection conditions.
服务器10得到运动数据对应的目标设备标识之后，就能得到该目标设备标识对应的目标选取条件，例如，目标设备标识为2，则目标选取条件为：加速度数据值达到预设加速度值。After the server 10 obtains the target device identifier corresponding to the motion data, it can obtain the target selection condition corresponding to the target device identifier. For example, if the target device identifier is 2, the target selection condition is that the acceleration data value reaches the preset acceleration value.
可选地，获取运动数据对应的目标选取条件的过程，可以包括：Optionally, the process of obtaining target selection conditions corresponding to the exercise data may include:
首先，获取运动数据对应的目标设备类型。First, get the target device type corresponding to the exercise data.
服务器10预先存储有多个设备类型及每个设备类型对应的选取条件，设备类型是指每个运动设备的类型，可以预先对游乐园中游乐设备进行分类得到所有的设备类型，例如，游乐园中的游乐设备包括过山车、海盗船、激流勇进、跳楼机、旋转木马和飞椅，则可以得到3种设备类型：高度变化大的设备、加速度变化大的设备、转动类设备；然后，设置每一种每个设备类型对应的选取条件， 例如，高度变化大的设备、加速度变化大的设备、转动类设备这3种设备类型对应的选取条件依次为：气压数据值达到预设气压值、加速度数据值达到预设加速度值、位置数据值对应预设位置等，如下表2所示：The server 10 pre-stores multiple equipment types and selection conditions corresponding to each equipment type. The equipment type refers to the type of each sports equipment. Amusement equipment in the amusement park can be classified in advance to obtain all equipment types, for example, amusement park The amusement equipment in, including roller coasters, pirate ships, torrents, jumping machines, carousels and flying chairs, you can get 3 types of equipment: equipment with large changes in height, equipment with large acceleration changes, and rotating equipment; then, set each A selection condition corresponding to each type of equipment, for example, equipment with large height changes, equipment with large acceleration changes, and rotating equipment. The selection conditions corresponding to the three types of equipment are: air pressure data value reaches the preset air pressure value, acceleration The data value reaches the preset acceleration value, the position data value corresponds to the preset position, etc., as shown in Table 2 below:
表2Table 2
设备类型Equipment type 选取条件Selection criteria
高度变化大的设备Highly variable equipment 气压数据值达到预设气压值The air pressure data value reaches the preset air pressure value
加速度变化大的设备Equipment with large acceleration changes 加速度数据值达到预设加速度值The acceleration data value reaches the preset acceleration value
转动类设备Rotating equipment 位置数据值对应预设位置The position data value corresponds to the preset position
服务器10在获取到拍摄设备20发送的运动数据之后，可以基于已有分类的设备类型，获取运动数据对应的目标设备类型。After the server 10 obtains the motion data sent by the photographing device 20, it may obtain the target device type corresponding to the motion data based on the device types that have been classified.
然后，根据目标设备类型，从多个选取条件中确定出运动数据对应的目标选取条件。Then, according to the type of the target device, the target selection condition corresponding to the motion data is determined from the multiple selection conditions.
服务器10获取到运动数据对应的目标设备类型之后，就能得到该目标设备类型对应的目标选取条件，例如，目标设备类型为高度变化大的设备，则目标选取条件为气压数据值达到预设气压值。After the server 10 obtains the target device type corresponding to the exercise data, it can obtain the target selection condition corresponding to the target device type. For example, if the target device type is a device with a large altitude change, the target selection condition is that the air pressure data value reaches the preset air pressure. value.
需要指出的是，某些设备标识或设备类型对应的选取条件可以包括多种，例如，过山车的设备标识为1、设备类型为高度变化大的设备，对应的选取条件为：气压数据值达到预设气压值、重力数据值达到预设重力值、加速度数据值达到预设加速度值等。同时，为了避免出现异常，当选取条件包括多种时，可以根据对应的设备标识或设备类型，为每种选取条件设置优先级，例如，过山车的设备标识为1，对应的选取条件为：气压数据值达到预设气压值、重力数据值达到预设重力值、加速度数据值达到预设加速度值，优先级依次降低，在执行时根据优先级确定目标选取条件。It should be pointed out that the selection conditions corresponding to some equipment identifications or equipment types can include multiple, for example, the equipment identification of a roller coaster is 1, the equipment type is a device with a large height change, and the corresponding selection condition is: the air pressure data value reaches the expected value. Set the air pressure value, the gravity data value to reach the preset gravity value, and the acceleration data value to reach the preset acceleration value, etc. At the same time, in order to avoid abnormalities, when there are multiple selection conditions, you can set the priority for each selection condition according to the corresponding device ID or device type. For example, the device ID of a roller coaster is 1, and the corresponding selection condition is: air pressure When the data value reaches the preset air pressure value, the gravity data value reaches the preset gravity value, and the acceleration data value reaches the preset acceleration value, the priority is sequentially reduced, and the target selection conditions are determined according to the priority during execution.
S1022，按照目标选取条件，从运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点。S1022: According to the target selection condition, locate the target data value from the motion data, and obtain the target time point corresponding to the target data value.
可选地，目标选取条件可以包括气压数据值达到预设气压值、或者相邻两个气压数据值的气压变化率达到预设气压变化率、或者位置数据值对应预设位置、或者加速度数据值达到预设加速度值、或者连续的预设数目个加速度数据值与重力加速度的差值均大于预设值、或者角速度数据达到预设角速度值、或者至少一个角速度数据值在预设时间内的累加值达到预设值等，下面对S1022的实现过程进行详细描述。Optionally, the target selection condition may include that the air pressure data value reaches the preset air pressure value, or the air pressure change rate of two adjacent air pressure data values reaches the preset air pressure change rate, or the position data value corresponds to the preset position, or the acceleration data value The preset acceleration value is reached, or the difference between the consecutive preset number of acceleration data values and the gravitational acceleration is greater than the preset value, or the angular velocity data reaches the preset angular velocity value, or the accumulation of at least one angular velocity data value within the preset time The value reaches the preset value, etc. The implementation process of S1022 will be described in detail below.
可选地，当运动数据包括气压数据时，气压数据可以是气压计采集的，气压数据包括多个气压数据值及每个气压数据值对应的采集时间点，目标选取条件为：气压数据值达到预设气压值，在这种情况下，可选地，S1022可以包括：Optionally, when the exercise data includes air pressure data, the air pressure data may be collected by a barometer. The air pressure data includes multiple air pressure data values and the collection time point corresponding to each air pressure data value. The target selection condition is: the air pressure data value reaches The preset air pressure value, in this case, optionally, S1022 may include:
S1022-1，从气压数据中定位出达到预设气压值的目标气压数据值。S1022-1: Locate a target air pressure data value that reaches a preset air pressure value from the air pressure data.
预设气压值可以是运动设备运行到最高点或者最低点的气压值，也可以是运动设备刚开始运行时的气压值。The preset air pressure value can be the air pressure value at which the sports equipment runs to the highest point or the lowest point, or the air pressure value when the sports equipment just starts to run.
S1022-2，获取目标气压数据值对应的目标时间点。S1022-2: Obtain a target time point corresponding to the target air pressure data value.
可选地，当运动数据包括气压数据时，气压数据可以是气压计采集的，气压数据包括多个气压数据值及每个气压数据值对应的采集时间点，目标选取条件为：相邻两个气压数据值的气压变化率达到预设气压变化率，在这种情况下，可选地，S1022可以包括：Optionally, when the exercise data includes air pressure data, the air pressure data may be collected by a barometer. The air pressure data includes multiple air pressure data values and the collection time points corresponding to each air pressure data value. The target selection condition is: two adjacent ones The air pressure change rate of the air pressure data value reaches the preset air pressure change rate. In this case, optionally, S1022 may include:
S1022-3，从多个气压数据值中，确定出气压变化率达到预设气压变化率的两个相邻气压数据值。S1022-3: Determine two adjacent air pressure data values whose air pressure change rate reaches a preset air pressure change rate from the multiple air pressure data values.
气压变化率可以是，两个相邻气压数据值中后一个气压数据值相比于前一个气压数据值的增大值。The air pressure change rate may be the increase value of the next air pressure data value compared to the previous air pressure data value in two adjacent air pressure data values.
S1022-4，将两个相邻气压数据值中的后一个作为目标气压数据值。In S1022-4, the latter of the two adjacent air pressure data values is used as the target air pressure data value.
S1022-5，获取目标气压数据值对应的目标时间点。S1022-5: Obtain the target time point corresponding to the target air pressure data value.
例如，气压计每0.2s采集一次数据，故可以将气压值变化最大的采集时间点作为目标时间点，通常对应冲下斜坡的中间靠下方的位置。当运动设备为过山车时，设置于过山车上的每一排拍摄设备20均可以按照这种方式确定目标时间点。另外，按照最大的采集时间点作为目标时间点，可以有效避免因过山车故障停止，导致目标时间点异常的情况。For example, the barometer collects data every 0.2s, so the collection time point at which the barometric pressure value changes the most can be used as the target time point, which usually corresponds to the lower position in the middle of the downslope. When the sports equipment is a roller coaster, each row of shooting devices 20 arranged on the roller coaster can determine the target time point in this way. In addition, taking the maximum collection time point as the target time point can effectively avoid the situation that the roller coaster stops due to a failure of the roller coaster, which causes the target time point to be abnormal.
另外，对于过山车等高度变化较大的游乐设备，可以利用气压计检测到的气压数据值变化来确定目标气压数据值，例如气压计检测到气压在10s内减小了0.18hpa(相当于过山车上升了2m)，则将减小后的气压数据值作为目标气压数据值。In addition, for amusement equipment with large changes in altitude such as roller coasters, the air pressure data value detected by the barometer can be used to determine the target air pressure data value. For example, the barometer detects that the air pressure has decreased by 0.18 hpa within 10 seconds (equivalent to the rise of the roller coaster 2m), the reduced air pressure data value will be used as the target air pressure data value.
可选地，当运动数据包括位置数据，位置数据可以是陀螺仪采集的，位置数据包括多个位置数据值及每个位置数据值对应的采集时间点，目标选取条件为：位置数据值对应预设位置，可选地，在这种情况下，S1022可以包括：Optionally, when the motion data includes position data, the position data may be collected by a gyroscope. The position data includes multiple position data values and the collection time points corresponding to each position data value. The target selection condition is: the position data value corresponds to the preset Set the location. Optionally, in this case, S1022 may include:
S1022-6，从位置数据中定位出对应预设位置的目标位置数据值。S1022-6: Locate the target position data value corresponding to the preset position from the position data.
预设位置可以是风景优美或者视野开阔等便于拍照的位置，也可以是运动设备刚开始运行时的位置。The preset location can be a location with beautiful scenery or a wide field of view that is convenient for taking pictures, or it can be a location when the sports equipment just starts running.
S1022-7，获取目标位置数据值对应的目标时间点。S1022-7: Obtain the target time point corresponding to the target position data value.
可选地，当运动数据包括加速度数据，加速度数据可以是加速度传感器采集的，加速度数据包括多个加速度数据值及每个加速度数据值对应的采集时间点，目标选取条件为：加速度数据值达到预设加速度值，可选地，在这种情况下，S1022可以包括：Optionally, when the motion data includes acceleration data, the acceleration data may be collected by an acceleration sensor, and the acceleration data includes multiple acceleration data values and the collection time point corresponding to each acceleration data value. The target selection condition is: the acceleration data value reaches the preset value. Set the acceleration value. Optionally, in this case, S1022 may include:
S1022-8，从加速度数据中定位出达到预设加速度值的目标加速度数据值。S1022-8: Locate a target acceleration data value that reaches a preset acceleration value from the acceleration data.
预设加速度可以是运动设备突然加速或者突然减速时的加速度值，也可以是运动设备刚开始运行时的加速度值。The preset acceleration may be the acceleration value when the sports equipment suddenly accelerates or decelerates, or it may be the acceleration value when the sports equipment just starts to run.
S1022-9，获取目标加速度数据值对应的目标时间点。S1022-9: Obtain a target time point corresponding to the target acceleration data value.
可选地，当运动数据包括加速度数据，加速度数据可以是加速度传感器采集的，加速度数据包括多个加速度数据值及每个加速度数据值对应的采集时间点，目标选取条件为：连续的预设数目个加速度数据值与重力加速度的差值均大于预设值，可选地，在这种情况下，S1022可以包括：Optionally, when the motion data includes acceleration data, the acceleration data may be collected by an acceleration sensor. The acceleration data includes multiple acceleration data values and the collection time point corresponding to each acceleration data value. The target selection condition is: a continuous preset number The difference between each of the acceleration data values and the acceleration of gravity is greater than the preset value. Optionally, in this case, S1022 may include:
S1022-10，从多个加速度数据值中，确定出与重力加速度的差值均大于预设值且连续的预设数目个加速度数据值。S1022-10: From the multiple acceleration data values, it is determined that the difference between the acceleration data and the gravitational acceleration is greater than the preset value and the continuous preset number of acceleration data values are determined.
S1022-11，将预设数目个加速度数据值中的最后一个作为目标加速度数据值。S1022-11: Use the last of the preset number of acceleration data values as the target acceleration data value.
S1022-12，获取目标加速度数据值对应的目标时间点。S1022-12: Obtain a target time point corresponding to the target acceleration data value.
例如，对于海盗船等加速度变化较大的游乐设备，利用加速度传感器检测到加速度数据值相比于重力加速度g(约9.8m/s 2)的最大差值均超过1m/s 2且连续达到6次，则将第6次对应的加速度数据作为目标加速度数据值。 For example, for amusement equipment with large acceleration changes such as pirate ships, the maximum difference between the acceleration data value detected by the acceleration sensor and the gravitational acceleration g (about 9.8m/s 2 ) exceeds 1m/s 2 and reaches 6 times in a row. , The acceleration data corresponding to the sixth time will be regarded as the target acceleration data value.
可选地，当运动数据包括角速度数据，角速度数据可以是陀螺仪采集的，角速度数据包括多个 角速度数据值及每个角速度数据值对应的采集时间点，目标选取条件为：角速度数据达到预设角速度值，可选地，在这种情况下，S1022可以包括：Optionally, when the motion data includes angular velocity data, the angular velocity data may be collected by a gyroscope. The angular velocity data includes multiple angular velocity data values and the collection time point corresponding to each angular velocity data value. The target selection condition is: the angular velocity data reaches a preset value The angular velocity value, optionally, in this case, S1022 may include:
S1022-13，从角速度数据中定位出达到预设角速度值的目标角速度数据值。S1022-13, locate the target angular velocity data value that reaches the preset angular velocity value from the angular velocity data.
预设角速度值可以是运动设备运行到离转轴最远或最近的角速度值，也可以是运动设备刚开始运行时的气压值。The preset angular velocity value can be the angular velocity value of the sports equipment running to the farthest or the nearest to the rotating shaft, or it can be the air pressure value when the sports equipment just starts to operate.
S1022-14，获取目标角速度数据值对应的目标时间点。S1022-14: Obtain the target time point corresponding to the target angular velocity data value.
可选地，当运动数据包括角速度数据，角速度数据可以是陀螺仪采集的，角速度数据包括多个角速度数据值及每个角速度数据值对应的采集时间点，目标选取条件为：至少一个角速度数据值在预设时间内的累加值达到预设值，可选地，在这种情况下，S1022可以包括：Optionally, when the motion data includes angular velocity data, the angular velocity data may be collected by a gyroscope. The angular velocity data includes multiple angular velocity data values and the collection time point corresponding to each angular velocity data value. The target selection condition is: at least one angular velocity data value The accumulated value within the preset time reaches the preset value. Optionally, in this case, S1022 may include:
S1022-15，从多个角速度数据值中，确定出预设时间内的累加值达到预设值的至少一个角速度数据值。S1022-15: Determine, from the multiple angular velocity data values, at least one angular velocity data value at which the accumulated value within the preset time reaches the preset value.
S1022-16，将至少一个角速度数据值中的最后一个作为目标角速度数据值。In S1022-16, the last of the at least one angular velocity data value is used as the target angular velocity data value.
S1022-17，获取目标角速度数据值对应的目标时间点。S1022-17: Obtain the target time point corresponding to the target angular velocity data value.
对于情侣飞车、旋转木马、旋转杯等角速度变化较大的游乐设备，可以利用陀螺仪检测到角速度数据值变化来确定目标角速度数据值，例如，利用陀螺仪检测到旋转木马的角速度数据值在20s内至少一个角速度数据值的累加值达到1.2rad/s，则将20s内的最后一个角速度数据值作为目标角速度数据值。For amusement equipment with large angular velocity changes such as lovers' speed, carousel, revolving cup, etc., the angular velocity data value change detected by the gyroscope can be used to determine the target angular velocity data value. For example, the angular velocity data value of the carousel detected by the gyroscope is 20s If the accumulated value of at least one angular velocity data value reaches 1.2 rad/s, the last angular velocity data value within 20s is taken as the target angular velocity data value.
S1023，基于目标时间点，从原始视频中选取目标时间点前和/或目标时间点后，持续预设时长的视频片段，得到至少一个视频片段。S1023: Based on the target time point, select a video clip with a preset duration before and/or after the target time point from the original video, to obtain at least one video clip.
可选地，从运动数据中定位出满足预设条件的目标数据值，并获取到该目标数据值对应的目标时间点(例如，12:01)之后，由于运动数据的采集时间和原始视频的拍摄时间是对应的，因此，可以根据该目标时间点(例如，12:01)，从原始视频中选取目标时间点(例如，12:01)前、或者目标时间点(例如，12:01)后、或者目标时间点(例如，12:01)前和目标时间点(例如，12:01)后，持续预设时长(例如，10s)的视频片段，得到至少一个视频片段，例如，11:56～12:01的视频片段、或者12:01～12:06的视频片段、或者11:56～12:01和12:01～12:06的视频片段。Optionally, the target data value that meets the preset conditions is located from the motion data, and after the target time point (for example, 12:01) corresponding to the target data value is obtained, due to the collection time of the motion data and the original video The shooting time is corresponding. Therefore, according to the target time point (for example, 12:01), the target time point (for example, 12:01) or before the target time point (for example, 12:01) can be selected from the original video. After, or before the target time point (for example, 12:01) and after the target time point (for example, 12:01), last a video clip of a preset duration (for example, 10s) to obtain at least one video clip, for example, 11: A video clip of 56 to 12:01, or a video clip of 12:01 to 12:06, or a video clip of 11:56 to 12:01 and 12:01 to 12:06.
预设时长通常可以设置为1～5s，至少一个视频片段的累积时长可以是10-20s，可以根据实际情况灵活设置，在此不做限定。The preset duration can usually be set to 1 to 5s, and the cumulative duration of at least one video segment can be 10-20s, which can be flexibly set according to the actual situation, and is not limited here.
S103，将至少一个视频片段***到预设的视频模板中，得到合成视频，视频模板包括至少一个模板片段，合成视频包括至少一个视频片段和至少一个模板片段。S103: Insert at least one video segment into a preset video template to obtain a composite video, where the video template includes at least one template segment, and the composite video includes at least one video segment and at least one template segment.
在本申请中，视频模板包括N个模板片段，N＝1,2,…，同时，视频模板还可以包括片头和片尾，N个模板片段设置于片头和片尾之间，且N个模板片段和片头、片尾形成M个留白，M＝1,2,…，该M个留白不是连续的。另外，该M个留白的数目与选取到的至少一个视频片段的数目一致、且该M个留白的累积时长与选取到的至少一个视频片段的累积时长一致，从而可以将至少一个视频片段***到该M个留白中，得到合成视频。In the present application, the video template includes N template fragments, N=1, 2,..., and at the same time, the video template may also include the opening and closing credits, the N template fragments are set between the opening and closing, and the N template fragments and The credits and credits form M blanks, M=1, 2,..., the M blanks are not continuous. In addition, the number of the M blanks is consistent with the number of the selected at least one video clip, and the cumulative duration of the M blanks is consistent with the cumulative duration of the selected at least one video clip, so that at least one video clip can be Insert into the M blanks to obtain a composite video.
可选地，模板片段可以是，但不限于模板视频、特效画面、字幕等，模板视频可以是游乐园或者游乐设备的航拍视频，例如，游乐园的风景视频、过山车轨道的航拍视频等。同时，视频模板中的M个留白可以是根据背景音乐的节奏设置的，例如，请参照图4，根据背景音乐的节奏，确定出 至少一个转场点，并根据转场点设置视频模板中留白的位置，一个转场点对应一个留白。Optionally, the template fragments may be, but are not limited to, template videos, special effects pictures, subtitles, etc. The template videos may be aerial videos of amusement parks or amusement equipment, for example, scenery videos of amusement parks, aerial videos of roller coaster tracks, and so on. At the same time, the M blanks in the video template can be set according to the rhythm of the background music, for example, please refer to Figure 4, according to the rhythm of the background music, determine at least one transition point, and set the video template according to the transition point For the blank position, one transition point corresponds to one blank.
可选地，合成视频包括至少一个视频片段和至少一个模板片段，同时，合成视频还可以包括片头和片尾，至少一个视频片段和至少一个模板片段设置于片头和片尾之间。合成视频中的至少一个视频片段和至少一个模板片段可以是间隔设置的，这里的间隔设置可以是一对一间隔设置，例如，图4中视频片段1、视频片段2、视频片段3、模板片段1、模板片段2一对一间隔设置；也可以是一对多、多对一、多对多间隔设置，例如，请参照图5，视频片段1、视频片段2、模板片段1一对二间隔设置。间隔设置的具体方式可以根据实际情况灵活设置，在此不做限定。Optionally, the composite video includes at least one video segment and at least one template segment. At the same time, the composite video may also include a credit and at least one template segment, and the at least one video segment and at least one template segment are arranged between the credit and the trailer. At least one video segment and at least one template segment in the composite video can be set at intervals, where the interval setting can be a one-to-one interval setting, for example, video segment 1, video segment 2, video segment 3, template segment in Figure 4 1. Template fragment 2 one-to-one interval setting; it can also be one-to-many, many-to-one, many-to-many interval setting, for example, please refer to Figure 5, video fragment 1, video fragment 2, template fragment 1 one-to-two interval Set up. The specific way of setting the interval can be flexibly set according to the actual situation, which is not limited here.
在一种可能的情形下，可选地，服务器10接收到拍摄设备20发送的原始视频后，可以对原始视频进行人脸识别，以建立人脸和原始视频的绑定关系，因此，在图2的基础上，图6为本申请提供的视频编辑方法的另一种流程示意图，请参照图6，在S102之前，该视频编辑方法还包括：In a possible situation, optionally, after the server 10 receives the original video sent by the shooting device 20, it can perform face recognition on the original video to establish a binding relationship between the face and the original video. Therefore, in the figure Based on 2, Fig. 6 is another flow diagram of the video editing method provided by this application. Please refer to Fig. 6. Before S102, the video editing method further includes:
S111，对原始视频进行人脸识别，得到人脸和原始视频的对应关系并存储到所述人脸数据库中。S111: Perform face recognition on the original video, obtain the corresponding relationship between the face and the original video, and store it in the face database.
可选地，服务器10接收到拍摄设备20发送的原始视频后，可以对原始视频进行人脸识别，例如，采用预先训练的人脸识别模型进行人脸识别，得到人脸和原始视频的对应关系，人脸可以用多维向量表示，例如，128维向量。Optionally, after the server 10 receives the original video sent by the shooting device 20, it may perform face recognition on the original video, for example, using a pre-trained face recognition model for face recognition to obtain the correspondence between the face and the original video , The face can be represented by a multi-dimensional vector, for example, a 128-dimensional vector.
可选地，服务器10在接收到拍摄设备20发送的一段原始视频后，首先，可以对这一段原始视频进行人脸检测，并选出人脸占比最大的一帧作为基准帧；然后，对基准帧进行人脸识别，并将其它帧均与该基准帧进行人脸匹配，若不匹配则丢弃，同时，后续接收到拍摄设备20发送的新的原始视频帧，也可以与该基准帧进行人脸匹配，重复上述步骤，建立原始视频和人脸的绑定关系，也就是，一个人脸对应一个原始视频。Optionally, after the server 10 receives a piece of original video sent by the shooting device 20, first, it can perform face detection on this piece of original video, and select the frame with the largest proportion of faces as the reference frame; The reference frame performs face recognition, and other frames are matched with the reference frame. If they do not match, they are discarded. At the same time, the new original video frame sent by the photographing device 20 is subsequently received, and the reference frame can also be matched with the reference frame. For face matching, repeat the above steps to establish a binding relationship between the original video and the face, that is, one face corresponds to one original video.
另外，基准帧并不是一成不变的，如果出现一个视频帧与基准帧对应同一个人脸，且该视频帧的人脸占比大于基准帧的人脸占比，则将该视频帧作为新的基准帧。In addition, the reference frame is not static. If there is a video frame corresponding to the same face as the reference frame, and the proportion of the face of the video frame is greater than the proportion of the face of the reference frame, then the video frame will be used as the new reference frame .
如此，服务器10每接收到一段拍摄设备20发送的原始视频，进行一次人脸匹配，得到人脸和原始视频的对应关系并存储到人脸数据库中。In this way, each time the server 10 receives a piece of the original video sent by the shooting device 20, it performs a face matching to obtain the corresponding relationship between the face and the original video and store it in the face database.
之后，针对每个人脸对应的原始视频，服务器10依次进行视频编辑，即执行S102～S103，得到每个原始视频对应的合成视频，也就是每个人脸对应的合成视频，并将原始视频和合成视频的对应关系也存储到人脸数据库中，即，人脸数据库包括人脸和原始视频的对应关系、以及原始视频和合成视频的对应关系。After that, for the original video corresponding to each face, the server 10 sequentially performs video editing, that is, executes S102 to S103 to obtain the synthesized video corresponding to each original video, that is, the synthesized video corresponding to each human face, and combines the original video and the synthesized video. The corresponding relationship of the video is also stored in the face database, that is, the face database includes the corresponding relationship between the face and the original video, and the corresponding relationship between the original video and the synthesized video.
同时，用户可以通过移动终端30观看或者下载自己的合成视频，因此，请参照图6，可选地，在S103之后，该视频编辑方法还包括：At the same time, the user can watch or download his own composite video through the mobile terminal 30. Therefore, please refer to FIG. 6. Optionally, after S103, the video editing method further includes:
S112，获取移动终端发送的视频获取请求，其中，视频获取请求包括人脸图像。S112: Acquire a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image.
可选地，用户在体验了运动设备后，如果想要观看或下载自己的合成视频，可以进入移动终端30中安装的第三方应用程序下运行的小程序、或者移动终端30中安装的应用程序等进行观看或下载；小程序或应用程序等首先会提示用户上传人脸图像，用户可以通过移动终端30进行自拍，得到人脸图像后通过小程序或应用程序等上传至服务器10。Optionally, after the user has experienced the sports equipment, if he wants to watch or download his own composite video, he can enter a small program running under a third-party application installed in the mobile terminal 30, or an application installed in the mobile terminal 30 The applet or application program will first prompt the user to upload a face image, and the user can take a selfie through the mobile terminal 30 and upload the face image to the server 10 through the applet or application program.
S113，对人脸图像进行人脸识别，得到人脸图像对应的目标人脸。S113: Perform face recognition on the face image to obtain a target face corresponding to the face image.
在本申请中，服务器10接收到用户通过移动终端30发送的视频获取请求后，可以视频获取请求中的人脸图像进行人脸搜索，确定出与人脸图像中的人脸对应的目标合成视频。In this application, after the server 10 receives the video acquisition request sent by the user through the mobile terminal 30, it can perform a face search on the face image in the video acquisition request, and determine the target composite video corresponding to the face in the face image. .
可选地，服务器10可以对该人脸图像进行人脸识别，例如，采用预先训练的人脸识别模型进行人脸识别，得到该人脸图像对应的目标人脸，该目标人脸以用多维向量表示，例如，128维向量。Optionally, the server 10 may perform face recognition on the face image, for example, use a pre-trained face recognition model to perform face recognition to obtain a target face corresponding to the face image. Vector representation, for example, a 128-dimensional vector.
S114，基于人脸数据库，确定出目标人脸对应的目标合成视频。S114: Based on the face database, determine the target composite video corresponding to the target face.
可选地，服务器10对移动终端30发送的人脸图像进行人脸识别，得到人脸图像对应的目标人脸后，可以基于该目标人脸、以及人脸数据库中预先存储的人脸和原始视频的对应关系以及原始视频和合成视频的对应关系，确定出该目标人脸对应的目标合成视频。Optionally, the server 10 performs face recognition on the face image sent by the mobile terminal 30, and after obtaining the target face corresponding to the face image, it may be based on the target face and the face and original face stored in the face database in advance. The corresponding relationship of the video and the corresponding relationship between the original video and the synthesized video determine the target synthesized video corresponding to the target face.
S115，将目标合成视频发送至移动终端，以使移动终端显示目标合成视频。S115: Send the target composite video to the mobile terminal, so that the mobile terminal displays the target composite video.
可选地，服务器10获取到目标合成视频之后，可以将目标合成视频发送至移动终端30，例如，发送至移动终端30中安装的第三方应用程序下运行的小程序、或者移动终端30中安装的应用程序等，以使移动终端显示目标合成视频，用户即可进行观看或下载自己的目标合成视频。Optionally, after the server 10 obtains the target composite video, it can send the target composite video to the mobile terminal 30, for example, to a small program running under a third-party application installed in the mobile terminal 30, or to a small program installed in the mobile terminal 30. In order to enable the mobile terminal to display the target composite video, users can watch or download their own target composite video.
在另一种可能的情形下，服务器10接收到拍摄设备20发送的原始视频后，可以对原始视频进行人脸识别，以建立人脸和原始视频的绑定关系，当用户想要通过移动终端30观看或者下载自己的游玩视频时，服务器10可以通过用户的人脸图像，找出用户的原始视频并进行视频编辑，得到用户的合成视频后发送至移动终端30，因此，在图2的基础上，图7为本申请提供的视频编辑方法的另一种流程示意图，请参照图7，可选地，在S102之前，该视频编辑方法还包括：In another possible situation, after the server 10 receives the original video sent by the shooting device 20, it can perform face recognition on the original video to establish a binding relationship between the face and the original video. When the user wants to use the mobile terminal 30 When watching or downloading its own play video, the server 10 can find the user’s original video and edit the video through the user’s face image, and then send the user’s composite video to the mobile terminal 30. Therefore, in the basis of Fig. 2 Above, FIG. 7 is a schematic diagram of another flow chart of the video editing method provided by this application. Please refer to FIG. 7. Optionally, before S102, the video editing method further includes:
S121，对原始视频进行人脸识别，得到人脸和原始视频的对应关系并存储到人脸数据库中，也就是，人脸数据库包括人脸和原始视频的对应关系。S121: Perform face recognition on the original video to obtain the correspondence between the face and the original video and store it in the face database, that is, the face database includes the correspondence between the face and the original video.
S122，获取移动终端发送的视频获取请求，其中，视频获取请求包括人脸图像。S122: Acquire a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image.
S123，对人脸图像进行人脸识别，得到人脸图像对应的目标人脸向量。S123: Perform face recognition on the face image to obtain a target face vector corresponding to the face image.
S124，基于人脸数据库，确定出目标人脸对应的目标原始视频。S124: Based on the face database, determine the target original video corresponding to the target face.
之后，对目标原始视频进行视频编辑，也就是，将目标原始视频作为原始视频执行S102～S103，得到目标原始视频对应的合成视频，并将该合成视频发送至请求视频的移动终端30，因此，请参照图7，在S103之后，该视频编辑方法还包括：Afterwards, perform video editing on the target original video, that is, perform S102 to S103 with the target original video as the original video to obtain a composite video corresponding to the target original video, and send the composite video to the mobile terminal 30 that requests the video. Therefore, Referring to FIG. 7, after S103, the video editing method further includes:
S125，将目标原始视频对应的合成视频发送至移动终端，以使移动终端显示目标原始视频对应的合成视频。S125: Send the composite video corresponding to the target original video to the mobile terminal, so that the mobile terminal displays the composite video corresponding to the target original video.
上述实施例的有益效果之一在于：One of the beneficial effects of the foregoing embodiment is:
首先，本申请能够根据运动设备的运动数据自动选取原始视频中的精彩片段生成合成视频，从而无需人工参与，提高了视频编辑的效率；First of all, this application can automatically select highlights in the original video to generate a synthesized video based on the motion data of the sports equipment, thereby eliminating the need for manual participation and improving the efficiency of video editing;
其次，拍摄设备20对真实拍摄的视频内容进行预处理得到原始视频，从而缩短时长且减小数据传输量，降低了对带宽和存储空间的要求；Secondly, the filming device 20 preprocesses the actual filmed video content to obtain the original video, thereby shortening the time period and reducing the amount of data transmission, and reducing the requirements for bandwidth and storage space;
第三，拍摄设备20拍摄的原始视频内容单一、枯燥、同时不够美观，服务器10依据运动数据从原始视频中选取精彩片段，并将精彩片段***到预设的视频模板中，得到画面丰富、有背景音乐、特效画面、风景画面等的合成视频，从而使视频内容丰富、生动。Third, the original video content shot by the shooting device 20 is single, boring, and not beautiful enough. The server 10 selects highlights from the original video according to the motion data, and inserts the highlights into the preset video template to obtain rich and interesting images. The composite video of background music, special effects pictures, landscape pictures, etc., makes the video content rich and vivid.
为了执行上述方法实施例及各个可能的实施方式中的相应步骤，下面给出一种可能的视频编辑装置的实现方式。请参照图8，图8示出了本申请实施例提供的视频编辑装置100的功能模块框图。视频编辑装置100应用于服务器10，该视频编辑装置100包括：接收模块101、选取模块102及处理模块103。In order to perform the corresponding steps in the foregoing method embodiments and various possible implementation manners, a possible implementation manner of the video editing apparatus is given below. Please refer to FIG. 8, which shows a block diagram of functional modules of a video editing apparatus 100 provided by an embodiment of the present application. The video editing device 100 is applied to the server 10, and the video editing device 100 includes: a receiving module 101, a selecting module 102 and a processing module 103.
接收模块101，配置成接收拍摄设备发送的原始视频及运动设备的运动数据，其中，运动数据是运动数据采集装置采集的。The receiving module 101 is configured to receive the original video sent by the shooting device and the motion data of the sports device, where the motion data is collected by the sports data collection device.
可选地，原始视频是拍摄设备20对拍摄的视频内容进行预处理得到的；其中，拍摄设备20对拍摄的视频内容进行预处理的步骤，包括：拍摄设备对视频内容进行人脸检测，得到视频内容中每一视频帧的人脸区域；拍摄设备计算每一视频帧的人脸区域在每一视频帧中的画面比例，并删除画面比例小于预设比例的视频帧，得到原始视频。Optionally, the original video is obtained by preprocessing the captured video content by the shooting device 20; wherein, the step of preprocessing the captured video content by the shooting device 20 includes: the shooting device performs face detection on the video content to obtain The face area of each video frame in the video content; the shooting device calculates the aspect ratio of the face area of each video frame in each video frame, and deletes the video frames whose aspect ratio is less than the preset ratio to obtain the original video.
可选地，原始视频是拍摄设备20对拍摄的视频内容进行预处理得到的；其中，拍摄设备20对拍摄的视频内容进行预处理的步骤，包括：拍摄设备对视频内容进行人脸检测，得到视频内容中每一视频帧的人脸区域；拍摄设备获取每一视频帧的人脸区域对应的人脸像素尺寸，并删除人脸像素尺寸小于预设的最小人脸像素尺寸的视频帧，得到原始视频。Optionally, the original video is obtained by preprocessing the captured video content by the shooting device 20; wherein, the step of preprocessing the captured video content by the shooting device 20 includes: the shooting device performs face detection on the video content to obtain The face area of each video frame in the video content; the shooting device obtains the face pixel size corresponding to the face area of each video frame, and deletes the video frame whose face pixel size is less than the preset minimum face pixel size to obtain Original video.
可选地，拍摄设备20对拍摄的视频内容进行预处理的步骤，还包括：拍摄设备删除视频内容中曝光过度或者模糊的视频帧。Optionally, the step of preprocessing the captured video content by the shooting device 20 further includes: the shooting device deletes overexposed or blurred video frames in the video content.
选取模块102，配置成依据运动数据，从原始视频中选取至少一个视频片段。The selecting module 102 is configured to select at least one video segment from the original video according to the motion data.
可选地，运动数据包括多个数据值及每个数据值对应的采集时间点；选取模块102配置成：获取运动数据对应的目标选取条件；按照目标选取条件，从运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点；基于目标时间点，从原始视频中选取目标时间点前和/或目标时间点后，持续预设时长的视频片段，得到至少一个视频片段。Optionally, the exercise data includes a plurality of data values and a collection time point corresponding to each data value; the selection module 102 is configured to: obtain target selection conditions corresponding to the exercise data; and locate the target data from the exercise data according to the target selection conditions And obtain the target time point corresponding to the target data value; based on the target time point, select a video clip with a preset duration before and/or after the target time point from the original video to obtain at least one video clip.
可选地，服务器10预先存储有多个设备标识及每个设备标识对应的选取条件；选取模块102执行获取运动数据对应的目标选取条件的方式，包括：对运动数据进行分析，确定出运动数据对应的目标设备标识；根据目标设备标识，从多个选取条件中确定出运动数据对应的目标选取条件。Optionally, the server 10 pre-stores multiple device identifications and selection conditions corresponding to each device identification; the selection module 102 executes the method of acquiring the target selection conditions corresponding to the exercise data, including: analyzing the exercise data to determine the exercise data Corresponding target device identification; according to the target device identification, the target selection condition corresponding to the motion data is determined from a plurality of selection conditions.
可选地，运动数据包括气压数据，气压数据包括多个气压数据值及每个气压数据值对应的采集时间点，目标选取条件包括气压数据值达到预设气压值；Optionally, the exercise data includes air pressure data, the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each air pressure data value, and the target selection condition includes that the air pressure data value reaches a preset air pressure value;
选取模块102执行按照目标选取条件，从运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点的方式，包括：从气压数据中定位出达到预设气压值的目标气压数据值；获取目标气压数据值对应的目标时间点。The selection module 102 executes the method of locating the target data value from the exercise data according to the target selection conditions, and obtaining the target time point corresponding to the target data value, including: locating the target air pressure data value that reaches the preset air pressure value from the air pressure data ; Obtain the target time point corresponding to the target air pressure data value.
可选地，运动数据包括气压数据，气压数据包括多个气压数据值及每个气压数据值对应的采集时间点，目标选取条件包括相邻两个气压数据值的气压变化率达到预设气压变化率；Optionally, the exercise data includes air pressure data, the air pressure data includes a plurality of air pressure data values and the collection time point corresponding to each air pressure data value, and the target selection condition includes that the air pressure change rate of two adjacent air pressure data values reaches a preset air pressure change rate;
选取模块102执行按照目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的方式，包括：从多个气压数据值中，确定出气压变化率达到预设气压变化率的两个相邻气压数据值；将两个相邻气压数据值中的后一个作为目标气压数据值；获取目标气压数据值对应的目标时间点。The selection module 102 executes the method of locating the target data value from the exercise data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: determining the air pressure change from a plurality of air pressure data values The two adjacent air pressure data values whose rate reaches the preset air pressure change rate; the latter of the two adjacent air pressure data values is used as the target air pressure data value; and the target time point corresponding to the target air pressure data value is obtained.
可选地，运动数据包括位置数据，位置数据包括多个位置数据值及每个位置数据值对应的采集时间点，目标选取条件包括位置数据值对应预设位置；选取模块102执行按照目标选取条件，从运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点的方式，包括：从位置数据中定位出对应预设位置的目标位置数据值；获取目标位置数据值对应的目标时间点。Optionally, the motion data includes position data, the position data includes a plurality of position data values and a collection time point corresponding to each position data value, and the target selection condition includes a position data value corresponding to a preset position; the selection module 102 executes the selection according to the target selection condition , The method of locating the target data value from the motion data and obtaining the target time point corresponding to the target data value includes: locating the target position data value corresponding to the preset position from the position data; obtaining the target corresponding to the target position data value Point in time.
可选地，运动数据包括加速度数据，加速度数据包括多个加速度数据值及每个加速度数据值对应的采集时间点，目标选取条件包括加速度数据值达到预设加速度值；Optionally, the motion data includes acceleration data, the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each acceleration data value, and the target selection condition includes that the acceleration data value reaches a preset acceleration value;
选取模块102执行按照目标选取条件，从运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点的方式，包括：从加速度数据中定位出达到预设加速度值的目标加速度数据值；获取目标加速度数据值对应的目标时间点。The selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: locating the target acceleration data value that reaches the preset acceleration value from the acceleration data ; Obtain the target time point corresponding to the target acceleration data value.
可选地，运动数据包括加速度数据，加速度数据包括多个加速度数据值及每个加速度数据值对应的采集时间点，目标选取条件包括连续的预设数目个加速度数据值与重力加速度的差值均大于预设值；Optionally, the motion data includes acceleration data, the acceleration data includes a plurality of acceleration data values and the collection time point corresponding to each acceleration data value, and the target selection condition includes a continuous preset number of acceleration data values and the difference between the acceleration data and the acceleration of gravity. Greater than the preset value;
选取模块102执行按照目标选取条件，从所述运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点的方式，包括：从多个加速度数据值中，确定出与重力加速度的差值均大于预设值且连续的预设数目个加速度数据值；将预设数目个加速度数据值中的最后一个作为目标加速度数据值；获取目标加速度数据值对应的目标时间点。The selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: determining the difference between the acceleration data and the gravitational acceleration The difference is greater than the preset value and a continuous preset number of acceleration data values; the last of the preset number of acceleration data values is used as the target acceleration data value; and the target time point corresponding to the target acceleration data value is obtained.
可选地，运动数据包括角速度数据，角速度数据包括多个角速度数据值及每个角速度数据值对应的采集时间点，目标选取条件包括角速度数据达到预设角速度值；Optionally, the motion data includes angular velocity data, the angular velocity data includes multiple angular velocity data values and a collection time point corresponding to each angular velocity data value, and the target selection condition includes that the angular velocity data reaches a preset angular velocity value;
选取模块102执行按照目标选取条件，从所述运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点的方式，包括：从角速度数据中定位出达到预设角速度值的目标角速度数据值；获取目标角速度数据值对应的目标时间点。The selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: locating the target angular velocity that reaches the preset angular velocity value from the angular velocity data Data value: Get the target time point corresponding to the target angular velocity data value.
可选地，运动数据包括角速度数据，角速度数据包括多个角速度数据值及每个角速度数据值对应的采集时间点，目标选取条件包括至少一个角速度数据值在预设时间内的累加值达到预设值；Optionally, the motion data includes angular velocity data, the angular velocity data includes a plurality of angular velocity data values and the collection time point corresponding to each angular velocity data value, and the target selection condition includes that the accumulated value of at least one angular velocity data value within a preset time reaches a preset value value;
选取模块102执行按照目标选取条件，从所述运动数据中定位出目标数据值，并获取目标数据值对应的目标时间点的方式，包括：从多个角速度数据值中，确定出预设时间内的累加值达到预设值的至少一个角速度数据值；将至少一个角速度数据值中的最后一个作为目标角速度数据值；获取目标角速度数据值对应的目标时间点。The selection module 102 executes the method of locating the target data value from the motion data according to the target selection condition, and obtaining the target time point corresponding to the target data value, including: determining the preset time from a plurality of angular velocity data values At least one angular velocity data value whose accumulated value reaches the preset value; the last one of the at least one angular velocity data value is used as the target angular velocity data value; and the target time point corresponding to the target angular velocity data value is obtained.
处理模块103，配置成将至少一个视频片段***到预设的视频模板中，得到合成视频，视频模板包括至少一个模板片段，合成视频包括至少一个视频片段和至少一个模板片段。The processing module 103 is configured to insert at least one video segment into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes at least one video segment and at least one template segment.
可选地，视频模板还包括片头和片尾，至少一个模板片段设置于片头和片尾之间；合成视频还包括片头和片尾，至少一个视频片段和至少一个模板片段设置于片头和片尾之间。Optionally, the video template further includes a credit card and a credit card, and at least one template segment is set between the credit card and the credit card; the composite video further includes a credit card and a credit card, and at least one video segment and at least one template fragment are located between the credit card and the credit card.
可选地，模板片段包括模板视频、特效画面、字幕中的至少一种。Optionally, the template segment includes at least one of a template video, a special effect picture, and a subtitle.
可选地，服务器10预先建立有人脸数据库，处理模块103还配置成：对原始视频进行人脸识别，得到人脸和原始视频的对应关系并存储到人脸数据库中。Optionally, the server 10 establishes a face database in advance, and the processing module 103 is further configured to perform face recognition on the original video to obtain the corresponding relationship between the face and the original video and store it in the face database.
可选地，人脸数据库包括人脸和原始视频的对应关系、以及原始视频和合成视频的对应关系；Optionally, the face database includes the correspondence between the face and the original video, and the correspondence between the original video and the synthesized video;
处理模块103还配置成：获取移动终端发送的视频获取请求，其中，视频获取请求包括人脸图像；对人脸图像进行人脸识别，得到人脸图像对应的目标人脸；基于人脸数据库，确定出目标人脸对应的目标合成视频；将目标合成视频发送至移动终端，以使移动终端显示目标合成视频。The processing module 103 is also configured to: acquire a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image; perform face recognition on the face image to obtain a target face corresponding to the face image; based on the face database, Determine the target composite video corresponding to the target face; send the target composite video to the mobile terminal so that the mobile terminal displays the target composite video.
可选地，服务器预先建立有人脸数据库，处理模块103还配置成：对原始视频进行人脸识别，得到人脸和原始视频的对应关系并存储到人脸数据库中；获取移动终端发送的视频获取请求，其中，视频获取请求包括人脸图像；对人脸图像进行人脸识别，得到人脸图像对应的目标人脸；基于人脸数据库，确定出目标人脸对应的目标原始视频，并将目标原始视频作为原始视频，执行依据所述运动数据，从原始视频中选取至少一个视频片段的步骤；将目标原始视频对应的合成视频发送至移动 终端，以使移动终端显示目标原始视频对应的合成视频。Optionally, the server establishes a face database in advance, and the processing module 103 is further configured to: perform face recognition on the original video to obtain the correspondence between the face and the original video and store it in the face database; obtain the video sent by the mobile terminal. Request, where the video acquisition request includes a face image; face recognition is performed on the face image to obtain the target face corresponding to the face image; based on the face database, the target original video corresponding to the target face is determined, and the target The original video is used as the original video, and the step of selecting at least one video segment from the original video according to the motion data is performed; the composite video corresponding to the target original video is sent to the mobile terminal, so that the mobile terminal displays the composite video corresponding to the target original video .
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的视频编辑装置100的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and conciseness of the description, the specific working process of the video editing apparatus 100 described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.
请参照图9，图9示出了本申请实施例提供的服务器10的功能模块框图。服务器10包括处理器11、存储器12及总线13，处理器11通过总线13与存储器12连接。Please refer to FIG. 9, which shows a block diagram of functional modules of the server 10 provided by an embodiment of the present application. The server 10 includes a processor 11, a memory 12 and a bus 13, and the processor 11 is connected to the memory 12 through the bus 13.
存储器12配置成存储程序，例如图8所示的视频编辑装置100，视频编辑装置100包括至少一个可以软件或固件(firmware)的形式存储于存储器12中或固化在服务器10的操作***(operating system，OS)中的软件功能模块，处理器11在接收到执行指令后，执行所述程序以实现上述实施例揭示的视频编辑方法。The memory 12 is configured to store programs, such as the video editing device 100 shown in FIG. 8. The video editing device 100 includes at least one operating system that can be stored in the memory 12 in the form of software or firmware or solidified in the server 10. , The software function module in the OS). After receiving the execution instruction, the processor 11 executes the program to implement the video editing method disclosed in the foregoing embodiment.
存储器12可能包括高速随机存取存储器(Random Access Memory，RAM)，也可能还包括非易失存储器(non-volatile memory，NVM)。The memory 12 may include a high-speed random access memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM).
处理器11可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器11中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器11可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、微控制单元(Microcontroller Unit，MCU)、复杂可编程逻辑器件(Complex Programmable Logic Device，CPLD)、现场可编程门阵列(Field－Programmable Gate Array，FPGA)、嵌入式ARM等芯片。The processor 11 may be an integrated circuit chip with signal processing capability. In the implementation process, the steps of the above method can be completed by an integrated logic circuit of hardware in the processor 11 or instructions in the form of software. The aforementioned processor 11 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a microcontroller unit (Microcontroller Unit, MCU), a complex programmable logic device (Complex Programmable Logic Device, CPLD), and an on-site programmable logic device (CPLD). Programmable gate array (Field-Programmable Gate Array, FPGA), embedded ARM and other chips.
本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器11执行时实现上述实施例揭示的视频编辑方法。The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by the processor 11 to implement the video editing method disclosed in the above-mentioned embodiment.
综上所述，本申请提供的一种视频编辑方法、装置、服务器及计算机可读存储介质，所述方法包括：接收拍摄设备发送的原始视频及运动设备的运动数据，其中，运动数据是运动数据采集装置采集的；依据运动数据，从原始视频中选取至少一个视频片段；将至少一个视频片段***到预设的视频模板中，得到合成视频，视频模板包括至少一个模板片段，合成视频包括至少一个视频片段和至少一个模板片段。与现有技术相比，本申请能够根据运动设备的运动数据自动选取原始视频中的精彩片段生成合成视频，从而无需人工参与，提高了视频编辑的效率。In summary, the present application provides a video editing method, device, server, and computer-readable storage medium. The method includes: receiving the original video sent by the shooting device and the motion data of the sports device, where the motion data is sports It is collected by a data collection device; at least one video segment is selected from the original video according to the motion data; at least one video segment is inserted into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes at least One video segment and at least one template segment. Compared with the prior art, the present application can automatically select highlights in the original video to generate a composite video according to the motion data of the sports equipment, thereby eliminating the need for manual participation and improving the efficiency of video editing.
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，附图中的流程图和框图显示了根据本申请的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。In the several embodiments provided in this application, it should be understood that the disclosed device and method may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions, and functions of the devices, methods, and computer program products according to multiple embodiments of the present application. operating. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of the code, and the module, program segment, or part of the code contains one or more functions for realizing the specified logical function. Executable instructions. It should also be noted that in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.
另外，在本申请各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的 部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. . It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply one of these entities or operations. There is any such actual relationship or order between. Moreover, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or equipment that includes the element.
以上所述仅为本申请的可选实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。The above descriptions are only optional embodiments of the application, and are not used to limit the application. For those skilled in the art, the application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection scope of this application. It should be noted that similar reference numerals and letters indicate similar items in the following figures. Therefore, once a certain item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
工业实用性Industrial applicability
本申请提供了一种视频编辑方法、装置、服务器及计算机可读存储介质，所述方法包括：接收拍摄设备发送的原始视频及运动设备的运动数据，其中，运动数据是运动数据采集装置采集的；依据运动数据，从原始视频中选取至少一个视频片段；将至少一个视频片段***到预设的视频模板中，得到合成视频，视频模板包括至少一个模板片段，合成视频包括至少一个视频片段和至少一个模板片段。与现有技术相比，本申请能够根据运动设备的运动数据自动选取原始视频中的精彩片段生成合成视频，从而无需人工参与，提高了视频编辑的效率。This application provides a video editing method, device, server, and computer-readable storage medium. The method includes: receiving the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the sports data collection device ; According to the motion data, select at least one video segment from the original video; insert at least one video segment into a preset video template to obtain a composite video, the video template includes at least one template segment, the composite video includes at least one video segment and at least A template fragment. Compared with the prior art, the present application can automatically select highlights in the original video to generate a composite video according to the motion data of the sports equipment, thereby eliminating the need for manual participation and improving the efficiency of video editing.

Claims (20)

  1. 一种视频编辑方法，其特征在于，应用于服务器，所述服务器与拍摄设备通信连接，所述拍摄设备安装于运动设备上且包括运动数据采集装置，所述方法包括：A video editing method, characterized in that it is applied to a server, the server is in communication connection with a shooting device, the shooting device is installed on the sports device and includes a sports data collection device, and the method includes:
    接收所述拍摄设备发送的原始视频及所述运动设备的运动数据，其中，所述运动数据是所述运动数据采集装置采集的；Receiving the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the sports data collection device;
    依据所述运动数据，从所述原始视频中选取至少一个视频片段；Selecting at least one video segment from the original video according to the motion data;
    将所述至少一个视频片段***到预设的视频模板中，得到合成视频，所述视频模板包括至少一个模板片段，所述合成视频包括所述至少一个视频片段和所述至少一个模板片段。The at least one video segment is inserted into a preset video template to obtain a composite video, the video template includes at least one template segment, and the composite video includes the at least one video segment and the at least one template segment.
  2. 如权利要求1所述的方法，其特征在于，所述运动数据包括多个数据值及每个数据值对应的采集时间点；The method of claim 1, wherein the exercise data includes a plurality of data values and a collection time point corresponding to each data value;
    所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤，包括：The step of selecting at least one video segment from the original video according to the motion data includes:
    获取所述运动数据对应的目标选取条件；Acquiring target selection conditions corresponding to the exercise data;
    按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点；Locate a target data value from the motion data according to the target selection condition, and obtain a target time point corresponding to the target data value;
    基于所述目标时间点，从所述原始视频中选取所述目标时间点前和/或所述目标时间点后，持续预设时长的视频片段，得到所述至少一个视频片段。Based on the target time point, a video clip with a preset duration is selected from the original video before the target time point and/or after the target time point to obtain the at least one video clip.
  3. 如权利要求2所述的方法，其特征在于，所述服务器预先存储有多个设备标识及每个所述设备标识对应的选取条件；3. The method of claim 2, wherein the server pre-stores a plurality of device identifiers and selection conditions corresponding to each of the device identifiers;
    所述获取所述运动数据对应的目标选取条件的步骤，包括：The step of obtaining target selection conditions corresponding to the exercise data includes:
    对所述运动数据进行分析，确定出所述运动数据对应的目标设备标识；Analyzing the exercise data to determine the target device identifier corresponding to the exercise data;
    根据所述目标设备标识，从多个选取条件中确定出所述运动数据对应的目标选取条件。According to the target device identifier, a target selection condition corresponding to the motion data is determined from a plurality of selection conditions.
  4. 如权利要求2所述的方法，其特征在于，所述运动数据包括气压数据，所述气压数据包括多个气压数据值及每个所述气压数据值对应的采集时间点，所述目标选取条件包括气压数据值达到预设气压值；The method of claim 2, wherein the exercise data includes air pressure data, the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each of the air pressure data values, and the target selection condition Including the air pressure data value reaching the preset air pressure value;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述气压数据中定位出达到所述预设气压值的目标气压数据值；Locate the target air pressure data value that reaches the preset air pressure value from the air pressure data;
    获取所述目标气压数据值对应的目标时间点。Obtain the target time point corresponding to the target air pressure data value.
  5. 如权利要求2所述的方法，其特征在于，所述运动数据包括气压数据，所述气压数据包括多个气压数据值及每个所述气压数据值对应的采集时间点，所述目标选取条件包括相邻两个气压数据值的气压变化率达到预设气压变化率；The method of claim 2, wherein the exercise data includes air pressure data, the air pressure data includes a plurality of air pressure data values and a collection time point corresponding to each of the air pressure data values, and the target selection condition The air pressure change rate including two adjacent air pressure data values reaches the preset air pressure change rate;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述多个气压数据值中，确定出气压变化率达到所述预设气压变化率的两个相邻气压数据值；From the multiple air pressure data values, determine two adjacent air pressure data values whose air pressure change rate reaches the preset air pressure change rate;
    将所述两个相邻气压数据值中的后一个作为目标气压数据值；Taking the latter of the two adjacent air pressure data values as the target air pressure data value;
    获取所述目标气压数据值对应的目标时间点。Obtain the target time point corresponding to the target air pressure data value.
  6. 如权利要求2所述的方法，其特征在于，所述运动数据包括位置数据，所述位置数据包括多 个位置数据值及每个所述位置数据值对应的采集时间点，所述目标选取条件包括位置数据值对应预设位置；The method according to claim 2, wherein the motion data includes position data, the position data includes a plurality of position data values and a collection time point corresponding to each of the position data values, and the target selection condition Including the position data value corresponding to the preset position;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述位置数据中定位出对应所述预设位置的目标位置数据值；Locate the target position data value corresponding to the preset position from the position data;
    获取所述目标位置数据值对应的目标时间点。Obtain the target time point corresponding to the target position data value.
  7. 如权利要求2所述的方法，其特征在于，所述运动数据包括加速度数据，所述加速度数据包括多个加速度数据值及每个所述加速度数据值对应的采集时间点，所述目标选取条件包括加速度数据值达到预设加速度值；The method of claim 2, wherein the motion data includes acceleration data, the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each of the acceleration data values, and the target selection condition Including acceleration data value reaching the preset acceleration value;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述加速度数据中定位出达到所述预设加速度值的目标加速度数据值；Locate the target acceleration data value that reaches the preset acceleration value from the acceleration data;
    获取所述目标加速度数据值对应的目标时间点。Obtain the target time point corresponding to the target acceleration data value.
  8. 如权利要求2所述的方法，其特征在于，所述运动数据包括加速度数据，所述加速度数据包括多个加速度数据值及每个所述加速度数据值对应的采集时间点，所述目标选取条件包括连续的预设数目个加速度数据值与重力加速度的差值均大于预设值；The method of claim 2, wherein the motion data includes acceleration data, the acceleration data includes a plurality of acceleration data values and a collection time point corresponding to each of the acceleration data values, and the target selection condition Including the continuous preset number of acceleration data values and the difference between the gravitational acceleration are greater than the preset value;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述多个加速度数据值中，确定出与所述重力加速度的差值均大于预设值且连续的预设数目个加速度数据值；From the plurality of acceleration data values, it is determined that the difference between the acceleration data and the acceleration of gravity is greater than a preset value and a preset number of consecutive acceleration data values are determined;
    将所述预设数目个加速度数据值中的最后一个作为目标加速度数据值；Taking the last one of the preset number of acceleration data values as the target acceleration data value;
    获取所述目标加速度数据值对应的目标时间点。Obtain the target time point corresponding to the target acceleration data value.
  9. 如权利要求2所述的方法，其特征在于，所述运动数据包括角速度数据，所述角速度数据包括多个角速度数据值及每个所述角速度数据值对应的采集时间点，所述目标选取条件包括角速度数据达到预设角速度值；The method of claim 2, wherein the motion data includes angular velocity data, the angular velocity data includes a plurality of angular velocity data values and a collection time point corresponding to each of the angular velocity data values, and the target selection condition Including the angular velocity data to reach the preset angular velocity value;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述角速度数据中定位出达到所述预设角速度值的目标角速度数据值；Locate the target angular velocity data value that reaches the preset angular velocity value from the angular velocity data;
    获取所述目标角速度数据值对应的目标时间点。Obtain the target time point corresponding to the target angular velocity data value.
  10. 如权利要求2所述的方法，其特征在于，所述运动数据包括角速度数据，所述角速度数据包括多个角速度数据值及每个所述角速度数据值对应的采集时间点，所述目标选取条件包括至少一个角速度数据值在预设时间内的累加值达到预设值；The method of claim 2, wherein the motion data includes angular velocity data, the angular velocity data includes a plurality of angular velocity data values and a collection time point corresponding to each of the angular velocity data values, and the target selection condition Including at least one angular velocity data value, the accumulated value within the preset time reaches the preset value;
    所述按照所述目标选取条件，从所述运动数据中定位出目标数据值，并获取所述目标数据值对应的目标时间点的步骤，包括：The step of locating a target data value from the motion data according to the target selection condition and obtaining the target time point corresponding to the target data value includes:
    从所述多个角速度数据值中，确定出所述预设时间内的累加值达到预设值的至少一个角速度数据值；From the plurality of angular velocity data values, determine at least one angular velocity data value at which the accumulated value within the preset time reaches the preset value;
    将所述至少一个角速度数据值中的最后一个作为目标角速度数据值；Taking the last one of the at least one angular velocity data value as the target angular velocity data value;
    获取所述目标角速度数据值对应的目标时间点。Obtain the target time point corresponding to the target angular velocity data value.
  11. 如权利要求1或2所述的方法，其特征在于，所述服务器预先建立有人脸数据库，所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤之前，所述方法还包括：The method of claim 1 or 2, wherein the server pre-establishes a human face database, and before the step of selecting at least one video segment from the original video according to the motion data, the method Also includes:
    对所述原始视频进行人脸识别，得到人脸和所述原始视频的对应关系并存储到所述人脸数据库中。Face recognition is performed on the original video, and the corresponding relationship between the face and the original video is obtained and stored in the face database.
  12. 如权利要求11所述的方法，其特征在于，所述人脸数据库包括人脸和原始视频的对应关系、以及原始视频和合成视频的对应关系，所述服务器还与移动终端通信连接；The method of claim 11, wherein the face database includes a correspondence relationship between a face and an original video, and a correspondence relationship between an original video and a synthesized video, and the server is also communicatively connected with the mobile terminal;
    所述将所述至少一个视频片段***到预设的视频模板中，得到合成视频的步骤之后，所述方法还包括：After the step of inserting the at least one video segment into a preset video template to obtain a composite video, the method further includes:
    获取所述移动终端发送的视频获取请求，其中，所述视频获取请求包括人脸图像；Acquiring a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image;
    对所述人脸图像进行人脸识别，得到所述人脸图像对应的目标人脸；Performing face recognition on the face image to obtain a target face corresponding to the face image;
    基于所述人脸数据库，确定出所述目标人脸对应的目标合成视频；Determine the target composite video corresponding to the target face based on the face database;
    将所述目标合成视频发送至所述移动终端，以使所述移动终端显示所述目标合成视频。The target composite video is sent to the mobile terminal, so that the mobile terminal displays the target composite video.
  13. 如权利要求1～12任意一项所述的方法，其特征在于，所述服务器预先建立有人脸数据库，所述服务器还与移动终端通信连接；The method according to any one of claims 1 to 12, wherein the server establishes a human face database in advance, and the server is also in communication connection with the mobile terminal;
    所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤之前，所述方法还包括：Before the step of selecting at least one video segment from the original video according to the motion data, the method further includes:
    对所述原始视频进行人脸识别，得到人脸和所述原始视频的对应关系并存储到所述人脸数据库中；Performing face recognition on the original video to obtain the corresponding relationship between the face and the original video and store it in the face database;
    获取所述移动终端发送的视频获取请求，其中，所述视频获取请求包括人脸图像；Acquiring a video acquisition request sent by the mobile terminal, where the video acquisition request includes a face image;
    对所述人脸图像进行人脸识别，得到所述人脸图像对应的目标人脸；Performing face recognition on the face image to obtain a target face corresponding to the face image;
    基于所述人脸数据库，确定出所述目标人脸对应的目标原始视频，并将所述目标原始视频作为所述原始视频，执行所述依据所述运动数据，从所述原始视频中选取至少一个视频片段的步骤；Based on the face database, the target original video corresponding to the target face is determined, and the target original video is taken as the original video. According to the motion data, at least selected from the original video is executed. The steps of a video clip;
    所述将所述至少一个视频片段***到预设的视频模板中，得到合成视频的步骤之后，所述方法还包括：After the step of inserting the at least one video segment into a preset video template to obtain a composite video, the method further includes:
    将所述目标原始视频对应的合成视频发送至所述移动终端，以使所述移动终端显示所述目标原始视频对应的合成视频。The composite video corresponding to the target original video is sent to the mobile terminal, so that the mobile terminal displays the composite video corresponding to the target original video.
  14. 如权利要求1～13任意一项所述的方法，其特征在于，所述原始视频是所述拍摄设备对拍摄的视频内容进行预处理得到的；The method according to any one of claims 1 to 13, wherein the original video is obtained by preprocessing the captured video content by the shooting device;
    其中，所述拍摄设备对拍摄的视频内容进行预处理的步骤，包括：Wherein, the step of preprocessing the captured video content by the shooting device includes:
    所述拍摄设备对所述视频内容进行人脸检测，得到所述视频内容中每一视频帧的人脸区域；Performing face detection on the video content by the shooting device to obtain the face area of each video frame in the video content;
    所述拍摄设备计算所述每一视频帧的人脸区域在所述每一视频帧中的画面比例，并删除所述画面比例小于预设比例的视频帧，得到所述原始视频。The shooting device calculates the aspect ratio of the face area of each video frame in each video frame, and deletes the video frames whose aspect ratio is less than a preset ratio to obtain the original video.
  15. 如权利要求1～14任意一项所述的方法，其特征在于，所述原始视频是所述拍摄设备对拍摄的视频内容进行预处理得到的；The method according to any one of claims 1 to 14, wherein the original video is obtained by preprocessing the captured video content by the shooting device;
    其中，所述拍摄设备对拍摄的视频内容进行预处理的步骤，包括：Wherein, the step of preprocessing the captured video content by the shooting device includes:
    所述拍摄设备对所述视频内容进行人脸检测，得到所述视频内容中每一视频帧的人脸区域；Performing face detection on the video content by the shooting device to obtain the face area of each video frame in the video content;
    所述拍摄设备获取所述每一视频帧的人脸区域对应的人脸像素尺寸，并删除所述人脸像素尺寸小于预设的最小人脸像素尺寸的视频帧，得到所述原始视频。The photographing device obtains the face pixel size corresponding to the face area of each video frame, and deletes video frames whose face pixel size is less than a preset minimum face pixel size to obtain the original video.
  16. 如权利要求14或15所述的方法，其特征在于，所述拍摄设备对拍摄的视频内容进行预处理的步骤，还包括：The method according to claim 14 or 15, wherein the step of preprocessing the captured video content by the shooting device further comprises:
    所述拍摄设备删除所述视频内容中曝光过度或者模糊的视频帧。The shooting device deletes overexposed or blurred video frames in the video content.
  17. 如权利要求1～16任意一项所述的方法，其特征在于，所述视频模板还包括片头和片尾，所述至少一个模板片段设置于所述片头和所述片尾之间；The method according to any one of claims 1 to 16, wherein the video template further comprises a credit and a credit, and the at least one template segment is set between the credit and the credit;
    所述合成视频还包括所述片头和所述片尾，所述至少一个视频片段和所述至少一个模板片段设置于所述片头和所述片尾之间；The composite video further includes the opening and the ending, and the at least one video segment and the at least one template segment are arranged between the opening and the ending;
    所述模板片段包括模板视频、特效画面、字幕中的至少一种。The template segment includes at least one of a template video, a special effect picture, and a subtitle.
  18. 一种视频编辑装置，其特征在于，应用于服务器，所述服务器与拍摄设备通信连接，所述拍摄设备安装于运动设备上且包括运动数据采集装置，所述装置包括：A video editing device, characterized in that it is applied to a server, the server is in communication connection with a shooting device, the shooting device is installed on the sports equipment and includes a sports data collection device, and the device includes:
    接收模块，配置成接收所述拍摄设备发送的原始视频及所述运动设备的运动数据，其中，所述运动数据是所述运动数据采集装置采集的；A receiving module configured to receive the original video sent by the shooting device and the motion data of the sports device, wherein the motion data is collected by the sports data collection device;
    选取模块，配置成依据所述运动数据，从所述原始视频中选取至少一个视频片段；A selection module configured to select at least one video segment from the original video according to the motion data;
    处理模块，配置成将所述至少一个视频片段***到预设的视频模板中，得到合成视频，所述视频模板包括至少一个模板片段，所述合成视频包括所述至少一个视频片段和所述至少一个模板片段。The processing module is configured to insert the at least one video segment into a preset video template to obtain a composite video, where the video template includes at least one template segment, and the composite video includes the at least one video segment and the at least one video segment. A template fragment.
  19. 一种服务器，其特征在于，所述服务器包括：A server, characterized in that the server includes:
    一个或多个处理器；One or more processors;
    存储器，配置成存储一个或多个程序，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如权利要求1-17中任一项所述的方法。The memory is configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any one of claims 1-17 The method described in the item.
  20. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该计算机程序被处理器执行时实现如权利要求1-17中任一项所述的方法。A computer-readable storage medium with a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1-17 when the computer program is executed by a processor.
PCT/CN2020/132585 2019-12-05 2020-11-30 Video editing method, apparatus and server, and computer readable storage medium WO2021109952A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911231580.4 2019-12-05
CN201911231580.4A CN110996112A (en) 2019-12-05 2019-12-05 Video editing method, device, server and storage medium

Publications (1)

Publication Number Publication Date
WO2021109952A1 true WO2021109952A1 (en) 2021-06-10

Family

ID=70090256

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/132585 WO2021109952A1 (en) 2019-12-05 2020-11-30 Video editing method, apparatus and server, and computer readable storage medium

Country Status (2)

Country Link
CN (1) CN110996112A (en)
WO (1) WO2021109952A1 (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110996112A (en) * 2019-12-05 2020-04-10 成都市喜爱科技有限公司 Video editing method, device, server and storage medium
CN111654619A (en) * 2020-05-18 2020-09-11 成都市喜爱科技有限公司 Intelligent shooting method and device, server and storage medium
CN112040278A (en) * 2020-09-16 2020-12-04 成都市喜爱科技有限公司 Video processing method and device, shooting terminal, server and storage medium
CN112203142A (en) * 2020-12-03 2021-01-08 浙江岩华文化科技有限公司 Video processing method and device, electronic device and storage medium
CN112702650A (en) * 2021-01-27 2021-04-23 成都数字博览科技有限公司 Blood donation promotion method and blood donation vehicle
CN115119044B (en) * 2021-03-18 2024-01-05 阿里巴巴新加坡控股有限公司 Video processing method, device, system and computer storage medium
CN114500826B (en) * 2021-12-09 2023-06-27 成都市喜爱科技有限公司 Intelligent shooting method and device and electronic equipment
CN114363712B (en) * 2022-01-13 2024-03-19 深圳迪乐普智能科技有限公司 AI digital person video generation method, device and equipment based on templated editing
CN115103206B (en) * 2022-06-16 2024-02-13 北京字跳网络技术有限公司 Video data processing method, device, equipment, system and storage medium
CN115278299B (en) * 2022-07-27 2024-03-19 腾讯科技（深圳）有限公司 Unsupervised training data generation method, device, medium and equipment

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050052532A1 (en) * 2003-09-08 2005-03-10 David Elooz System and method for filming and recording attractions
CN204425487U (en) * 2015-03-17 2015-06-24 百度在线网络技术（北京）有限公司 Flying Camera head unit, bicycle and system of riding
CN107281709A (en) * 2017-06-27 2017-10-24 深圳市酷浪云计算有限公司 The extracting method and device, electronic equipment of a kind of sport video fragment
CN108694737A (en) * 2018-05-14 2018-10-23 星视麒（北京）科技有限公司 The method and apparatus for making image
CN108769560A (en) * 2018-05-31 2018-11-06 广州富勤信息科技有限公司 The production method of medelling digitized video under a kind of high velocity environment
CN110121105A (en) * 2018-02-06 2019-08-13 上海全土豆文化传播有限公司 Editing video generation method and device
CN110418073A (en) * 2019-07-22 2019-11-05 富咖科技(大连)有限公司 A kind of video automatic collection and synthetic method for Karting
CN110996112A (en) * 2019-12-05 2020-04-10 成都市喜爱科技有限公司 Video editing method, device, server and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0535178A (en) * 1991-07-26 1993-02-12 Pioneer Electron Corp Recording and reproducing device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050052532A1 (en) * 2003-09-08 2005-03-10 David Elooz System and method for filming and recording attractions
CN204425487U (en) * 2015-03-17 2015-06-24 百度在线网络技术（北京）有限公司 Flying Camera head unit, bicycle and system of riding
CN107281709A (en) * 2017-06-27 2017-10-24 深圳市酷浪云计算有限公司 The extracting method and device, electronic equipment of a kind of sport video fragment
CN110121105A (en) * 2018-02-06 2019-08-13 上海全土豆文化传播有限公司 Editing video generation method and device
CN108694737A (en) * 2018-05-14 2018-10-23 星视麒（北京）科技有限公司 The method and apparatus for making image
CN108769560A (en) * 2018-05-31 2018-11-06 广州富勤信息科技有限公司 The production method of medelling digitized video under a kind of high velocity environment
CN110418073A (en) * 2019-07-22 2019-11-05 富咖科技(大连)有限公司 A kind of video automatic collection and synthetic method for Karting
CN110996112A (en) * 2019-12-05 2020-04-10 成都市喜爱科技有限公司 Video editing method, device, server and storage medium

Also Published As

Publication number Publication date
CN110996112A (en) 2020-04-10

Similar Documents

Publication Publication Date Title
WO2021109952A1 (en) Video editing method, apparatus and server, and computer readable storage medium
CN109326310B (en) Automatic editing method and device and electronic equipment
US10897659B2 (en) System and method for enhanced video image recognition using motion sensors
EP3488618B1 (en) Live video streaming services with machine-learning based highlight replays
US10157638B2 (en) Collage of interesting moments in a video
CN106162223B (en) News video segmentation method and device
US20180227482A1 (en) Scene-aware selection of filters and effects for visual digital media content
US20160225410A1 (en) Action camera content management system
CN107436921B (en) Video data processing method, device, equipment and storage medium
CN104123396B (en) A kind of abstract of football video generation method and device based on cloud TV
US8897603B2 (en) Image processing apparatus that selects a plurality of video frames and creates an image based on a plurality of images extracted and selected from the frames
CN105262942B (en) Distributed automatic image and video processing
US11640169B2 (en) Systems and methods for determining preferences for control settings of unmanned aerial vehicles
CN112312142B (en) Video playing control method and device and computer readable storage medium
CN110612721A (en) Video processing method and terminal equipment
US10958837B2 (en) Systems and methods for determining preferences for capture settings of an image capturing device
CN104660948A (en) Video recording method and device
CN105872601A (en) Video playing method, device and system
CN111241872A (en) Video image shielding method and device
CN105872537A (en) Video playing method, device and system
CN108540817B (en) Video data processing method, device, server and computer readable storage medium
CN112287771A (en) Method, apparatus, server and medium for detecting video event
CN110472562A (en) Position ball video clip detection method, device, system and storage medium
KR20160025474A (en) Determination method and device
CN108965859B (en) Projection mode identification method, video playing method and device and electronic equipment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20896610

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20896610

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09-03-2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20896610

Country of ref document: EP

Kind code of ref document: A1