CN109194978A - Live video clipping method, device and electronic equipment - Google Patents
Live video clipping method, device and electronic equipment Download PDFInfo
- Publication number
- CN109194978A CN109194978A CN201811198454.9A CN201811198454A CN109194978A CN 109194978 A CN109194978 A CN 109194978A CN 201811198454 A CN201811198454 A CN 201811198454A CN 109194978 A CN109194978 A CN 109194978A
- Authority
- CN
- China
- Prior art keywords
- live video
- picture frame
- editing
- object event
- video stream
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000003860 storage Methods 0.000 claims abstract description 16
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 210000003813 thumb Anatomy 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- H04N21/23—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
-
- 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
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- 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
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
- H04N21/8547—Content authoring involving timestamps for synchronizing content
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The present invention provides a kind of live video clipping method, and the picture frame by obtaining live video stream carries out image recognition, determines the first picture frame of object event occur；The timestamp for extracting first picture frame obtains the editing position of video clipping according to the timestamp；According to the editing position, editing goes out target video segment from the live video stream, obtains the technical solution of target video segment.The present invention also provides the device, electronic equipment and the computer readable storage mediums that execute above-mentioned live video clipping method.The live video clipping method, device, electronic equipment and computer readable storage medium, the correspondent time of editing live video stream is determined with the object event in live video stream, quickly and accurately editing can obtain the high target video segment of editing accuracy.Above-mentioned live video clipping method, device, electronic equipment and computer readable storage medium is adapted to the real-time editing work of large batch of video resource.
Description
Technical field
The present invention relates to technical field of internet application, specifically, the present invention relates to a kind of live video clipping method,
Device and electronic equipment.
Background technique
In today that the audio-visual entertainment resource scale of construction is skyrocketed through, on the one hand the increase of these audio-visual entertainment resources will increase
The material of creation, but also the processing speed to audio-visual entertainment resource and accuracy propose higher challenge simultaneously.With therein
For video, a large amount of video resource is created in fields such as live streaming, real-time game recordings, these video resources are secondary creation
High-quality material, need to carry out editing processing.For live video stream, due to requirement of real-time height, using the hand of caching
Section is unable to satisfy application requirement.
In the prior art be usually according to input editing operation, to video resource carry out editing, but due to the editing time,
Editing clip durations etc. are difficult to control, cause editing video quality not high, and editing low efficiency.
Summary of the invention
The purpose of the present invention is intended at least can solve above-mentioned one of technological deficiency, especially can not will be by substantial amounts
The technological deficiency of video resource quickly and accurately editing.
The present invention provides a kind of live video clipping method, comprising:
The picture frame for obtaining live video stream carries out image recognition, determines the first picture frame of object event occur；
The timestamp for extracting first picture frame obtains the editing position of video clipping according to the timestamp；
According to the editing position, editing goes out target video segment from the live video stream.
It is in one embodiment, described that according to the editing position, editing goes out target video piece from the live video stream
Section the step of include:
The first position point of editing video is determined according to the editing position；
The second position point that setting duration determines editing video is pushed back on the first position point；
The picture frame between first position point and second position point is extracted, the target video segment is synthesized.
In one embodiment, when recognizing continuous multiframe picture frame is the first picture frame, last frame the is extracted
The corresponding timestamp of one picture frame obtains the editing position of video clipping according to the timestamp.
In one embodiment, the live video clipping method further include:
The indicating label that the setting of the first picture frame is played according to the type of object event；
It is inserted into the indicating label in target video segment, is used to indicate the content and appearance position of object event, when
When the indicating label is clicked, jumps to corresponding first picture frame position and start to play.
In one embodiment, the picture frame for obtaining live video stream carries out image recognition, and target thing occurs in determination
The step of first picture frame of part, comprising:
Extract the picture frame of live video stream；
The picture material of the picture frame is identified, when appearance target figure associated with object event in picture frame
When picture, determine occur the object event in the picture frame.
In one embodiment, the live video clipping method further include:
According to multiple object events of setting, the editing from live video stream goes out multistage target video segment respectively；
The target video segment is ranked up according to each object event type；
According to sequence selected section target video segment synthetic video album from target video segment.
In one embodiment, the step that the target video segment is ranked up according to each object event type
Suddenly, comprising:
Classify to the object event；
The score value of number and the object event setting occurred according to object event in target video segment is to target video
Segment scores；
Target video segment is ranked up according to the scoring of each target video segment, several mesh that will sort forward
Mark video clip synthetic video album.
In one embodiment, the picture frame for obtaining live video stream carries out image recognition, and object event occurs in determination
Before the step of first picture frame, further includes:
Obtain the upload information or production information of the live video stream；
Obtain video clipping white list；
When the upload information or production information and video clipping white list match, to the picture frame of live video stream into
Row identification, obtains the object event occurred in the picture frame.
In one embodiment, the live video stream is game live video stream, and the object event is game points
Event.
In one embodiment, the picture frame for obtaining live video stream carries out image recognition, and object event occurs in determination
Before the step of first picture frame, further includes:
When a game starts, start to execute the step of picture frame for obtaining live video stream carries out image recognition；
When a game over, stop executing the step of picture frame for obtaining live video stream carries out image recognition.
In one embodiment, according to the editing position from the live video stream editing go out target video segment it
Afterwards, further includes:, will the target video segment that obtain in this game live streaming when detecting this game over or pause
It plays out.
The present invention also provides a kind of video clipping devices, comprising:
Recognition unit carries out image recognition and determines occur the of object event for obtaining the picture frame of live video stream
One picture frame；
Extraction unit obtains video clipping according to the timestamp for extracting the timestamp of first picture frame
Editing position；
Editing unit, for editing to go out target video segment from the live video stream according to the editing position.
The present invention also provides a kind of electronic equipment, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing above-mentioned live video clipping method.
The present invention also provides a kind of non-transitorycomputer readable storage mediums, when the instruction in the storage medium is by electricity
When the processor of sub- equipment executes, so that electronic equipment is able to carry out above-mentioned live video clipping method.
The present invention also provides a kind of computer program product, including computer program code, the computer program code
Including program instruction, when described program instruction is executed by electronic equipment, so that the electronic equipment is executed above-mentioned live video and cut
The method of collecting.
The automatic editing method, apparatus of above-mentioned video, electronic equipment and computer readable storage medium, by live streaming
The picture frame of video flowing is identified, the object event occurred in the picture frame is obtained；It obtains and generates the object event
The corresponding timestamp in live video stream of picture frame；Editing is carried out to the live video stream according to the timestamp, is obtained
The technical solution of video clip determines the correspondent time of editing live video stream, energy with the object event in live video stream
Quickly and accurately editing obtains the high video clip of editing accuracy.Above-mentioned live video clipping method, device, electronic equipment
And computer readable storage medium is adapted to the editing work of large batch of video resource.
The technical scheme is that obtaining video and executing framing parsing to video, images to be recognized information is obtained；Point
The images to be recognized information is analysed, object event in the images to be recognized information is detected；Obtain the time of the object event
Stamp obtains video clip according to video described in the timestamp and preset time interval editing.Through the above technical solutions,
The present invention can obtain object event and correspondent time by detection with editing video, can accurately identify object event,
And using object event as core, surrounding target event editing improves the accuracy of video clipping, applies the technical scheme of the present invention
Large batch of video clipping work can also quickly be handled.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the live video clipping method flow chart of one embodiment；
Fig. 2 is the flow diagram in one embodiment according to editing position editing target video segment；
Fig. 3 is the method flow diagram for identifying indicating label in one embodiment to target video segment；
Fig. 4 is to determine that the flow diagram of object event occurs in picture frame in one embodiment；
Fig. 5 is the method flow diagram that video album is formed in one embodiment；
Fig. 6 is to score to screen the method flow diagram of video clip with video in one embodiment；
Fig. 7 is the method flow diagram that editing is triggered in one embodiment；
Fig. 8 is live video editing structure drawing of device in one embodiment；
Fig. 9 is a kind of electronic equipment structure chart of the execution live video clipping method of one embodiment；
Figure 10 is the editing schematic diagram of a scenario of the live video clipping method of one embodiment；
Figure 11 is the application scenario diagram of the live video clipping method of one embodiment.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
Those skilled in the art of the present technique are appreciated that remote network devices used herein above, device comprising but it is unlimited
In the cloud that computer, network host, single network server, multiple network server collection or multiple servers are constituted.Here, cloud
It is made of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is distributed
One kind of calculating, a super virtual computer consisting of a loosely coupled set of computers.In the embodiment of the present invention,
It can be realized and be communicated by any communication modes between remote network devices, terminal device and WNS server, including but not limited to,
Mobile communication based on 3GPP, LTE, WIMAX, based on TCP/IP, udp protocol computer network communication and based on bluetooth,
The low coverage wireless transmission method of Infrared Transmission standard.
Referring to FIG. 1, in the present embodiment, providing a kind of live video clipping method, including the following steps:
The picture frame for obtaining live video stream in step s 11 carries out image recognition, and determination occurs the first of object event
Picture frame.
In above process, by taking one section of live video stream as an example, the live video stream, which can be, to be recorded
Game video or just in live video.The live video stream is made of multiframe with the picture frame of timestamp, to each frame
Picture frame is identified.Wherein, the picture frame of identification is if it is determined that there is object event, then the picture frame is exactly the first picture
Frame.In other possible embodiments, it can also be identified simultaneously for multiframe picture frame when specifying in long video, example
It such as can be the multiframe picture frame of the video to 1 second or 5 seconds durations while identifying.
By taking application image recognizer as an example, identify whether object event occur in picture frame, the object event is
Refer to the specific image information of preparatory typing.
For specific game live video stream, the tools such as the object event can refer to score, release technical ability, kill
There is the corresponding specific image information of the special event of ornamental value.Correspondingly, usually there is specific image to believe for these special events
Breath, e.g. text, instrument image, character image etc..For example, scoring event can be shown as in picture frame, " A player obtains 10
Point ", kill event and can be shown as " A player kills B player " in picture frame.Release technical ability event can be shown in picture frame
Image is discharged for certain technical ability, the technical ability release image has special recognition site, e.g. color change, Wan Jiatu
As variation etc..Instrument image therein can be identified as the instruments such as " rifle ", " gun ", " even crossbow " in picture frame.
Above-mentioned character image can be identified as " certain task publisher ", " ultimate monster " etc. in picture frame.In addition to this, also
The specific image that can be reflection scene, team's whole member rolls into a ball the fields such as war, certain role upgrading e.g. in same picture frame
Scape.
In step s 12, the timestamp for extracting first picture frame obtains cutting for video clipping according to the timestamp
Collect position.
In above process, the first picture frame that object event occurs corresponds to the generation moment of a specific event, this
The timestamp of corresponding first picture frame of a moment point.In conjunction with the example of above-mentioned game live video stream, such as recognize " A player
10 points " object event, the timestamp which occurs in game recording live video stream is 00:05:07.Work as trip
When there are multiple object events in play video recording live video stream, multiple timestamps are recorded respectively.In other implementations, also
Can method by continuously identifying and matching object event, identify initial time stamp and the end time of single target time
Stamp.For example, the object event of " A player obtains 10 points ", which persistently occurs 13 seconds, and corresponding initial time stamp is 00:05:
07, ending time stamp is 00:05:20.The editing position in the live video stream is assured that according to above-mentioned timestamp.
The timestamp can indicate absolute time, i.e. universal time, can also indicate that relative time, i.e., opposite in this live video stream
Time.
In step s 13, according to the editing position, editing goes out target video segment from the live video stream.
It in above process, is target video segment by live video stream editing according to the editing position of timestamp instruction.
In some embodiments, the number occurred according to object event is different, can obtain single or more than two target views
Frequency segment.For example, only occurring the object event of " A player obtains 10 points " in above-mentioned live video stream, live video stream editing is obtained
To one section of target video segment.If in live video stream, in addition to the object event of " A player obtains 10 points ", also appearance " group goes out "
Object event, two sections of target video segments will be obtained to live video stream editing.
In one embodiment, if the interval of the timestamp of two or more object events be less than appointed interval (such as
10 seconds), it can be by two or more object event editings in same target video segment, to guarantee the target video segment
Integrality and continuity avoid damage to the logical relation between object event.If the timestamp of two or more object events
Interval is greater than or equal to appointed interval, is multiple target video segments by the corresponding live video stream editing of object event.
In another embodiment, the corresponding duration information of target video segment can also be obtained, according to timestamp and
Duration information intercepts target video segment from live video stream.For example, the object event of " A player obtains 10 points ", corresponding time
Stamp is that 00:05:07 is terminal, and target video clip durations are 30 seconds, then it is corresponding to intercept 00:04:36 to 00:05:07
Live video stream is target video segment.In addition to this, can centered on the first picture frame correspondent time, on a timeline to
It is preceding and backward respectively interception corresponding duration, corresponding duration can be intercepted backward on a timeline using timestamp as starting point.
Further, according to the difference of object event, the duration information of respective objects video clip is not also identical.Example
Such as, in game live video stream, the object event of " continuously killing " can have 30 seconds duration informations, it can editing 30 seconds
Target video segment comprising " continuously killing ".And the object event of " killing ", just only 10 seconds duration informations, i.e. editing 10
Second includes the target video segment of " killing " object event.Relationship between object event and duration information can be according to target thing
The information such as the generation duration of part, excellent degree, audient's degree of liking determine.
In above process, by being identified to live video stream framing, high frequency identification may be implemented, quickly find target thing
The timestamp position that part occurs, convenient for it is accurate, quickly, determine editing position in real time, and then quickly editing goes out corresponding target
Video clip.Using the above method, to live video stream may be implemented low-latency (such as delay time can 3 seconds with
It is interior) target video segment editing reduce longest that is, when live streaming terminates or other need to extract the occasion of target video segment
Waiting time can be obtained the target video segment of this live streaming.
The application with editing game live video stream for other kinds of live video stream in addition to that can also be cut
Volume.By taking the live video stream for performing class as an example.Firstly, the picture frame for obtaining live video stream carries out image recognition, determines and occur
First picture frame of object event.Thereafter, the timestamp for extracting first picture frame obtains video according to the timestamp and cuts
The editing position collected.Then, according to the editing position, editing goes out target video segment from the live video stream.
During class live video stream is performed in above-mentioned editing, the picture frame of performance class live video stream, and needle are obtained
Object event is recognized whether to picture frame.For performance class live video stream, the object event can refer to send present,
Viewing number thumbs up the corresponding specific image information of special event that quantity etc. has record meaning, above-mentioned specific image letter
It ceases and can be dialogue, number variation, the variation at live streaming interface etc. in live streaming performance.Above-mentioned dialogue can be shown in picture frame
For the text informations such as the present of first online friend " thank ", " number broken ten thousand ", " thumbing up brokenly ten thousand ", e.g. the barrage of online friend, comment on, be
System prompting etc..In addition to this it is possible to be the viewing number for recognizing in picture frame be more than 10000, to thumb up number 500 etc. special
Event.The editing position that the timestamp instruction of the first picture frame is obtained according to identification, cuts from the performance class live video stream
Collect target video segment.
Referring to FIG. 2, on the basis of the present embodiment, step S13 specifically includes the following steps:
In the step s 21, the first position point of editing video is determined according to the editing position.
In above process, an editing position can confirm first position point, when the editing position is corresponding
Between stamp instruction object event at the time of occur.
When recognizing continuous multiframe picture frame is the first picture frame, when extraction the first picture frame of last frame is corresponding
Between stab, according to the timestamp obtain video clipping editing position.Multiple editing positions are obtained when there are multiple object event determinations
When setting, under the premise of meeting timestamp spacing less than appointed interval, made with the corresponding timestamp of the first picture frame of last frame
For the timestamp for determining first position point.For example, obtaining appointed interval is 30 seconds, if the timestamp of the first picture frame instruction is shared
3, interval of timestamps is respectively 25 seconds and 5 seconds, respectively less than appointed interval, then in 3 timestamps, with the first figure of last frame
The corresponding determining first position point of piece frame.
If the timestamp of the first picture frame instruction has 4, interval of timestamps is respectively 20 seconds, 10 seconds, 35 seconds, when above-mentioned
Between stamp in, remove the last one beyond specified time interval time stamp, with the first picture frame of frame second from the bottom corresponding time
It stabs and determines first position point.
In step S22, the second position point that setting duration determines editing video is pushed back on the first position point.
Above-mentioned setting duration refers to that the duration of target video segment, setting duration limit as the case may be.For example, setting
Duration can be set to 40 seconds, then determining the second position point of editing video toward retracting 40 seconds in first position point.Such as mesh
The timestamp of mark event is 00:06:03, then it is determined that first position point be 00:06:03, second position point be 00:05:22.
When there are multiple object events, that is, when there is multiple timestamps, setting duration accordingly increases according to the quantity of timestamp
It is long.For example, there are 6 object events, the timestamp of the last one object event is 00:09 in the picture frame of live video stream:
15, first position point is 00:09:15, and unit is 30 seconds a length of when setting, and 180 seconds a length of when setting accordingly, second position point is
00:06:14。
In step S23, the picture frame between first position point and second position point is extracted, the target video piece is synthesized
Section.
When above-mentioned first position point is 00:06:03, and second position point is 00:05:22, to live video stream interception 00:
The picture frame of 05:22 to 00:06:03, group are combined into target video segment.
When above-mentioned first position point be 00:09:15, second cut location point be 00:06:14 when, to live video stream intercept
The picture frame of 00:06:14 to 00:09:15, as target video segment.
On the basis of the present embodiment, step S21 is specifically included: being the first picture when recognizing continuous multiframe picture frame
When frame, the corresponding timestamp of the first picture frame of last frame is extracted, the editing position of video clipping is obtained according to the timestamp.
When an object event has continuity, the e.g. D player continuous 5 seconds target things using machine gun score
Part, the object event is for 5 seconds, and correspondent time is 00:03:04 to 00:03:09, then there is target thing with last frame
The corresponding timestamp of the picture frame of part, i.e. 00:03:09, determine first position point be live video stream 00:03:09 at.
The operation that above-mentioned identification obtains timestamp can realize in backstage, terminal etc., Preferable scheme is that, it is above-mentioned to identify
Operation to timestamp, editing video can realize that the video that editing obtains can pass through the modes such as link on Cloud Server
Distribution, user can by link directly access cloud in target video segment, reduce live video stream downloading, cache and
The waiting time and bandwidth resources that target video segment uploads accelerate the processing speed and target video segment of live video stream
Efficiency for issuing.Using the above method, editing can be carried out to live video stream in real time, not need that video is carried out the behaviour such as to cache
Make, greatly improves treatment effeciency.
Referring to FIG. 3, on the basis of the present embodiment, the method also includes:
In step S31, according to the type of object event to the indicating label of the first picture frame setting broadcasting.
In above process, the object event of identification is arranged according to classifying content plays label, and the broadcasting label is used for
Indicate title or content, the abstract etc. of the object event in the first picture frame.
In step s 32, the indicating label is inserted into target video segment, be used to indicate object event content and
Appearance position jumps to corresponding first picture frame position and starts to play when the indicating label is clicked.
It is inserted into indicating label in target video segment, user can be allowed to be quickly found out the position of object event appearance, and
According to the content presentation for playing label, fast browsing target video segment.In addition to click play label can jump to corresponding the
The position of one picture frame starts outside broadcasting, can also be by modes such as suspension, the click of specific keys, three-dimensional touch, display pair
The information of label should be played.Further, the small window that suspends can be shown, from the correspondence picture frame for playing label in the small window that suspends
Position starts to play target video segment.
Referring to FIG. 4, on the basis of the present embodiment, step S11 specifically includes the following steps:
In step S41, the picture frame of live video stream is extracted.
In above process, by the parsing to live video stream, the picture frame for having timestamp is obtained, for identification mesh
Mark event.
It, can be by establishing the database comprising target image, by goal-selling image and target before the above process
Event is associated.For example, establishing mesh of the database including a variety of keyword images to Matching conversation class, system prompt class
Mark event；It establishes the database including a variety of weapon images, stage property image, present image and uses weapon, using road to match
Tool or the present associated object event of present.
In step S42, the picture material of the picture frame is identified, when appearance and object event phase in picture frame
When associated target image, determine occur the object event in the picture frame.
In above process, turn text algorithm, picture recognition algorithm, convolution mind using intelligent algorithm (AI), picture
Through recognizers such as network algorithms, can be compared according to the figure occurred in picture frame and preset target image, it is final to determine
Whether object event is occurred.In general, usually there is preferable correlation to object event according to preparatory associated target image
Property, whether capable of accurately indicating the generation of object event.It, can be in multiple trained or repeatedly identification using intelligent algorithm
Afterwards, preferable recognition result is obtained.
Referring to FIG. 5, the live video clipping method further comprises the steps of: on the basis of the present embodiment
In step s 51, according to multiple object events of setting, the editing from live video stream goes out multistage target view respectively
Frequency segment.
In step S52, the target video segment is ranked up according to each object event type.
In above process, by taking game video as an example, can be classified according to the content for occurring object event in game,
Such as can be divided into classifying, upgrading class, vision class etc..According to different target event type, object event can all be answered
Target video segment is ranked up.The foundation of sequence can be degree, the probability of appearance etc. that spectators like.For example, " player's liter
The object event of grade " is rarer, the object event of " player's upgrading " can be divided into upgrading class, by its corresponding target video
Segment comes first of sequence.For example, the object event of " technical ability release ", since visual effect is more magnificent, spectators like
Degree is relatively high, the object event of " technical ability release " can be divided into vision class, and corresponding target video segment is come sequence
Second.The object event of " A player obtains 10 points " is classified as obtaining classification, corresponding target video segment is come to the end of sequence
Position.
In some embodiments, if there are multiple object events in same target video segment, to target video segment
Sequence, statistics can be weighted according to the quantification index of multiple object events, further to target video segment sort.This
A scheme can be adapted for occurring in target video segment sequence when complicated object event.
In step S53, according to sequence selected section target video segment synthetic video from target video segment
Album.
In above process, when thering is duration to limit or have quantity limitation to target video segment video album, example
It such as limits when video album a length of 30 seconds.Above-mentioned upgrading class object event corresponds to target video piece segment length 10 seconds, vision class target
Event corresponds to target video piece segment length 20 seconds, obtains class object event and corresponds to target video piece segment length 30 seconds, then according to above-mentioned
Ranking results preferentially choose upgrading class object event correspond to target video segment with liter vision class object event correspond to target video
Segment forms video album.Above scheme can screen the higher target video piece of quality under limited duration resources control
Section forms the better video album of viewability.
Referring to FIG. 6, on the basis of the present embodiment, step S52 specifically includes the following steps:
In step S61, classify to the object event.
By taking shooting game as an example, it can be classified as that " killing ", " continuously killing ", " super mind is hit according to object event content
Kill ", " finals ", " sniping gun ", " a times mirror kills ", " killing by bus ", " stage property kills ".
In step S62, point of number and the object event setting occurred according to object event in target video segment
Value scores to target video segment.
Such as above-mentioned " killing ", " continuously killing ", " super mind kills ", " finals ", " sniping gun ", " a times mirror kills ",
The object event of " killing by bus ", " stage property kills " respectively corresponds fractional value are as follows: 2,5,5,5,3,4,4,6.
In target video segment A, identification object event " stage property kills " 2 times, " super mind kills " 1 time amounts to 15 points, target
Video clip duration 25 seconds；
In target video segment B, identification object event " killing by bus " 1 time, " a times mirror kills " 1 time amounts to 8 points, target
Video clip duration 10 seconds；
In target video segment C, identification object event " killing " 5 times, " finals " 2 times amounts to 20 points, target video piece
Duan Shichang 30 seconds；
In target video segment D, identification object event " killing " 3 times, " finals " 1 time, " super mind kills " 1 time amounts to
16 points, target video clip durations 60 seconds；
In target video segment E, identification object event " a times mirror kills " 1 time, " finals " 1 time, " sniping gun " 1 time, altogether
12 points, target video clip durations 60 seconds of meter.
In step S63, target video segment is ranked up according to the scoring of each target video segment, sequence is leaned on
Several preceding target video segment synthetic video albums.
According to the sequence arrangement of scoring from high to low: target video segment C (20 points), target video segment D (16 points), mesh
Mark video clip A (15 points), target video segment E (12 points), target video segment B (8 points).Select preceding 3 target video pieces
Duan Zucheng video album uses target video segment C, target video segment D, target video segment A.In composition video album
When, it can be arranged according to the absolute time or relative time of the timestamp of target video segment according to the sequencing of time；Also
It can be according to the scoring of target video segment, according to scoring from down to high sequence composite object video clip；It can also basis
The duration of target video segment forms video album according to the sequence of duration from long to short.
In conjunction with above-mentioned example, the scheme to the object event label in target video segment is shown:
Referring to FIG. 3, the scheme of corresponding label is respectively set according to the content of the object event, still with above-mentioned video
For segment A, in video clip A, identification object event " stage property kills " 2 times, " super mind kills " 1 time accordingly identifies label " road
Tool kills " 2, " super mind kills " 1.
According to the timestamp for the first picture frame that the object event occurs, the position of time shaft in target video segment
It is inserted into the indicating label, is used to indicate the content and appearance position of object event.
In above-mentioned target video segment A, the timestamp that identification object event " stage property kills " is 2 times is respectively 00:09:06
And 00:15:12, the timestamp that " super mind kills " is 1 time is 00:11:26, according to the sequencing of timestamp in target video segment
Corresponding position be inserted into indicating label respectively.In the target video segment A, when mouse or other there is instruction interactive function
It, can be with call tag content when tool is touched, suspended, clicking the label.For example, when user is in ornamental target video segment A
When, when mouse is suspended in the 00:11:26 of progress bar, it can show suspension instruction, show that the section is the object event of " super mind kills "
Content or related abstract information.
Referring to FIG. 7, before the step S11 of the live video clipping method, further including on the basis of the present embodiment
Step:
In step S71, the upload information or production information of the live video stream are obtained.
Wherein upload information can be the title or identity identification information of uploader, and the production information can be production
The information of person, the e.g. information such as the title of producer or the identification code of production team.
In step S72, video clipping white list is obtained.
Above-mentioned video clipping white list may include the title of uploader or the letter of identity identification information, producer
The information such as breath, the title of producer or the identification code of production team, the video clipping white list are to be clipped for screening
Live video stream.
In step S73, when the upload information or production information and the matching of video clipping white list, to live video
The picture frame of stream is identified, the object event occurred in the picture frame is obtained.
In video clipping white list author production, record or upload live video stream quality with higher or
Person has certain spectators basis, therefore when the upload information or production information and video clipping white list match, can incite somebody to action
Corresponding live video stream is selected, and carries out editing as live video stream to be clipped.
On the basis of the present embodiment, when live video stream is game live video stream, the object event obtains for game
When dividing event, before the step S11 of the live video clipping method, further includes:
When a game starts, start to execute the step that the picture frame for obtaining game live video stream carries out image recognition
Suddenly.When a game over, stop executing the step of picture frame for obtaining live video stream carries out image recognition.
In above process, when main broadcaster is switched to, games page is full frame or games page is more than the one of entire live streaming interface
Certainty ratio is assured that game has begun.When main broadcaster cuts out interface or interface has been identified to local exchange trip
When play such as is at the contents, it can determine that game is over.
In some other embodiment, the click by main broadcaster can be, password identification either game provider refers to
Enable the instruction for starting or terminating as game.After game starts, the picture frame of game live video stream can be started to identify.
Through the above scheme, main broadcaster can be cut off to carry out that unrelated video content is broadcast live with game during live streaming, reduce identification fortune
Calculation amount and the occupancy for identifying resource just reinstate the method for above-mentioned video clipping when in game live streaming progress.
In above process, by taking live streaming as an example, single game live streaming is 11:39AM at the time of beginning, and live streaming is at the time of end
1:25PM.So correspondingly, the identification of live video stream is just carried out in 11:39AM the and 1:25PM time.
It, will be in this game live streaming when detecting this game over or pause after obtaining target video segment
The target video segment obtained plays out.Real-time playback editing obtains after this game over target video segment or
Person is to play the video album being made of above-mentioned target video segment.
Referring to FIG. 9, the present embodiment also provides a kind of live video editing device, comprising:
Recognition unit 91 carries out image recognition determination and object event occurs for obtaining the picture frame of live video stream
First picture frame；
Extraction unit 92 obtains video clipping according to the timestamp for extracting the timestamp of first picture frame
Editing position；
Editing unit 93, for editing to go out target video segment from the live video stream according to the editing position.
Above-mentioned video clipping device is for executing above-mentioned live video clipping method.
The present embodiment also provides a kind of electronic equipment, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing above-mentioned live video clipping method.
Fig. 9 is a kind of a kind of electronic equipment for executing live video clipping method shown according to an exemplary embodiment
Block diagram.For example, electronic equipment 900 may be provided as a server.Referring to Fig. 9, electronic equipment 900 includes processing component 922,
It further comprises one or more processors, and the memory resource as representated by memory 932, can be by for storing
Manage the instruction of the execution of component 922, such as application program.The application program stored in memory 932 may include one or one
Each more than a corresponds to the module of one group of instruction.In addition, processing component 922 is configured as executing instruction, on executing
The method for stating live video editing.
Electronic equipment 900 can also include that a power supply module 926 is configured as executing the power supply pipe of electronic equipment 900
Reason, a wired or wireless network interface 950 are configured as electronic equipment 900 being connected to network and an input and output (I/
O) interface 958.Electronic equipment 900 can be operated based on the operating system for being stored in memory 932, such as Windows
ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
The present embodiment also provides a kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium by
When the processor of electronic equipment executes, so that electronic equipment is able to carry out above-mentioned live video clipping method.
Referring to FIG. 10, the present embodiment illustratively shows a kind of editing schematic diagram of a scenario of live video editing.This reality
Example is applied by obtaining picture frame 101, picture frame 102, picture frame 103 in live video stream.Above-mentioned picture frame is carried out respectively
Identification, identification obtain the presence of " score " object event in picture frame 102, picture frame 102 are identified as the first picture frame.According to
The timestamp 102B of one picture frame determines that i.e. first position point is timestamp 102B in the editing position of the live video stream.Root
According to the preset duration of " score " object event, push back to second position point, the e.g. position of timestamp 101A.By first position
Video clip editing between point and second position point, obtains target video segment.
Please refer to Figure 11, it is also exemplary in the present embodiment that a kind of application scenarios of live video clipping method are provided.Wherein,
Server obtains live video stream, and live video stream is sent to video end, parses picture frame by video end.Before this, by rear
Platform determines whether to trigger editing according to the information of live video stream, such as it is white for uploading or make the user of the live video stream
Name single user either credit user, then backstage can issue editing instruction with order of priority or directly to server, with triggering
The editing of live video stream.When backstage determines triggering editing, issues editing instruction, know at editing end using artificial intelligence (AI)
Other algorithm identifies object event, such as can identify the associated profile of object event, text, pixel identification point or pixel point set
Close etc., and it is converted into target video piece segment information.It include the corresponding time in target video piece segment information in the object event
The information such as stamp, the corresponding preset duration of object event.According to target video piece segment information and live video stream, at editing end into one
It walks editing and generates target video segment, the target video segment is gone to server and stored by editing end.From the background to server tune
Target video segment is taken, and generates the link of video album, the publication video album.
During above-mentioned execution live video clipping method, the operation at editing end can be incorporated to server execution, institute
The operations such as editing, identification can mainly be executed using cloud server by stating server.
In one embodiment, the operands such as identification, editing are high, step of operation complexity, can server beyond the clouds
It completes, and can distribute in the form of a link, avoid caching live video stream, reduce target video segment, video album is downloaded
Time and bandwidth occupancy.
Above-mentioned live video clipping method, device, electronic equipment and computer readable storage medium, by live streaming
The picture frame of video flowing is identified, the object event occurred in the picture frame is obtained；It obtains and generates the object event
The corresponding timestamp in live video stream of picture frame；Editing is carried out to the live video stream according to the timestamp, is obtained
The technical solution of video clip determines the correspondent time of editing live video stream, energy with the object event in live video stream
Quickly and accurately editing obtains the high video clip of editing accuracy.Above-mentioned live video clipping method, device, electronic equipment
And computer readable storage medium is adapted to the editing work of large batch of video resource.
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (14)
1. a kind of live video clipping method characterized by comprising
The picture frame for obtaining live video stream carries out image recognition, determines the first picture frame of object event occur；
The timestamp for extracting first picture frame obtains the editing position of video clipping according to the timestamp；
According to the editing position, editing goes out target video segment from the live video stream.
2. live video clipping method according to claim 1, which is characterized in that it is described according to the editing position from institute
Stating the step of editing in live video stream goes out target video segment includes:
The first position point of editing video is determined according to the editing position；
The second position point that setting duration determines editing video is pushed back on the first position point；
The picture frame between first position point and second position point is extracted, the target video segment is synthesized.
3. live video clipping method according to claim 1, which is characterized in that when recognizing continuous multiframe picture frame
When for the first picture frame, the corresponding timestamp of the first picture frame of last frame is extracted, video clipping is obtained according to the timestamp
Editing position.
4. live video clipping method according to claim 3, which is characterized in that further include:
The indicating label that the setting of the first picture frame is played according to the type of object event；
It is inserted into the indicating label in target video segment, the content and appearance position of object event are used to indicate, when described
When indicating label is clicked, jumps to corresponding first picture frame position and start to play.
5. live video clipping method according to claim 1, which is characterized in that the picture for obtaining live video stream
Frame carries out image recognition, and the step of the first picture frame of object event occurs in determination, comprising:
Extract the picture frame of live video stream；
The picture material of the picture frame is identified, when appearance target image associated with object event in picture frame
When, determine occur the object event in the picture frame.
6. live video clipping method according to claim 1, which is characterized in that further include:
According to multiple object events of setting, the editing from live video stream goes out multistage target video segment respectively；
The target video segment is ranked up according to each object event type；
According to sequence selected section target video segment synthetic video album from target video segment.
7. live video clipping method according to claim 6, which is characterized in that described according to each object event type
The step of target video segment is ranked up, comprising:
Classify to the object event；
The score value of number and the object event setting occurred according to object event in target video segment is to target video segment
It scores；
Target video segment is ranked up according to the scoring of each target video segment, several targets for sorting forward are regarded
Frequency segment synthetic video album.
8. live video clipping method according to claim 1, which is characterized in that obtain the picture frame of live video stream into
Row image recognition determines before there is the step of the first picture frame of object event, further includes:
Obtain the upload information or production information of the live video stream；
Obtain video clipping white list；
When the upload information or production information and video clipping white list match, the picture frame of live video stream is known
Not, the object event occurred in the picture frame is obtained.
9. live video clipping method according to any one of claims 1 to 8, which is characterized in that the live video stream
For game live video stream, the object event is game points event.
10. live video clipping method according to claim 9, which is characterized in that obtain the picture frame of live video stream
Image recognition is carried out, is determined before there is the step of the first picture frame of object event, further includes:
When a game starts, start to execute the step of picture frame for obtaining live video stream carries out image recognition；
When a game over, stop executing the step of picture frame for obtaining live video stream carries out image recognition.
11. live video clipping method according to claim 10, which is characterized in that according to the editing position from described
Editing goes out after target video segment in live video stream, further includes: when detecting this game over or pause, by this
The target video segment obtained in game live streaming plays out.
12. a kind of live video editing device characterized by comprising
Recognition unit carries out image recognition and determines the first figure for object event occur for obtaining the picture frame of live video stream
Piece frame；
Extraction unit obtains the editing of video clipping according to the timestamp for extracting the timestamp of first picture frame
Position；
Editing unit, for editing to go out target video segment from the live video stream according to the editing position.
13. a kind of electronic equipment characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to perform claim requires live video clipping method described in 1 to 11 any one.
14. a kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of electronic equipment
When device executes, so that electronic equipment is able to carry out live video clipping method described in claim 1 to 11 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811198454.9A CN109194978A (en) | 2018-10-15 | 2018-10-15 | Live video clipping method, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811198454.9A CN109194978A (en) | 2018-10-15 | 2018-10-15 | Live video clipping method, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109194978A true CN109194978A (en) | 2019-01-11 |
Family
ID=64944996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811198454.9A Pending CN109194978A (en) | 2018-10-15 | 2018-10-15 | Live video clipping method, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109194978A (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109714644A (en) * | 2019-01-22 | 2019-05-03 | 广州虎牙信息科技有限公司 | A kind of processing method of video data, device, computer equipment and storage medium |
| CN109862388A (en) * | 2019-04-02 | 2019-06-07 | 网宿科技股份有限公司 | Generation method, device, server and the storage medium of the live video collection of choice specimens |
| CN109874026A (en) * | 2019-03-05 | 2019-06-11 | 网易（杭州）网络有限公司 | Data processing method and device, storage medium, electronic equipment |
| CN109889882A (en) * | 2019-01-24 | 2019-06-14 | 北京亿幕信息技术有限公司 | A kind of video clipping synthetic method and system |
| CN109889856A (en) * | 2019-01-21 | 2019-06-14 | 南京微特喜网络科技有限公司 | A kind of live streaming editing system based on artificial intelligence |
| CN109889879A (en) * | 2019-03-25 | 2019-06-14 | 联想(北京)有限公司 | Information control method and electronic equipment |
| CN109922379A (en) * | 2019-02-22 | 2019-06-21 | 深圳前海微众银行股份有限公司 | Advertisement video optimization method, device, equipment and computer readable storage medium |
| CN110124317A (en) * | 2019-05-23 | 2019-08-16 | 网易（杭州）网络有限公司 | Interactive approach, device, equipment and storage medium in game live streaming |
| CN110198472A (en) * | 2019-04-25 | 2019-09-03 | 腾讯科技（深圳）有限公司 | The playback method and device of video resource |
| CN110392304A (en) * | 2019-06-24 | 2019-10-29 | 北京达佳互联信息技术有限公司 | A kind of video display method, apparatus, electronic equipment and storage medium |
| CN110460869A (en) * | 2019-08-14 | 2019-11-15 | 咪咕文化科技有限公司 | A kind of method, electronic equipment and the storage medium of determining video clipping segment |
| CN110478914A (en) * | 2019-08-28 | 2019-11-22 | 武汉宇宙寓言影视发展有限公司 | A kind of control method, system and device emulating children swing machine |
| CN110505528A (en) * | 2019-08-29 | 2019-11-26 | 网易（杭州）网络有限公司 | The matched method, apparatus of game, equipment and readable storage medium storing program for executing in live streaming |
| CN111428660A (en) * | 2020-03-27 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Video editing method and device, storage medium and electronic device |
| CN111556328A (en) * | 2020-04-17 | 2020-08-18 | 北京达佳互联信息技术有限公司 | Program acquisition method and device for live broadcast room, electronic equipment and storage medium |
| CN111654749A (en) * | 2020-06-24 | 2020-09-11 | 百度在线网络技术（北京）有限公司 | Video data production method and device, electronic equipment and computer readable medium |
| CN111770359A (en) * | 2020-06-03 | 2020-10-13 | 苏宁云计算有限公司 | Event video clipping method, system and computer readable storage medium |
| CN111787341A (en) * | 2020-05-29 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Broadcasting directing method, device and system |
| CN111800648A (en) * | 2020-06-30 | 2020-10-20 | 北京玩在一起科技有限公司 | Live stream editing method and system for electricity competition |
| CN112037593A (en) * | 2019-06-03 | 2020-12-04 | 广东小天才科技有限公司 | Learning interaction implementation method and system based on augmented reality |
| CN112423115A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Flock video editing method and system |
| US11025964B2 (en) | 2019-04-02 | 2021-06-01 | Wangsu Science & Technology Co., Ltd. | Method, apparatus, server, and storage medium for generating live broadcast video of highlight collection |
| CN113038151A (en) * | 2021-02-25 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Video editing method and video editing device |
| CN113179418A (en) * | 2021-05-31 | 2021-07-27 | 北京达佳互联信息技术有限公司 | Live video processing method and device, electronic equipment and storage medium |
| CN113286173A (en) * | 2021-05-19 | 2021-08-20 | 北京沃东天骏信息技术有限公司 | Video editing method and device |
| CN113343055A (en) * | 2021-05-31 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Video processing method and device, electronic equipment and computer readable storage medium |
| CN113542894A (en) * | 2020-11-25 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Game video editing method, device, equipment and storage medium |
| CN113556485A (en) * | 2021-07-23 | 2021-10-26 | 上海商汤智能科技有限公司 | Video generation method and device, electronic equipment and storage medium |
| CN113559503A (en) * | 2021-06-30 | 2021-10-29 | 上海掌门科技有限公司 | Video generation method, device and computer readable medium |
| CN113824972A (en) * | 2021-05-31 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Live video processing method, device and equipment and computer readable storage medium |
| CN114697749A (en) * | 2020-12-28 | 2022-07-01 | 北京小米移动软件有限公司 | Video editing method, video editing device, storage medium and electronic equipment |
| CN114827739A (en) * | 2022-06-06 | 2022-07-29 | 百果园技术(新加坡)有限公司 | Live playback video generation method, device, equipment and storage medium |
| CN114827709A (en) * | 2022-04-26 | 2022-07-29 | 北京达佳互联信息技术有限公司 | Video display method and device, electronic equipment and storage medium |
| CN115119044A (en) * | 2021-03-18 | 2022-09-27 | 阿里巴巴新加坡控股有限公司 | Video processing method, device, system and computer storage medium |
| WO2022199372A1 (en) * | 2021-03-25 | 2022-09-29 | 腾讯科技（深圳）有限公司 | Video editing method and apparatus, and computer device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100104261A1 (en) * | 2008-10-24 | 2010-04-29 | Zhu Liu | Brief and high-interest video summary generation |
| US20120076367A1 (en) * | 2010-09-24 | 2012-03-29 | Erick Tseng | Auto tagging in geo-social networking system |
| CN104703055A (en) * | 2015-03-13 | 2015-06-10 | 天脉聚源（北京）教育科技有限公司 | Locating method and device of video playing |
| CN104796781A (en) * | 2015-03-31 | 2015-07-22 | 小米科技有限责任公司 | Video clip extraction method and device |
| CN104811787A (en) * | 2014-10-27 | 2015-07-29 | 深圳市腾讯计算机***有限公司 | Game video recording method and game video recording device |
| CN104823453A (en) * | 2012-10-05 | 2015-08-05 | 谷歌公司 | Stitching videos into aggregate video |
| CN105009599A (en) * | 2012-12-31 | 2015-10-28 | 谷歌公司 | Automatic identification of a notable moment |
| CN105915936A (en) * | 2016-06-22 | 2016-08-31 | 武汉斗鱼网络科技有限公司 | Video dotting method and system for video website |
| CN106803987A (en) * | 2015-11-26 | 2017-06-06 | 腾讯科技（深圳）有限公司 | The acquisition methods of video data, device and system |
| CN108295468A (en) * | 2018-02-28 | 2018-07-20 | 网易（杭州）网络有限公司 | Information processing method, equipment and the storage medium of game |
| CN108540854A (en) * | 2018-03-29 | 2018-09-14 | 努比亚技术有限公司 | Live video clipping method, terminal and computer readable storage medium |
-
2018
- 2018-10-15 CN CN201811198454.9A patent/CN109194978A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100104261A1 (en) * | 2008-10-24 | 2010-04-29 | Zhu Liu | Brief and high-interest video summary generation |
| US20120076367A1 (en) * | 2010-09-24 | 2012-03-29 | Erick Tseng | Auto tagging in geo-social networking system |
| CN104823453A (en) * | 2012-10-05 | 2015-08-05 | 谷歌公司 | Stitching videos into aggregate video |
| CN105009599A (en) * | 2012-12-31 | 2015-10-28 | 谷歌公司 | Automatic identification of a notable moment |
| CN104811787A (en) * | 2014-10-27 | 2015-07-29 | 深圳市腾讯计算机***有限公司 | Game video recording method and game video recording device |
| CN104703055A (en) * | 2015-03-13 | 2015-06-10 | 天脉聚源（北京）教育科技有限公司 | Locating method and device of video playing |
| CN104796781A (en) * | 2015-03-31 | 2015-07-22 | 小米科技有限责任公司 | Video clip extraction method and device |
| CN106803987A (en) * | 2015-11-26 | 2017-06-06 | 腾讯科技（深圳）有限公司 | The acquisition methods of video data, device and system |
| CN105915936A (en) * | 2016-06-22 | 2016-08-31 | 武汉斗鱼网络科技有限公司 | Video dotting method and system for video website |
| CN108295468A (en) * | 2018-02-28 | 2018-07-20 | 网易（杭州）网络有限公司 | Information processing method, equipment and the storage medium of game |
| CN108540854A (en) * | 2018-03-29 | 2018-09-14 | 努比亚技术有限公司 | Live video clipping method, terminal and computer readable storage medium |
Cited By (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109889856A (en) * | 2019-01-21 | 2019-06-14 | 南京微特喜网络科技有限公司 | A kind of live streaming editing system based on artificial intelligence |
| CN109714644B (en) * | 2019-01-22 | 2022-02-25 | 广州虎牙信息科技有限公司 | Video data processing method and device, computer equipment and storage medium |
| CN109714644A (en) * | 2019-01-22 | 2019-05-03 | 广州虎牙信息科技有限公司 | A kind of processing method of video data, device, computer equipment and storage medium |
| CN109889882A (en) * | 2019-01-24 | 2019-06-14 | 北京亿幕信息技术有限公司 | A kind of video clipping synthetic method and system |
| CN109922379A (en) * | 2019-02-22 | 2019-06-21 | 深圳前海微众银行股份有限公司 | Advertisement video optimization method, device, equipment and computer readable storage medium |
| CN109874026A (en) * | 2019-03-05 | 2019-06-11 | 网易（杭州）网络有限公司 | Data processing method and device, storage medium, electronic equipment |
| US11265594B2 (en) | 2019-03-05 | 2022-03-01 | Netease (Hangzhou) Network Co., Ltd. | Data processing method and device, storage medium, electronic device |
| CN109874026B (en) * | 2019-03-05 | 2020-07-07 | 网易（杭州）网络有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN109889879A (en) * | 2019-03-25 | 2019-06-14 | 联想(北京)有限公司 | Information control method and electronic equipment |
| WO2020199303A1 (en) * | 2019-04-02 | 2020-10-08 | 网宿科技股份有限公司 | Live stream video highlight generation method and apparatus, server, and storage medium |
| US11025964B2 (en) | 2019-04-02 | 2021-06-01 | Wangsu Science & Technology Co., Ltd. | Method, apparatus, server, and storage medium for generating live broadcast video of highlight collection |
| CN109862388A (en) * | 2019-04-02 | 2019-06-07 | 网宿科技股份有限公司 | Generation method, device, server and the storage medium of the live video collection of choice specimens |
| CN110198472A (en) * | 2019-04-25 | 2019-09-03 | 腾讯科技（深圳）有限公司 | The playback method and device of video resource |
| CN110198472B (en) * | 2019-04-25 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Video resource playing method and device |
| CN110124317B (en) * | 2019-05-23 | 2023-02-28 | 网易（杭州）网络有限公司 | Interaction method, device, equipment and storage medium in game live broadcast |
| CN110124317A (en) * | 2019-05-23 | 2019-08-16 | 网易（杭州）网络有限公司 | Interactive approach, device, equipment and storage medium in game live streaming |
| CN112037593A (en) * | 2019-06-03 | 2020-12-04 | 广东小天才科技有限公司 | Learning interaction implementation method and system based on augmented reality |
| CN110392304A (en) * | 2019-06-24 | 2019-10-29 | 北京达佳互联信息技术有限公司 | A kind of video display method, apparatus, electronic equipment and storage medium |
| CN110460869B (en) * | 2019-08-14 | 2022-03-25 | 咪咕文化科技有限公司 | Method for determining video clip segments, electronic device and storage medium |
| CN110460869A (en) * | 2019-08-14 | 2019-11-15 | 咪咕文化科技有限公司 | A kind of method, electronic equipment and the storage medium of determining video clipping segment |
| CN110478914A (en) * | 2019-08-28 | 2019-11-22 | 武汉宇宙寓言影视发展有限公司 | A kind of control method, system and device emulating children swing machine |
| CN110505528A (en) * | 2019-08-29 | 2019-11-26 | 网易（杭州）网络有限公司 | The matched method, apparatus of game, equipment and readable storage medium storing program for executing in live streaming |
| CN111428660A (en) * | 2020-03-27 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Video editing method and device, storage medium and electronic device |
| CN111428660B (en) * | 2020-03-27 | 2023-04-07 | 腾讯科技（深圳）有限公司 | Video editing method and device, storage medium and electronic device |
| CN111556328A (en) * | 2020-04-17 | 2020-08-18 | 北京达佳互联信息技术有限公司 | Program acquisition method and device for live broadcast room, electronic equipment and storage medium |
| US11553019B2 (en) | 2020-04-17 | 2023-01-10 | Beijing Dajia Internet Information Technology Co., Ltd. | Method, apparatus, electronic device and storage medium for acquiring programs in live streaming room |
| CN111787341B (en) * | 2020-05-29 | 2023-12-05 | 北京京东尚科信息技术有限公司 | Guide broadcasting method, device and system |
| CN111787341A (en) * | 2020-05-29 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Broadcasting directing method, device and system |
| CN111770359A (en) * | 2020-06-03 | 2020-10-13 | 苏宁云计算有限公司 | Event video clipping method, system and computer readable storage medium |
| WO2021258655A1 (en) * | 2020-06-24 | 2021-12-30 | 百度在线网络技术（北京）有限公司 | Video data production method and apparatus, electronic device, and computer readable medium |
| CN111654749A (en) * | 2020-06-24 | 2020-09-11 | 百度在线网络技术（北京）有限公司 | Video data production method and device, electronic equipment and computer readable medium |
| CN111654749B (en) * | 2020-06-24 | 2022-03-01 | 百度在线网络技术（北京）有限公司 | Video data production method and device, electronic equipment and computer readable medium |
| CN111800648A (en) * | 2020-06-30 | 2020-10-20 | 北京玩在一起科技有限公司 | Live stream editing method and system for electricity competition |
| CN112423115A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Flock video editing method and system |
| CN113542894A (en) * | 2020-11-25 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Game video editing method, device, equipment and storage medium |
| CN114697749A (en) * | 2020-12-28 | 2022-07-01 | 北京小米移动软件有限公司 | Video editing method, video editing device, storage medium and electronic equipment |
| CN113038151A (en) * | 2021-02-25 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Video editing method and video editing device |
| CN113038151B (en) * | 2021-02-25 | 2022-11-18 | 北京达佳互联信息技术有限公司 | Video editing method and video editing device |
| 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 |
| CN115119044A (en) * | 2021-03-18 | 2022-09-27 | 阿里巴巴新加坡控股有限公司 | Video processing method, device, system and computer storage medium |
| WO2022199372A1 (en) * | 2021-03-25 | 2022-09-29 | 腾讯科技（深圳）有限公司 | Video editing method and apparatus, and computer device and storage medium |
| CN113286173B (en) * | 2021-05-19 | 2023-08-04 | 北京沃东天骏信息技术有限公司 | Video editing method and device |
| CN113286173A (en) * | 2021-05-19 | 2021-08-20 | 北京沃东天骏信息技术有限公司 | Video editing method and device |
| CN113179418A (en) * | 2021-05-31 | 2021-07-27 | 北京达佳互联信息技术有限公司 | Live video processing method and device, electronic equipment and storage medium |
| CN113824972A (en) * | 2021-05-31 | 2021-12-21 | 腾讯科技（深圳）有限公司 | Live video processing method, device and equipment and computer readable storage medium |
| CN113343055A (en) * | 2021-05-31 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Video processing method and device, electronic equipment and computer readable storage medium |
| CN113824972B (en) * | 2021-05-31 | 2024-01-09 | 深圳市雅阅科技有限公司 | Live video processing method, device, equipment and computer readable storage medium |
| CN113559503A (en) * | 2021-06-30 | 2021-10-29 | 上海掌门科技有限公司 | Video generation method, device and computer readable medium |
| CN113559503B (en) * | 2021-06-30 | 2024-03-12 | 上海掌门科技有限公司 | Video generation method, device and computer readable medium |
| CN113556485A (en) * | 2021-07-23 | 2021-10-26 | 上海商汤智能科技有限公司 | Video generation method and device, electronic equipment and storage medium |
| CN114827709A (en) * | 2022-04-26 | 2022-07-29 | 北京达佳互联信息技术有限公司 | Video display method and device, electronic equipment and storage medium |
| CN114827709B (en) * | 2022-04-26 | 2024-03-01 | 北京达佳互联信息技术有限公司 | Video display method and device, electronic equipment and storage medium |
| CN114827739A (en) * | 2022-06-06 | 2022-07-29 | 百果园技术(新加坡)有限公司 | Live playback video generation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109194978A (en) | Live video clipping method, device and electronic equipment | |
| US11380101B2 (en) | Data processing systems and methods for generating interactive user interfaces and interactive game systems based on spatiotemporal analysis of video content | |
| CN110012348B (en) | A kind of automatic collection of choice specimens system and method for race program | |
| EP3855753B1 (en) | Method and apparatus for locating video playing node, device and storage medium | |
| CN105657535B (en) | A kind of audio identification methods and device | |
| US10057651B1 (en) | Video clip creation using social media | |
| US20180132011A1 (en) | System and method for creating and distributing multimedia content | |
| CN108769723B (en) | Method, device, equipment and storage medium for pushing high-quality content in live video | |
| CN107704525A (en) | Video searching method and device | |
| CN110166811B (en) | Bullet screen information processing method, device and equipment | |
| CN109640112B (en) | Video processing method, device, equipment and storage medium | |
| US20110151971A1 (en) | Technological platform for gaming | |
| US20110099195A1 (en) | Method and Apparatus for Video Search and Delivery | |
| CN112312142B (en) | Video playing control method and device and computer readable storage medium | |
| CN113779381B (en) | Resource recommendation method, device, electronic equipment and storage medium | |
| CN109710806A (en) | The method for visualizing and system of football match data | |
| US20110179003A1 (en) | System for Sharing Emotion Data and Method of Sharing Emotion Data Using the Same | |
| CN111726682A (en) | Video clip generation method, device, equipment and computer storage medium | |
| CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
| CN113992974B (en) | Method, device, computing equipment and computer readable storage medium for simulating competition | |
| CN113507630B (en) | Method and device for stripping game video | |
| CN113497946B (en) | Video processing method, device, electronic equipment and storage medium | |
| CN111400511B (en) | Method and device for intercepting multimedia resources | |
| CN111949820A (en) | Video associated interest point processing method and device and electronic equipment | |
| CN107729486A (en) | A kind of video searching method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |
|
| RJ01 | Rejection of invention patent application after publication |