CN108924644A - Video clip extracting method and device - Google Patents
Video clip extracting method and device Download PDFInfo
- Publication number
- CN108924644A CN108924644A CN201810638750.XA CN201810638750A CN108924644A CN 108924644 A CN108924644 A CN 108924644A CN 201810638750 A CN201810638750 A CN 201810638750A CN 108924644 A CN108924644 A CN 108924644A
- Authority
- CN
- China
- Prior art keywords
- video
- processed
- time point
- point
- time
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000000605 extraction Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims description 42
- 230000008859 change Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 239000012634 fragment Substances 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 22
- 238000005516 engineering process Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000005236 sound signal Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000012092 media component Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 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]
- H04N21/40—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]
- H04N21/40—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
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
This disclosure relates to a kind of video clip extracting method and device.This method includes:According to the characteristic information of video to be processed, the period of interest point in video to be processed is determined, wherein characteristic information includes at least one of audience ratings and watching focus of video to be processed of video to be processed;It will be according to multiple switching time points of video to be processed, the determining target switching time point for being less than or equal to time interval threshold value with the time interval of period of interest point;According to the first time period that target switching time point and target object occur in video to be processed, the second time period for carrying out video clip extraction is determined;According to second time period, the video clip for target object is extracted from video to be processed.Video clip extracting method and device provided by the embodiment of the present disclosure, extracted video clip can characterize the content of video, and extract that the high-efficient of video clip, speed is fast, accuracy is good, save the human and material resources cost for extracting video clip.
Description
Technical field
This disclosure relates to field of computer technology more particularly to a kind of video clip extracting method and device.
Background technique
With the continuous development of the terminals such as smart phone, user can watch interested video by terminal.Related skill
It is general to pass through viewing view during user browses many kinds of, substantial amounts video selections interested video in art
The cover picture of frequency, trailer, dynamic picture etc. determine whether the video is interested video.But due to the surface plot of video
The information content of piece is limited, and user is difficult to determine the particular content of video based on cover picture.Although user can also pass through video
Trailer, dynamic picture etc. determine the particular content of video, but the play time of trailer is too long, occupy user it is longer when
Between;The content that dynamic picture can express is limited, and the understanding without acoustic impacts user to video.It in the related technology, can be with
Editing is carried out to video by artificial mode, produces the video clip that can characterize the content of video.But artificial editing
It is mode low efficiency, at high cost.
Summary of the invention
In view of this, the present disclosure proposes a kind of video clip extracting method and devices.
According to the disclosure in a first aspect, provide a kind of video clip extracting method, including:
According to the characteristic information of video to be processed, the period of interest point in the video to be processed is determined, wherein the spy
Reference breath includes the audience ratings of the video to be processed and at least one of the watching focus of the video to be processed;
According to multiple switching time points of the video to be processed, the determining time interval with the period of interest point is less than
Or the target switching time point equal to time interval threshold value;
According to the first time period that the target switching time point and target object occur in the video to be processed, really
Surely the second time period of video clip extraction is carried out;
According to the second time period, the piece of video for the target object is extracted from the video to be processed
Section.
For the above method, in one possible implementation, according to the characteristic information of video to be processed, determine described in
Period of interest point in video to be processed, including:
Audience ratings in the video to be processed is greater than or equal to corresponding to the audience ratings extreme point of rating threshold and is broadcast
Time point is put, the period of interest point is determined as.
For the above method, in one possible implementation, the method also includes:
Image recognition processing is carried out to multiple screenshots of the video to be processed, is determined in the multiple screenshot comprising
State the target screenshot of target object;
In the target screenshot there are quantity be greater than or equal to the first amount threshold continuous target screenshot when, according to
The continuous target screenshot, determines the first time period.
For the above method, in one possible implementation, the method also includes:
Text region processing is carried out to multiple screenshots of the video to be processed, determines and does not include word in the multiple screenshot
The screenshot of curtain;
According to the screenshot not comprising subtitle, determine in the video to be processed not comprising subtitle without credit video piece
Section;
The time point that generation Shot change in the no credit video segment will be belonged to is determined as the switching time point.
For the above method, in one possible implementation, according to the target switching time point and described first
Period determines the second time period for carrying out video clip extraction, including:
According to the first time point that the first time period starts, described first will be in the target switching time point
The smallest target switching time point of time interval before time point, and between the first time point is determined as described
The second time point that two periods started;
The third time point terminated according to the first time period will be in the third in the target switching time point
The smallest target switching time point of time interval after time point, and between the third time point is determined as described
The 4th time point that two periods terminated;
According to second time point and the 4th time point, the second time period is determined.
For the above method, in one possible implementation, according to the second time period, from the view to be processed
The video clip for the target object is extracted in frequency, including:
When the duration of the second time period is less than or equal to duration threshold value, according to the second time period, from described
The video clip for the target object is extracted in video to be processed.
According to the second aspect of the disclosure, a kind of video clip extraction element is provided, including:
Period of interest point determining module determines emerging in the video to be processed according to the characteristic information of video to be processed
Interesting time point, wherein the characteristic information includes in the audience ratings of the video to be processed and the watching focus of the video to be processed
At least one;
Target switching time point determining module, according to multiple switching time points of the video to be processed, it is determining with it is described
The time interval of period of interest point is less than or equal to the target switching time point of time interval threshold value;
Second time period determining module, according to the target switching time point and target object in the video to be processed
The first time period of appearance determines the second time period for carrying out video clip extraction;
Video clip extraction module is extracted from the video to be processed according to the second time period for described
The video clip of target object.
For above-mentioned apparatus, in one possible implementation, period of interest point determining module, including:
Audience ratings determines submodule, and audience ratings in the video to be processed is greater than or equal to the audience ratings of rating threshold
Play time corresponding to extreme point is determined as the period of interest point.
For above-mentioned apparatus, in one possible implementation, described device further includes:
Target screenshot determining module carries out image recognition processing to multiple screenshots of the video to be processed, determine described in
It include the target screenshot of the target object in multiple screenshots;
First time period determining module, there are the companies that quantity is greater than or equal to the first amount threshold in the target screenshot
When continuous target screenshot, according to the continuous target screenshot, the first time period is determined.
For above-mentioned apparatus, in one possible implementation, described device further includes:
Text region module carries out Text region processing to multiple screenshots of the video to be processed, determines the multiple
The screenshot of subtitle is not included in screenshot;
It determines and is not wrapped in the video to be processed according to the screenshot not comprising subtitle without subtitle fragment determining module
Containing subtitle without credit video segment;
Switching time point determining module, the time point that will belong to generation Shot change in the no credit video segment determine
For the switching time point.
For above-mentioned apparatus, in one possible implementation, second time period determining module, including:
Second time point determined submodule, and according to the first time point that the first time period starts, the target is cut
It changes in time point before the first time point, and the smallest target of time interval between the first time point is cut
Time point is changed, the second time point that the second time period starts is determined as;
4th time point determined submodule, at the third time point terminated according to the first time period, the target was cut
It changes in time point after the third time point, and the smallest target of time interval between the third time point is cut
Time point is changed, the 4th time point that the second time period terminates is determined as;
Second time period determines submodule, according to second time point and the 4th time point, determines described second
Period.
For above-mentioned apparatus, in one possible implementation, the video clip extraction module, including:
Video clip extracting sub-module, when the duration of the second time period is less than or equal to duration threshold value, according to institute
Second time period is stated, the video clip for the target object is extracted from the video to be processed.
According to the third aspect of the disclosure, a kind of video clip extraction element is provided, including:Processor;For storing
The memory of processor-executable instruction;Wherein, the processor is configured to executing above-mentioned video clip extracting method.
According to the fourth aspect of the disclosure, a kind of non-volatile computer readable storage medium storing program for executing is provided, is stored thereon with
Computer program instructions, wherein the computer program instructions realize above-mentioned video clip extracting method when being executed by processor.
Video clip extracting method and device according to provided by the embodiment of the present disclosure are believed according to the feature of video to be processed
Breath, determines the period of interest point in video to be processed, wherein characteristic information includes the audience ratings and view to be processed of video to be processed
At least one of watching focus of frequency;It will be according to multiple switching time points of video to be processed, the determining time with period of interest point
Interval is less than or equal to the target switching time point of time interval threshold value;According to target switching time point and target object wait locate
The first time period occurred in reason video, determines the second time period for carrying out video clip extraction;According to second time period, to
The video clip for target object is extracted in processing video.The video clip of extraction can characterize the content of video, and mention
It takes that the high-efficient of video clip, speed are fast, accuracy is good, saves the human and material resources cost for extracting video clip.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the other feature and aspect of the disclosure will become
It is clear.
Detailed description of the invention
Comprising in the description and constituting the attached drawing of part of specification and specification together illustrates the disclosure
Exemplary embodiment, feature and aspect, and for explaining the principles of this disclosure.
Fig. 1 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure;
Fig. 2 shows the flow charts according to the video clip extracting method of one embodiment of the disclosure;
Fig. 3 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure;
Fig. 4 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure;
Fig. 5 shows the flow chart of step S13 in the video clip extracting method according to one embodiment of the disclosure;
Fig. 6 shows the schematic diagram of step S13 in the video clip extracting method according to one embodiment of the disclosure;
Fig. 7 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure;
Fig. 8 a, Fig. 8 b show the schematic diagram of the application scenarios of the video clip extracting method according to one embodiment of the disclosure;
Fig. 9 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure;
Figure 10 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure;
Figure 11 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure;
Figure 12 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure.
Specific embodiment
Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to attached drawing.It is identical in attached drawing
Appended drawing reference indicate element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, remove
It non-specifically points out, it is not necessary to attached drawing drawn to scale.
Dedicated word " exemplary " means " being used as example, embodiment or illustrative " herein.Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, giving numerous details in specific embodiment below to better illustrate the disclosure.
It will be appreciated by those skilled in the art that without certain details, the disclosure equally be can be implemented.In some instances, for
Method, means, element and circuit well known to those skilled in the art are not described in detail, in order to highlight the purport of the disclosure.
Fig. 1 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure.This method can be applied to
The terminals such as computer, also can be applied to server.As shown in Figure 1, the method comprising the steps of S11 to step S14.
In step s 11, according to the characteristic information of video to be processed, the period of interest point in video to be processed is determined.Its
In, characteristic information may include at least one of audience ratings and watching focus of video to be processed of video to be processed.
In the present embodiment, video to be processed can be the videos such as TV play, film, variety show, concert.Feature letter
Breath can also be that other can characterize user to the information of the interested degree of each video clip of video to be processed, the disclosure pair
The concrete type of video and characteristic information to be processed is with no restriction.Period of interest point in determining video to be processed, can be
Time point relevant to the audience ratings of video to be processed, watching focus.For example, when period of interest point can be broadcasting corresponding to watching focus
Between point.Period of interest point can also be the corresponding play time in audience ratings maximum place of video to be processed.
In the present embodiment, refer in video being capable of noticeable or worth viewing part for the watching focus of video to be processed.
The watching focus of video can be the production side of video, operator etc. according to the curriculum offering of video, can be according to role in video
Between conflict, the development of plot etc. the watching focus of video is configured, the disclosure to this with no restriction.For example, certain film
Two leading roles in the film are quarrelled fierce time point, are determined as watching focus by production side.The audience ratings of video to be processed refers to a certain
Watch that the number of the video to be processed accounts for the percentage of video spectators' total number of persons in period.
In step s 12, according to multiple switching time points of video to be processed, the determining time interval with period of interest point
Less than or equal to the target switching time point of time interval threshold value.
It in the present embodiment, can be according to duration, duration of required video clip of video to be processed etc. between the time
It is configured every threshold value.For example, setting time interval threshold value to 1 minute.Those skilled in the art can be according to actual needs
Time interval threshold is configured, the disclosure to this with no restriction.
In the present embodiment, switching time point can be the time point that Shot change occurs in video to be processed.It can lead to
Cross FFmpeg technology (FFmpeg be it is a set of can be used to record, converted digital audio, video, and opening for stream can be translated into
Source computer program) etc. come determine in video to be processed carry out Shot change time point.
In the present embodiment, switching time point can also be according to the period in video to be processed without plot and mirror occur
What the time point of head switching determined.It can be by time point in the period for belonging to no plot in video, that Shot change occurs
It is determined as switching time point.In this way, while guaranteeing switching time point is that the time point of Shot change occurs, it can also be ensured that
There is no plots for switching time point, guarantee the integrality of extracted video clip, meet the viewing demand of user.
In the present embodiment, video voiceless sound to be processed can be determined by the carry out voice recognition to video to be processed
Period, and be determined as to the period of no plot the asonant period.For example, identify video to be processed t1~
In t2 this period in the case where noiseless sound signal, t1~t2 can be determined as to the period of no plot.It can also be by right
Multiple screenshots of video to be processed carry out Text region, determine in video to be processed not comprising subtitle without credit video segment,
And no credit video segment is determined as to the period of no plot.Face can also be carried out by multiple screenshots to video to be processed
Color identification, determines the period without plot in video to be processed.Those skilled in the art can be according to actual needs to determination
The mode of the period without plot in video to be processed is configured, the disclosure to this with no restriction.
In step s 13, the first time occurred in video to be processed according to target switching time point and target object
Section determines the second time period for carrying out video clip extraction.
In the present embodiment, the duration of first time period can be greater than or equal to clip durations threshold value, to guarantee final institute
The video clip user extracted can watch, and therefrom determine the associated video content of video to be processed, meet the sight of user
See demand.Clip durations threshold value can be configured according to duration, the viewing demand of user etc. of video to be processed, the disclosure
With no restriction to this.For example, setting clip durations threshold value to 6 seconds.
In the present embodiment, target object can be one, be also possible to multiple.Target object can be video to be processed
The people of middle appearance, is also possible to the objects such as the animal occurred in video to be processed, article, the disclosure to this with no restriction.For example,
Target object can be star A and star B, be also possible to star D.It can be needed according to the extraction of video clip to target object
Quantity and classification be configured, the disclosure to this with no restriction.
In step S14, according to second time period, the piece of video for target object is extracted from video to be processed
Section.
In the present embodiment, corresponding second time period is extracted from video to be processed according to second time period and is directed to
The video clip of target object.It is then possible to according to the targeted target object of video clip, related story introduction etc. and the view
The relevant information of frequency segment, is marked video clip, is extracted in order to basis labeled as different user's recommendations
Video clip.
It in the present embodiment, can be using the video clip of extraction as the cover of video to be processed, so that user passes through
Video clip as cover determines the content of video to be processed, understands the plot of video to be processed.
Video clip extracting method provided by the embodiment of the present disclosure, according to the characteristic information of video to be processed, determine to
Handle the period of interest point in video, wherein characteristic information includes the audience ratings of video to be processed and the watching focus of video to be processed
At least one of;By according to multiple switching time points of video to be processed, the determining time interval with period of interest point is less than
Or the target switching time point equal to time interval threshold value;According to target switching time point and target object in video to be processed
The first time period of appearance determines the second time period for carrying out video clip extraction;According to second time period, from video to be processed
In extract video clip for target object.The video clip of extraction can characterize the content of video, and extract piece of video
Section it is high-efficient, speed is fast, accuracy is good, save extract video clip human and material resources cost.
Fig. 2 shows the flow charts according to the video clip extracting method of one embodiment of the disclosure.In a kind of possible realization
In mode, as shown in Fig. 2, step S11 may include step S111.
In step S111, audience ratings in video to be processed is greater than or equal to the audience ratings extreme point institute of rating threshold
Corresponding play time is determined as period of interest point.
In this implementation, rating threshold can be according to the average value of audience ratings, required extraction in video to be processed
The number etc. of video clip rating threshold is configured, the disclosure to this with no restriction.Audience ratings extreme point can be
The maximum point in the curve of the audience ratings of video to be processed is characterized, to guarantee that it is to be processed that video clip obtained can show
The video feature and video content of video, so that user can determine in video to be processed according to extracted video clip
Hold, determines whether it is interested video.
In this implementation, all maximum points in the audience ratings curve of video to be processed can also be obtained, and according to
It needs play time corresponding to part extreme point therein being determined as period of interest point.For example, certain video to be processed
It include maximum point Q1, Q2, Q3, Q4 and Q5 in audience ratings curve, and the size order of maximum point is Q1 > Q2 > Q3 > Q4
> Q5.The number of required period of interest point is 3, then the preceding 3 maximum point Q1, Q2 that will sort in 5 maximum points,
Play time t1, t2, t3 corresponding to Q3 are determined as period of interest point.
Fig. 3 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure.As shown in figure 3, this method
It can also include step S15 and step S16.
In step S15, image recognition processing is carried out to multiple screenshots of video to be processed, determines in multiple screenshots and includes
There is the target screenshot of target object.
In the present embodiment, multiple screenshots of video to be processed can be the video frame of video to be processed, be also possible to pair
Video to be processed carries out screenshot and handles screenshot obtained, the disclosure to this with no restriction.For same video to be processed, institute is really
The quantity of fixed screenshot is more, and the first time period that determining target object occurs in video to be processed is more accurate.Wait locate
It, can be according to first time interval when multiple screenshots of reason video are to video to be processed progress screenshot processing screenshot obtained
Screenshot processing is carried out to video to be processed, to guarantee the content in screenshot, there are certain differences, the quantity of multiple screenshots is reduced,
The time of image recognition is saved, the speed for extracting video clip is accelerated.Those skilled in the art can according to actual needs to cut
Figure acquisition and acquired quantity be configured, the disclosure to this with no restriction.
In the present embodiment, image recognition can be carried out to screenshot, the feature of the object occurred in screenshot is extracted, by this
The feature of object is compared with the target signature of target object, and the screenshot comprising target signature is determined as target screenshot.It can
Target screenshot to be marked according to the title of target object, classification etc., according to included in the determining target screenshot of label
Target object.It, can be according to the history of different user in the case where video clip to be determined as to the cover of video to be processed
Property for user show corresponding video clip, then can be that drill by target object for example, user likes watching the video of performer A
The video clip of member A is selected as the cover of certain video to be processed.According to the difference of target object, different technologies pair can be used
Screenshot is identified.For example, can be obtained using face recognition technology in the case where target object is people in video occur
The face feature of the people in screenshot is taken, to determine in screenshot with the presence or absence of target object.
In the present embodiment, the target signature of target object can be obtained in advance.For example, a large amount of packet can be obtained in advance
The image of target object is included, feature extraction then is carried out to image, the target signature of target object is determined by training.
In step s 16, the continuous target for being greater than or equal to the first amount threshold there are quantity in target screenshot is cut
When figure, according to continuous target screenshot, first time period is determined.
In the present embodiment, can according between screenshot time interval and clip durations threshold value determine the first quantity threshold
Value.For example, carrying out screenshot processing to video to be processed for time interval with 1 second, multiple screenshots of video to be processed are obtained.In piece
In the case that Duan Shichang threshold value is set as 6 seconds, the first amount threshold can be set to 6s ÷ 1s=6.
In this implementation, it can be determined according to the time of occurrence for playing target screenshot during video to be processed
It whether is continuous between target screenshot.During playing video to be processed, if two target screenshots successively occur, and two
Other screenshots are not present between a target screenshot, it is determined that two target screenshots are continuous target screenshot.It can be to be processed
Multiple screenshots of video are successively numbered according to its appearance sequence in the playing process of video to be processed, number adjacent
Two screenshots are continuous.In this way, can determine whether between different target screenshot be continuous according to numbering.For example, certain is waited for
Appearance sequence and number of the multiple screenshots of video in the playing process of the video to be processed is handled to be followed successively by:Screenshot a-1 (is cut
The map title claims-numbers), screenshot b-2, screenshot c-3, screenshot d-4, screenshot e-5, screenshot f-6, screenshot g-7 and screenshot h-8.Determining
It include that the target screenshot of target object is:Screenshot a, screenshot b, screenshot c and screenshot h.Continuous target screenshot be screenshot a,
Screenshot b, screenshot c.
Fig. 4 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure.As shown in figure 4, this method
It can also include step S17 to step S19.
In step S17, Text region processing is carried out to multiple screenshots of video to be processed, determines and is not wrapped in multiple screenshots
Screenshot containing subtitle.
In the present embodiment, can the region of the display subtitle such as lower zone to screenshot carry out Text region processing, really
It include the screenshot of subtitle in fixed multiple screenshots.Then, the screenshot for not including subtitle in multiple screenshots is determined by way of counter select.
In step S18, according to the screenshot for not including subtitle, regarding without subtitle not comprising subtitle in video to be processed is determined
Frequency segment.
In the present embodiment, video to be processed can be determined according to two or more continuous screenshots for not including subtitle
In do not include subtitle without credit video segment.Can according to playing video to be processed during do not include the screenshot of subtitle
Time of occurrence determines between the screenshot for not including subtitle whether be continuous, the determination side of the continuous screenshot not comprising subtitle
Formula is identical as the method for determination of continuous target screenshot, can refer to the associated description of step S16.
In step S19, the time point that will belong to generation Shot change in no credit video segment is determined as switching time
Point.
In this manner it is ensured that the video clip for target object finally extracted can have complete plot, it is full
The viewing demand of sufficient user.
Fig. 5 shows the flow chart of step S13 in the video clip extracting method according to one embodiment of the disclosure.One kind can
In the implementation of energy, as shown in figure 5, step S13 may include step S131 to step S133.
In step S131, the first time point started according to first time period will be in target switching time point in the
The smallest target switching time point of time interval before one time point, and between first time point, was determined as the second time
The second time point that section starts.
It wherein, can be true by first time point in the case where target switching time point is not present before first time point
It was set to for the second time point.
It, the third time point terminated according to first time period, will be in target switching time point in the in step S132
The smallest target switching time point of time interval after three time points, and between third time point, was determined as the second time
The 4th time point that section terminates.
It wherein, can be true by third time point in the case where target switching time point is not present after third time point
It was set to for the 4th time point.
In step S133, according to the second time point and the 4th time point, second time period is determined.
Fig. 6 shows the schematic diagram of step S13 in the video clip extracting method according to one embodiment of the disclosure.Such as Fig. 6 institute
Show, the first time point t0 started according to first time period t0~t1, will in target switching time point T1 and T2 in t0 it
Before, and the smallest target switching time point T1 of time interval between t0 is determined as the second time that second time period starts
Point.The third time point t1 terminated according to first time period t0~t1, due to being not present among target switching time point T1 and T2
Third time point t1 was then determined as the 4th time point by the time point after t1.Then, according to determining third time point
With the 4th time point, second time period T1~t3 is determined.
Fig. 7 shows the flow chart of the video clip extracting method according to one embodiment of the disclosure.In a kind of possible realization
In mode, as shown in fig. 7, step S14 may include step S141.
In step s 141, when the duration of second time period is less than or equal to duration threshold value, according to second time period, from
The video clip for target object is extracted in video to be processed.
It in this implementation, can be according to duration, content of video to be processed of video to be processed etc. to duration threshold value
Be configured, the disclosure to this with no restriction.
It should be noted that it is as above although describing video clip extracting method using above-described embodiment as example, this
Field technical staff it is understood that the disclosure answer it is without being limited thereto.In fact, user completely can be according to personal preference and/or reality
Application scenarios flexibly set each step, as long as meeting the technical solution of the disclosure.
Below in conjunction with " carrying out video clip extraction to video A " property application scenarios as an example, provide according to this public affairs
The application example of embodiment is opened, in order to understand the process of video clip extracting method.It will be understood by those skilled in the art that following
Using example merely for the sake of the purpose for being easy to understand the embodiment of the present disclosure, it is not construed as the limitation to the embodiment of the present disclosure.
Fig. 8 a, Fig. 8 b show the schematic diagram of the application scenarios of the video clip extracting method according to one embodiment of the disclosure.
As shown in Fig. 8 a, Fig. 8 b, the process that video clip extraction is carried out to video A includes step S201 to step S212.
In step s 201, video A is obtained, for example, can be locally downloading by video A.
In step S202, according to the audience ratings curve of determining video A, determine period of interest point X in video A (such as
Shown in Fig. 8 b).
In step S203, screenshot processing is carried out to video A with first time interval (such as 1 second), obtains the more of video A
A screenshot, and screenshot is numbered according to appearance sequence of each screenshot in video A.For example, screenshot is Ci, i is screenshot
Number (as shown in Figure 8 b).
In step S204, image recognition processing is carried out to multiple screenshots, determines to include target object in multiple screenshots
Target screenshot Ci ', i are the number (as shown in Figure 8 b) of screenshot.
In step S205, the first amount threshold (such as 5) are greater than or equal to according to quantity present in target screenshot
Continuous target screenshot, determines its corresponding first time period D1 (as shown in Figure 8 b).
In step S206, Text region is carried out to screenshot, determines that the screenshot Ci ", i that do not include subtitle are the number of screenshot
(as shown in Figure 8 b).
In step S207, according to the determining screenshot Ci " not comprising subtitle, determination is not comprising subtitle without credit video
Segment P1 (as shown in Figure 8 b).
In step S208, video A is identified, determines time point Q (such as Fig. 8 b for carrying out Shot change in video A
It is shown).
In step S209, the time point Q for the progress Shot change for belonging to no credit video segment P1 is determined as switching
Time point Q ' (as shown in Figure 8 b).Detailed process refers to the associated description of step S19.
In step S210, according to the switching time of video A point Q ', the determining time interval with period of interest point X is less than
Or it is equal to the target switching time point Q " (as shown in Figure 8 b) of time interval threshold value T (such as 1 minute).
In step S211, according to first time period D1 and target switching time point Q ", determine second time period D2 (as schemed
Shown in 8b).Detailed process refers to the associated description of step S131 to step S133.
In step S212, the video clip for target object is extracted according to second time period D2.
In this way, the video clip extracted can characterize the content of video A, and extract the high-efficient of video clip, speed it is fast,
Accuracy is good, saves the human and material resources cost for extracting video clip.
Fig. 9 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure.As shown in figure 9, the device packet
Include period of interest point determining module 51, target switching time point determining module 52, second time period determining module 53 and piece of video
Section extraction module 54.
The period of interest point determining module 51 is configured as the characteristic information according to video to be processed, determines video to be processed
In period of interest point.Wherein, characteristic information may include in the audience ratings of video to be processed and the watching focus of video to be processed
It is at least one.The target switching time point determining module 52 is configured as multiple switching time points according to video to be processed, really
Fixed and period of interest point time interval is less than or equal to the target switching time point of time interval threshold value.The second time period is true
Cover half block 53 is configured as the first time period occurred in video to be processed according to target switching time point and target object, really
Surely the second time period of video clip extraction is carried out.The video clip extraction module 54 is configured as according to second time period, from
The video clip for target object is extracted in video to be processed.
Figure 10 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure.
In one possible implementation, as shown in Figure 10, period of interest point determining module 51 may include audience ratings
Determine submodule 511.The audience ratings determines that submodule 511 is configured as audience ratings in video to be processed being greater than or equal to rating
Play time corresponding to the audience ratings extreme point of rate threshold value is determined as period of interest point.
In one possible implementation, as shown in Figure 10, which can also include target screenshot determining module 55
With first time period determining module 56.The target screenshot determining module 55 is configured as carrying out multiple screenshots of video to be processed
Image recognition processing, determine include in multiple screenshots target object target screenshot.56 quilt of first time period determining module
Be configured in target screenshot there are quantity be greater than or equal to the first amount threshold continuous target screenshot when, according to continuous
Target screenshot, determines first time period.
In one possible implementation, as shown in Figure 10, which can also include Text region module 57, without word
Mask section determining module 58 and switching time point determining module 59.The text identification module 57 is configured as to video to be processed
Multiple screenshots carry out Text region processing, determine the screenshot for not including subtitle in multiple screenshots.This is without subtitle fragment determining module
58 are configured as being determined in video to be processed not comprising subtitle according to the screenshot for not including subtitle without credit video segment.It should
The time point that switching time point determining module 59 is configured as to belong to generation Shot change in no credit video segment is determined as
Switching time point.
In one possible implementation, as shown in Figure 10, when second time period determining module 53 may include second
Between put and determine that submodule 531, the 4th time point determine that submodule 532 and second time period determine submodule 533.Second time
Point determines that submodule 531 is configured as the first time point started according to first time period, will be in target switching time point
The smallest target switching time point of time interval before first time point, and between first time point, when being determined as second
Between the second time point for starting of section.4th time point determined that submodule 532 is configured as terminating according to first time period
At three time points, after being in third time point in target switching time point, and the time interval between third time point is most
Small target switching time point, is determined as the 4th time point that second time period terminates.The second time period determines submodule 533
It is configured as determining second time period according to the second time point and the 4th time point.
In one possible implementation, as shown in Figure 10, video clip extraction module 54 may include video clip
Extracting sub-module 541.The video clip extracting sub-module 541 is configured as being less than or equal to duration when the duration of second time period
When threshold value, according to second time period, the video clip for target object is extracted from video to be processed.
It should be noted that it is as above although describing video clip extraction element using above-described embodiment as example, this
Field technical staff it is understood that the disclosure answer it is without being limited thereto.In fact, user completely can be according to personal preference and/or reality
Application scenarios flexibly set each module, as long as meeting the technical solution of the disclosure.
The video clip of video clip extraction element provided by the embodiment of the present disclosure, extraction can characterize the interior of video
Hold, and extract the high-efficient of video clip, speed is fast, accuracy is good, save extract video clip human and material resources cost.
Figure 11 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure.For example, device 800 can be
Mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, Medical Devices, body-building are set
It is standby, personal digital assistant etc..
Referring to Fig.1 1, device 800 may include following one or more components:Processing component 802, memory 804, power supply
Component 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor module 814, and
Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 802 may include that one or more processors 820 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more modules, just
Interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, it is more to facilitate
Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in device 800.These data are shown
Example includes the instruction of any application or method for operating on device 800, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 may include power management system
System, one or more power supplys and other with for device 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen of one output interface of offer between described device 800 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 808 includes a front camera and/or rear camera.When device 800 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when device 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 804 or via communication set
Part 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, is used for output audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to:Home button, volume button, start button and lock
Determine button.
Sensor module 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor module 814 can detecte the state that opens/closes of device 800, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 800, and sensor module 814 can be with 800 1 components of detection device 800 or device
Position change, the existence or non-existence that user contacts with device 800,800 orientation of device or acceleration/deceleration and device 800
Temperature change.Sensor module 814 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 814 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing is additionally provided, for example including calculating
The memory 804 of machine program instruction, above-mentioned computer program instructions can be executed above-mentioned to complete by the processor 820 of device 800
Method.
Figure 12 shows the block diagram of the video clip extraction element according to one embodiment of the disclosure.For example, device 1900 can be with
It is provided as a server.Referring to Fig.1 2, it further comprises one or more processing that device 1900, which includes processing component 1922,
Device and memory resource represented by a memory 1932, can be by the instruction of the execution of processing component 1922, example for storing
Such as application program.The application program stored in memory 1932 may include it is one or more each correspond to one group
The module of instruction.In addition, processing component 1922 is configured as executing instruction, to execute the above method.
Device 1900 can also include that a power supply module 1926 be configured as the power management of executive device 1900, and one
Wired or wireless network interface 1950 is configured as device 1900 being connected to network and input and output (I/O) interface
1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing is additionally provided, for example including calculating
The memory 1932 of machine program instruction, above-mentioned computer program instructions can be executed by the processing component 1922 of device 1900 to complete
The above method.
The disclosure can be system, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the disclosure.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment
Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes:Portable computer diskette, random access memory (RAM), read-only is deposited hard disk
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing disclosure operation can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one
Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the disclosure
Face.
Referring herein to according to the flow chart of the method, apparatus (system) of the embodiment of the present disclosure and computer program product and/
Or block diagram describes various aspects of the disclosure.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced
The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction
Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the disclosure
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
The presently disclosed embodiments is described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In the principle, practical application or technological improvement to the technology in market for best explaining each embodiment, or lead this technology
Other those of ordinary skill in domain can understand each embodiment disclosed herein.
Claims (14)
1. a kind of video clip extracting method, which is characterized in that including:
According to the characteristic information of video to be processed, the period of interest point in the video to be processed is determined, wherein the feature letter
Breath includes the audience ratings of the video to be processed and at least one of the watching focus of the video to be processed;
According to multiple switching time points of the video to be processed, the determining time interval with the period of interest point is less than or waits
In the target switching time point of time interval threshold value;
According to the first time period that the target switching time point and target object occur in the video to be processed, determine into
The second time period that row video clip is extracted;
According to the second time period, the video clip for the target object is extracted from the video to be processed.
2. the method according to claim 1, wherein according to the characteristic information of video to be processed, determine it is described to
The period of interest point in video is handled, including:
When audience ratings in the video to be processed is greater than or equal to broadcasting corresponding to the audience ratings extreme point of rating threshold
Between point, be determined as the period of interest point.
3. the method according to claim 1, wherein the method also includes:
Image recognition processing is carried out to multiple screenshots of the video to be processed, determines to include the mesh in the multiple screenshot
Mark the target screenshot of object;
In the target screenshot there are quantity be greater than or equal to the first amount threshold continuous target screenshot when, according to described
Continuous target screenshot, determines the first time period.
4. the method according to claim 1, wherein the method also includes:
Text region processing is carried out to multiple screenshots of the video to be processed, determines and does not include subtitle in the multiple screenshot
Screenshot;
According to the screenshot not comprising subtitle, determine in the video to be processed not comprising subtitle without credit video segment;
The time point that generation Shot change in the no credit video segment will be belonged to is determined as the switching time point.
5. the method according to claim 1, wherein according to the target switching time point and the first time
Section determines the second time period for carrying out video clip extraction, including:
According to the first time point that the first time period starts, the first time will be in the target switching time point
Before point, and the smallest target switching time point of time interval between the first time point, when being determined as described second
Between the second time point for starting of section;
The third time point terminated according to the first time period will be in the third time in the target switching time point
After point, and the smallest target switching time point of time interval between the third time point, when being determined as described second
Between the 4th time point for terminating of section;
According to second time point and the 4th time point, the second time period is determined.
6. the method according to claim 1, wherein according to the second time period, from the video to be processed
In extract video clip for the target object, including:
When the duration of the second time period is less than or equal to duration threshold value, according to the second time period, from described to from
The video clip for the target object is extracted in reason video.
7. a kind of video clip extraction element, which is characterized in that including:
Period of interest point determining module, according to the characteristic information of video to be processed, when determining the interest in the video to be processed
Between point, wherein the characteristic information include in the audience ratings of the video to be processed and the watching focus of the video to be processed extremely
Few one kind;
Target switching time point determining module, according to multiple switching time points of the video to be processed, the determining and interest
The time interval at time point is less than or equal to the target switching time point of time interval threshold value;
Second time period determining module occurs in the video to be processed according to the target switching time point and target object
First time period, determine carry out video clip extraction second time period;
Video clip extraction module is extracted from the video to be processed for the target according to the second time period
The video clip of object.
8. device according to claim 7, which is characterized in that period of interest point determining module, including:
Audience ratings determines submodule, and audience ratings in the video to be processed is greater than or equal to the audience ratings extreme value of rating threshold
The corresponding play time of point, is determined as the period of interest point.
9. device according to claim 7, which is characterized in that described device further includes:
Target screenshot determining module carries out image recognition processing to multiple screenshots of the video to be processed, determines the multiple
It include the target screenshot of the target object in screenshot;
First time period determining module, there are quantity to be greater than or equal to the continuous of the first amount threshold in the target screenshot
When target screenshot, according to the continuous target screenshot, the first time period is determined.
10. device according to claim 7, which is characterized in that described device further includes:
Text region module carries out Text region processing to multiple screenshots of the video to be processed, determines the multiple screenshot
In do not include subtitle screenshot;
Without subtitle fragment determining module, according to the screenshot not comprising subtitle, determines and do not include word in the video to be processed
Curtain without credit video segment;
Switching time point determining module, the time point that will belong to generation Shot change in the no credit video segment are determined as institute
State switching time point.
11. device according to claim 7, which is characterized in that second time period determining module, including:
Second time point determined submodule, according to the first time point that the first time period starts, when the target is switched
Between in point before the first time point, and when the smallest target switching of time interval between the first time point
Between point, be determined as the second time point that the second time period starts;
4th time point determined submodule, the third time point terminated according to the first time period, when the target is switched
Between in point after the third time point, and when the smallest target switching of time interval between the third time point
Between point, be determined as the 4th time point that the second time period terminates;
Second time period determines submodule, according to second time point and the 4th time point, determines second time
Section.
12. device according to claim 7, which is characterized in that the video clip extraction module, including:
Video clip extracting sub-module, when the duration of the second time period is less than or equal to duration threshold value, according to described the
Two periods extracted the video clip for the target object from the video to be processed.
13. a kind of video clip extraction element, which is characterized in that including:
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to realizing method described in any one of claim 1 to 6 when executing.
14. a kind of non-volatile computer readable storage medium storing program for executing, is stored thereon with computer program instructions, which is characterized in that institute
It states and realizes method described in any one of claim 1 to 6 when computer program instructions are executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810638750.XA CN108924644B (en) | 2018-06-20 | 2018-06-20 | Video clip extraction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810638750.XA CN108924644B (en) | 2018-06-20 | 2018-06-20 | Video clip extraction method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108924644A true CN108924644A (en) | 2018-11-30 |
CN108924644B CN108924644B (en) | 2021-11-26 |
Family
ID=64420700
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810638750.XA Active CN108924644B (en) | 2018-06-20 | 2018-06-20 | Video clip extraction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108924644B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110191357A (en) * | 2019-06-28 | 2019-08-30 | 北京奇艺世纪科技有限公司 | The excellent degree assessment of video clip, dynamic seal face generate method and device |
CN111131884A (en) * | 2020-01-19 | 2020-05-08 | 腾讯科技(深圳)有限公司 | Video clipping method, related device, equipment and storage medium |
CN112488107A (en) * | 2020-12-04 | 2021-03-12 | 北京华录新媒信息技术有限公司 | Video subtitle processing method and processing device |
CN112528075A (en) * | 2020-12-02 | 2021-03-19 | 北京奇艺世纪科技有限公司 | Video cover generation 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 |
CN114979770A (en) * | 2022-06-28 | 2022-08-30 | 北京爱奇艺科技有限公司 | Video playing method and device, electronic equipment and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104519401A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Video division point acquiring method and equipment |
CN104780388A (en) * | 2015-03-31 | 2015-07-15 | 北京奇艺世纪科技有限公司 | Video data partitioning method and device |
CN104796781A (en) * | 2015-03-31 | 2015-07-22 | 小米科技有限责任公司 | Video clip extraction method and device |
CN105100894A (en) * | 2014-08-26 | 2015-11-25 | Tcl集团股份有限公司 | Automatic face annotation method and system |
CN106162222A (en) * | 2015-04-22 | 2016-11-23 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
CN106210902A (en) * | 2016-07-06 | 2016-12-07 | 华东师范大学 | A kind of cameo shot clipping method based on barrage comment data |
CN106303675A (en) * | 2016-08-24 | 2017-01-04 | 北京奇艺世纪科技有限公司 | A kind of video segment extracting method and device |
CN106851437A (en) * | 2017-01-17 | 2017-06-13 | 南通同洲电子有限责任公司 | A kind of method for extracting video frequency abstract |
CN107071587A (en) * | 2017-04-25 | 2017-08-18 | 腾讯科技(深圳)有限公司 | The acquisition methods and device of video segment |
US20170374398A1 (en) * | 2016-06-23 | 2017-12-28 | Bindu Rama Rao | Computing infrastructure for movie making and product placements |
CN108093315A (en) * | 2017-12-28 | 2018-05-29 | 优酷网络技术(北京)有限公司 | Video generation method and device |
-
2018
- 2018-06-20 CN CN201810638750.XA patent/CN108924644B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104519401A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Video division point acquiring method and equipment |
CN105100894A (en) * | 2014-08-26 | 2015-11-25 | Tcl集团股份有限公司 | Automatic face annotation method and system |
CN104780388A (en) * | 2015-03-31 | 2015-07-15 | 北京奇艺世纪科技有限公司 | Video data partitioning method and device |
CN104796781A (en) * | 2015-03-31 | 2015-07-22 | 小米科技有限责任公司 | Video clip extraction method and device |
CN106162222A (en) * | 2015-04-22 | 2016-11-23 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
US20170374398A1 (en) * | 2016-06-23 | 2017-12-28 | Bindu Rama Rao | Computing infrastructure for movie making and product placements |
CN106210902A (en) * | 2016-07-06 | 2016-12-07 | 华东师范大学 | A kind of cameo shot clipping method based on barrage comment data |
CN106303675A (en) * | 2016-08-24 | 2017-01-04 | 北京奇艺世纪科技有限公司 | A kind of video segment extracting method and device |
CN106851437A (en) * | 2017-01-17 | 2017-06-13 | 南通同洲电子有限责任公司 | A kind of method for extracting video frequency abstract |
CN107071587A (en) * | 2017-04-25 | 2017-08-18 | 腾讯科技(深圳)有限公司 | The acquisition methods and device of video segment |
CN108093315A (en) * | 2017-12-28 | 2018-05-29 | 优酷网络技术(北京)有限公司 | Video generation method and device |
Non-Patent Citations (2)
Title |
---|
A.D. DOULAMIS等: "Optimal content-based video decomposition for interactive video navigation", 《 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》 * |
王娟等: "视频摘要技术综述", 《中国图象图形学报》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110191357A (en) * | 2019-06-28 | 2019-08-30 | 北京奇艺世纪科技有限公司 | The excellent degree assessment of video clip, dynamic seal face generate method and device |
CN111131884A (en) * | 2020-01-19 | 2020-05-08 | 腾讯科技(深圳)有限公司 | Video clipping method, related device, equipment and storage medium |
CN111131884B (en) * | 2020-01-19 | 2021-11-23 | 腾讯科技(深圳)有限公司 | Video clipping method, related device, equipment and storage medium |
CN112528075A (en) * | 2020-12-02 | 2021-03-19 | 北京奇艺世纪科技有限公司 | Video cover generation method and device |
CN112488107A (en) * | 2020-12-04 | 2021-03-12 | 北京华录新媒信息技术有限公司 | Video subtitle processing method and processing 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 |
CN114979770A (en) * | 2022-06-28 | 2022-08-30 | 北京爱奇艺科技有限公司 | Video playing method and device, electronic equipment and storage medium |
CN114979770B (en) * | 2022-06-28 | 2024-02-02 | 北京爱奇艺科技有限公司 | Video playing method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108924644B (en) | 2021-11-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109189987A (en) | Video searching method and device | |
CN108924644A (en) | Video clip extracting method and device | |
CN107948708A (en) | Barrage methods of exhibiting and device | |
CN109089170A (en) | Barrage display methods and device | |
CN106792170A (en) | Method for processing video frequency and device | |
CN109729435A (en) | The extracting method and device of video clip | |
CN108985176A (en) | image generating method and device | |
CN106993229A (en) | Interactive attribute methods of exhibiting and device | |
CN108093315A (en) | Video generation method and device | |
CN108833939A (en) | Generate the method and device of the poster of video | |
CN108259991A (en) | Method for processing video frequency and device | |
CN106960014A (en) | Association user recommends method and device | |
CN110121083A (en) | The generation method and device of barrage | |
CN110121106A (en) | Video broadcasting method and device | |
CN110209877A (en) | Video analysis method and device | |
CN109151548A (en) | Interface alternation method and device | |
CN109803158A (en) | Video broadcasting method and device | |
CN108062364A (en) | Information displaying method and device | |
CN110519655A (en) | Video clipping method and device | |
CN108540850A (en) | Barrage display methods and device | |
CN109544716A (en) | Student registers method and device, electronic equipment and storage medium | |
CN109146789A (en) | Picture splicing method and device | |
CN107943550A (en) | Method for showing interface and device | |
CN108259974A (en) | Video matching method and device | |
CN108833952A (en) | The advertisement placement method and device of video |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200417 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100000 room 26, 9 Building 9, Wangjing east garden four, Chaoyang District, Beijing. Applicant before: BEIJING YOUKU TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |