CN103139663B - The automatic detachment device of video and the method automatically splitting thereof - Google Patents
The automatic detachment device of video and the method automatically splitting thereof Download PDFInfo
- Publication number
- CN103139663B CN103139663B CN201310032021.7A CN201310032021A CN103139663B CN 103139663 B CN103139663 B CN 103139663B CN 201310032021 A CN201310032021 A CN 201310032021A CN 103139663 B CN103139663 B CN 103139663B
- Authority
- CN
- China
- Prior art keywords
- point
- video
- frame
- module
- difference
- 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.)
- Active
Links
Landscapes
- Television Signal Processing For Recording (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
- Studio Circuits (AREA)
Abstract
The automatic detachment device of a kind of video, comprising: module, acquisition module, judge module are set and split module. The fractionation starting point of module marks video is set, is made as A point, the A point in video is designated as to C point simultaneously, the more lower B of the being designated as point that C is ordered; Acquisition module obtains frames all between A point and B point; Judge module judges whether the similitude of the frame between frame and the AB that B is ordered is greater than first threshold, and wherein, the similitude of the frame between frame and AB that judge module is also ordered at B judges while being greater than first threshold whether B point is the last frame in video; Splitting module is the video segment between A point and B point to be split out when last frame in video at B point. By the automatic detachment device of video of the present invention carry out video split can reach split efficiency high, ageing good.
Description
Technical field
The present invention relates to Video processing, relate in particular to the automatic detachment device of a kind of video and automatically tear openThe method of dividing.
Background technology
Video fractionation is at present all generally where artificial judgment video is to belong to same wherefromFragment, then manually splits.
But artificial fractionation needs a large amount of manpowers, because being people's browsing video from front to back,Could carry out segmentation to video according to content, manually watch video and differentiate need to spending when a large amount ofBetween, and often need to split a large amount of videos, so cost of labor is extremely high. Artificial fractionation oneIndividual video, need to this much the same time of video playback time, need so split videoTime very long, ageing non-constant, if it is just all the more so to split a large amount of videos.
Summary of the invention
In view of this, be necessary to provide a kind of high, ageing good video detachment device of efficiency that splitsAnd method.
The automatic detachment device of a kind of video provided by the invention, comprising: arrange module, acquisition module,Judge module and fractionation module. The fractionation starting point of module for marking video is set, is made as APoint is designated as C point by the A point in video simultaneously, the more lower B of the being designated as point that C is ordered; ObtainModule is for obtaining frames all between A point and B point; Judge module is for judging the frame that B is orderedAnd whether the similitude of the frame between AB is greater than first threshold, wherein, judge module is also at BThe similitude of the frame between frame and the AB of point judges whether B point is in video while being greater than first thresholdLast frame; Split module at B point be when video last frame by A point and B point itBetween video segment split out.
A kind of method that the present invention also provides video automatically to split, comprising: video starting point is made asA point; A point in video is designated as to C point, the more lower B of the being designated as point that C is ordered; Obtain AAll frames between point and B point; Whether the similitude that judges the frame between frame and the AB that B is ordered is largeIn first threshold; If so, judge whether B point is last frame in video; If so, by AVideo segment between point and B point splits out.
The automatic detachment device of video provided by the invention and the method automatically splitting thereof are looked by judgementFrequently in, the similitude of frame is determined fractionation point, and then video is split, and effectively carriesHigh fractionation efficiency is ageing good.
Brief description of the drawings
Fig. 1 is the module map of the automatic detachment device of video in an embodiment of the present invention;
Fig. 2 is the flow chart of the automatic method for splitting of video in an embodiment of the present invention.
Detailed description of the invention
Describe embodiments of the invention below in detail, the example of described embodiment is shown in the drawings,Wherein from start to finish same or similar label represent same or similar element or have identical orThe element of similar functions. Exemplary below by the embodiment being described with reference to the drawings, only forExplain the present invention, and can not be interpreted as limitation of the present invention.
In description of the invention, term " interior ", " outward ", " longitudinally ", " laterally ", " on ", D score,The orientation of the instruction such as " top ", " end " or position relationship are to close based on orientation shown in the drawings or positionSystem is only the present invention for convenience of description instead of require the present invention to construct with specific orientationAnd operation, therefore can not be interpreted as limitation of the present invention.
Refer to Fig. 1, Figure 1 shows that the automatic detachment device 10 of video in an embodiment of the present inventionModule map.
In the present embodiment, the automatic detachment device 10 of video comprises: module 102 is set, obtainsModule 104, judge module 106, fractionation module 108, processor 110 and memory module 112,Module 102, acquisition module 104, judge module 106 are set and split module 108 and be stored inIn memory module 112, processor 110 is for carrying out the modules of memory module 112.
In the present embodiment, the fractionation starting point of module 102 for marking video is set, is made asA point is designated as C point by the A point in video simultaneously, the more lower B of the being designated as point that C is ordered.
Acquisition module 104 is for obtaining frames all between A point and B point.
Judge module 106 is for judging whether the similitude of the frame between frame and the AB that B is ordered is greater thanOne threshold value. In the present embodiment, the frame that judge module 106 is ordered B and A point and A pointInstitute's frame a little compares one by one afterwards and before B point, and judgement has how many two field pictures and B to orderFrame is similar. In the present embodiment, similarly refer to fixing video features, for example same person,Or identical object, or identical background colour.
In the present embodiment, judge module 106 extracts video features, sentences according to video featuresThe frame that disconnected B order and A point and A point afterwards and B point before frame a little similitude whetherBe greater than first threshold.
In the present embodiment, judge module 106 is also for the frame between frame and the AB of ordering at BWhen being greater than first threshold, similitude judges whether B point is the last frame in video.
Split module 108 in the time that B point is video last frame by between A point and B pointVideo segment split out.
In the present embodiment, memory module 112 is for the frame between frame and the AB of ordering at described BSimilitude B point is recorded as to peculiar point while being not more than first threshold. In the present embodiment, depositWhen storage module 112 storage difference point, continuous difference point is stored together, and records continuous differenceThe number of point.
In the present embodiment, described judge module 106 is also for judging described memory module BBefore point, continuous difference counts whether be greater than Second Threshold.
In the present embodiment, the described module 102 that arranges is also for counting and be greater than in continuous differenceWhen described Second Threshold, a upper point of first difference point in described continuous difference point is changedBe made as C point.
In the present embodiment, split module 108 also for by the piece of video between A point and C pointSection splits out.
In the present embodiment, the described module 102 that arranges is also for by described continuous difference pointFirst difference point be made as A point.
In the present embodiment, the described module 102 that arranges is also for counting not quite in continuous differenceMore lower the changing of in the time of described Second Threshold, B being ordered is designated as B point, moves to down a bit by B point.
In the present embodiment, the described module 102 that arranges is not also for being that video is last at B pointMore lower the changing of when one frame, B being ordered is designated as B point, moves to down a bit by B point.
Refer to Fig. 2, Figure 2 shows that the automatic method for splitting of video in an embodiment of the present inventionFlow chart.
In the present embodiment, the automatic detachment device 10 of video is received the instruction that need to split videoTime, the method for execution graph 2.
At step S200, module 102 is set video starting point is made as to A point.
At step S202, module 102 is set the A point in video is designated as to C point, C is orderedBe designated as down B point.
At step S204, acquisition module 104 obtains all frames between A point and B point.
At step S206, judge module 106 judges that the similitude of the frame between frame and the AB that B is ordered isThe no first threshold that is greater than. In the present embodiment, seemingly refer to fixing video features, for example sameA people or identical object, or identical background colour.
In the present embodiment, judge module 106 extracts video features, sentences according to video featuresThe frame that disconnected B order and A point and A point afterwards and B point before frame a little similitude whetherBe greater than first threshold.
If the similitude of the frame between frame and AB that B is ordered is greater than first threshold, at step S208,Judge module 106 judges whether B point is last frame in video.
If B point is last frame in video, at step S210, split module 108 by A pointAnd the video segment between B point splits out.
If B point is not the last frame in video, at step S222, what B was ordered is more lowerChange and be designated as B point, move to down a bit by B point, next perform step S206, so do not doRepeat.
If the similitude of the frame between frame and AB that described B is ordered is not more than first threshold, in stepS212, described B point is recorded as peculiar point by memory module 112. In the present embodiment, at thisIn embodiment, when memory module 112 storage difference point, continuous difference point is stored together, andRecord the number of continuous difference point.
At step S214, judge module 106 judges that continuous difference is counted and whether is greater than Second Threshold.
Be greater than Second Threshold if continuous difference is counted, at step S216, module 102 is set willIn continuous difference point, first difference is put to change and is made as C point before described B point.
At step S218, split module 108 video segment between A point and C point is split outCome.
At step S210, module 102 is set by the in difference point continuous before described B pointA difference point is made as A point. Next perform step S202, so do not repeat.
Be not more than Second Threshold if described continuous difference is counted,, at step S222, module be set102 more lower the changing that B is ordered are designated as B point, move to down a bit by B point. Next carry out stepRapid S206, does not repeat at this.
The automatic detachment device 10 of video in embodiment of the present invention and the method automatically splitting thereof are logicalCross judge module 106 and judge that in video, the similitude of frame is determined fractionation point, and then video is carried outSplit, effectively raise fractionation efficiency, ageing good.
Although the present invention is described with reference to current preferred embodiments, the technology of this areaPersonnel will be understood that above-mentioned preferred embodiments is only used for illustrating the present invention, are not used for limiting thisThe protection domain of invention, any within the spirit and principles in the present invention scope, any repairing of doingDecorations, equivalence replacement, improvement etc., within all should being included in the scope of the present invention.
Claims (7)
1. the automatic detachment device of video, comprising:
Module is set, for the fractionation starting point of marking video, is made as A point, simultaneously by videoA point be designated as C point, the more lower B of the being designated as point that C is ordered; And count greatly in continuous differenceIn the time of Second Threshold, a upper point of first difference point in described continuous difference point is changed and establishedFor C point;
Acquisition module, for obtaining frames all between A point and B point;
Whether judge module, be greater than first for the similitude that judges the frame between frame and the AB that B is orderedThreshold value, wherein, judge module is also greater than for the similitude of the frame between frame and the AB of ordering at BWhen one threshold value, judge whether B point is the last frame in video; And judge in memory module B point itFront continuous difference counts whether be greater than Second Threshold;
Split module, in the time that B point is video last frame by between A point and B pointVideo segment splits out, and the video segment between A point and C point is split out;
Memory module, is not more than first for the similitude of the frame between frame and the AB of ordering at described BWhen threshold value, B point is recorded as to peculiar point.
2. the automatic detachment device of video as claimed in claim 1, is characterized in that, described in establishPut module also for first difference point of described continuous difference point is made as to A point.
3. the automatic detachment device of video as claimed in claim 1, is characterized in that, described in establishPut when module is also not more than described Second Threshold for counting in continuous difference, B is ordered more lowerChange and be designated as B point.
4. the automatic detachment device of video as claimed in claim 1, is characterized in that, described in establishPut module and be also designated as B for more lower the changing of in the time that B point is not video last frame, B being orderedPoint.
5. the method that video splits automatically, comprising:
Video starting point is made as to A point;
A point in video is designated as to C point, the more lower B of the being designated as point that C is ordered;
Obtain all frames between A point and B point;
Whether the similitude that judges the frame between frame and the AB that B is ordered is greater than first threshold;
If so, judge whether B point is last frame in video;
If so, the video segment between A point and B point is split out;
If the similitude of the frame between frame and AB that described B is ordered is not more than first threshold, described in inciting somebody to actionB point is recorded as peculiar point;
Whether judge that continuous difference is counted is greater than Second Threshold;
If so, first difference point in difference point continuous before described B point is changed and is made as C point;
Video segment between A point and C point is split out;
First difference point in difference point continuous before described B point is made as to A point.
6. the method that video as claimed in claim 5 splits automatically, is characterized in that, also bagDraw together:
If B point is not the last frame in video, more lower the changing of B being ordered is designated as B point.
7. the method that video as claimed in claim 6 splits automatically, is characterized in that, also bagDraw together:
Be not more than Second Threshold if described continuous difference is counted, more lower the changing of B being ordered is designated asB point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310032021.7A CN103139663B (en) | 2013-01-25 | 2013-01-25 | The automatic detachment device of video and the method automatically splitting thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310032021.7A CN103139663B (en) | 2013-01-25 | 2013-01-25 | The automatic detachment device of video and the method automatically splitting thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103139663A CN103139663A (en) | 2013-06-05 |
| CN103139663B true CN103139663B (en) | 2016-05-11 |
Family
ID=48498870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310032021.7A Active CN103139663B (en) | 2013-01-25 | 2013-01-25 | The automatic detachment device of video and the method automatically splitting thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103139663B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104618662B (en) * | 2013-11-05 | 2019-03-15 | 富泰华工业（深圳）有限公司 | Audio/video player system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101676953A (en) * | 2008-08-22 | 2010-03-24 | 奥多比公司 | Automatic video image segmentation |
| CN102543136A (en) * | 2012-02-17 | 2012-07-04 | 广州盈可视电子科技有限公司 | Method and device for clipping video |
| CN102591892A (en) * | 2011-01-13 | 2012-07-18 | 索尼公司 | Data segmenting device and method |
| CN102833638A (en) * | 2012-07-26 | 2012-12-19 | 北京数视宇通技术有限公司 | Automatic video segmentation and annotation method and system based on caption information |
| CN102890778A (en) * | 2011-07-21 | 2013-01-23 | 北京新岸线网络技术有限公司 | Content-based video detection method and device |
-
2013
- 2013-01-25 CN CN201310032021.7A patent/CN103139663B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101676953A (en) * | 2008-08-22 | 2010-03-24 | 奥多比公司 | Automatic video image segmentation |
| CN102591892A (en) * | 2011-01-13 | 2012-07-18 | 索尼公司 | Data segmenting device and method |
| CN102890778A (en) * | 2011-07-21 | 2013-01-23 | 北京新岸线网络技术有限公司 | Content-based video detection method and device |
| CN102543136A (en) * | 2012-02-17 | 2012-07-04 | 广州盈可视电子科技有限公司 | Method and device for clipping video |
| CN102833638A (en) * | 2012-07-26 | 2012-12-19 | 北京数视宇通技术有限公司 | Automatic video segmentation and annotation method and system based on caption information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103139663A (en) | 2013-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103902044B (en) | Intelligence puts out screen method and mobile terminal | |
| US8358842B2 (en) | Electronic device with function of separating panels of digital comic strip and method thereof | |
| US10999534B2 (en) | Optimized video review using motion recap images | |
| CN104408428B (en) | A kind of processing method and processing device of same scene photo | |
| CN104284252A (en) | Method for generating electronic photo album automatically | |
| CN106202333A (en) | A kind of method of store in a warehouse Video processing and quick-searching | |
| CN103310005A (en) | Thumbnail display method and device | |
| CN105138616A (en) | Method convenient for searching for image | |
| CN104239458A (en) | Method and device for representing search results | |
| CN104063444A (en) | Method and device for generating thumbnail | |
| US11768871B2 (en) | Systems and methods for contextualizing computer vision generated tags using natural language processing | |
| CN104750688A (en) | Photo management method and system | |
| CN103139663B (en) | The automatic detachment device of video and the method automatically splitting thereof | |
| CN112422804A (en) | Video special effect generation method and terminal | |
| CN104965594A (en) | Intelligent face identification cloud sound control method, device and system thereof | |
| CN105824859A (en) | Picture classification method and device as well as intelligent terminal | |
| CN104866627A (en) | Searching system and searching method for photo information | |
| US20190082002A1 (en) | Media file sharing method, media file sharing device, and terminal | |
| CN111480168A (en) | Context-based image selection | |
| CN102970410B (en) | Terminal and display method for contact names | |
| CN106162222A (en) | A kind of method and device of video lens cutting | |
| CN106486117A (en) | A kind of sharing files method and device | |
| CN105787496A (en) | Data collection method and electronic device | |
| CN103207890A (en) | Method and device for acquiring contact person information | |
| US11055321B2 (en) | Rules based albums |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |