CN100545856C - Video content analysis system - Google Patents
Video content analysis system Download PDFInfo
- Publication number
- CN100545856C CN100545856C CNB2006101408348A CN200610140834A CN100545856C CN 100545856 C CN100545856 C CN 100545856C CN B2006101408348 A CNB2006101408348 A CN B2006101408348A CN 200610140834 A CN200610140834 A CN 200610140834A CN 100545856 C CN100545856 C CN 100545856C
- Authority
- CN
- China
- Prior art keywords
- video
- video content
- content analysis
- information
- scene
- 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.)
- Expired - Fee Related
Links
Images
Abstract
A kind of video content analysis system belongs to video analysis and retrieval technique field, is one and analyzes the system that extracts video content information automatically.System framework comprises: input interface, task scheduling modules, video flowing acquisition module, video content analysis module (nucleus module, structure is shown in Figure of abstract), video analysis be auditing module, output interface and user interface as a result.System flow is: system receives the video analysis order of automatic network or this machine, by task scheduling modules decision task executions order, the video that decoding will be analyzed through the video flowing acquisition module, video content analysis module is analyzed shot information, camera lens key frame information, scene information, scene key frame information, key frame images information and the people's face information of extracting from video afterwards, analysis result is examined according to demand, with the storage of XML document form, upload in the video information data base at last by output interface.System is used to support the Content-based Video Retrieval service.
Description
Technical field
The invention belongs to video analysis and retrieval technique field, be specifically related to a video content analysis system.
Background technology
In this age of knowledge explosion, along with being extensive use of of Internet, the continuous expansion of Database Systems storage capacity, the video data that people face is more and more, and video information is used also more and more widely, and the demand of video frequency searching is more and more urgent.
Traditional video frequency search system comprises a video information data base system, and the relevant information of store video, these video informations often only comprise the video metadata information of artificial input, and message form is single, quantity of information is little, is difficult to satisfy user's Search Requirement.
In order to change this situation of video data retrieval, must be with unordered video data ordering, thereby set up the Content-based Video Retrieval instrument, allow the user can retrieve the desired video data at any time, video can automatically be conformed, can interactive operation, retrieval apace, and on the net rapidly, transmit reliably.
For video data, so-called unordered, promptly only stored a succession of linear array time-domain signal---sequence of pictures, but the more structure of deep layer, contents such as the keyword of similar one piece of article, outline or theme are not provided.For structureless digital video frequency flow, must at first carry out Video Segmentation, it is divided into the basic composition unit, therefrom extract the structural information and the high-layer semantic information of video again, promptly must carry out content-based analysis, can realize content-based video data retrieve application video.
At present, also do not have one to overlap complete, automatic video content analysis system on the market, can finish functions such as comprising analysis extraction video lens, scene, camera lens key frame, scene key frame, key frame images information and people's face information.
Summary of the invention
At the situation that does not have at present a cover video content analysis system, the objective of the invention is to design a kind of video content analysis system that comprises reception user video analysis instruction, video decode, video content analysis, video content signal auditing and video content information uploading to a series of flow processs such as video information data base; System can extract rich video content informations such as comprising camera lens, scene, camera lens key frame, scene key frame, key frame images information and people's face information from video; System extracts the rich video content information in full-automatic mode from video, can be Content-based Video Retrieval and provide support.
Described video content analysis system mainly comprises seven parts: input interface, task scheduling modules, video flowing acquisition module, video content analysis module, video content analysis be auditing module, output interface and user interface as a result.System construction drawing as shown in Figure 1.
Input interface is used for receiver, video content analysis order, and system comprises two kinds of order receive modes: from the order of the analysis order of network receiver, video or this machine of acceptance customer analysis video file.
Task scheduling modules is used for the priority according to the video content analysis task, the execution order of scheduling allocating task.
The video flowing acquisition module is used for obtaining video flowing according to a definite decoding rule from external video source.
Video content analysis module, it is the corn module of native system, as shown in Figure 2, be used to carry out video content analysis, comprising six submodules: camera lens is cut apart submodule, camera lens key-frame extraction submodule, scene and is cut apart submodule, scene key-frame extraction submodule, key frame images and analyze submodule and human face analysis submodule.
Camera lens is cut apart submodule, and being used for video is a series of basic unit---camera lens by content segmentation; Camera lens key-frame extraction submodule, be used for camera lens cut apart finish after, from camera lens, extract can the representative shot main contents frame of video; Scene is cut apart submodule, be used for camera lens cut apart with the camera lens key-frame extraction after, with the synthetic video scene that semantic meaning is arranged of lens group; Scene key-frame extraction submodule is used for extracting the representative frame of scene and represents scene; The key frame images analysis module is used for extracting the two field picture bottom-up information from camera lens key frame and scene key frame, comprises texture, color and the edge of image; The human face analysis submodule is used for extracting video high-level semantic information---people's face information from video.
Video content analysis is auditing module as a result, and whether have error, and can carry out the manual amendment to the place that produces error if being used to examine the video content analysis result that video content analysis module produces.
Output interface is used for the video content analysis result is uploaded to video information data base.
User interface mainly comprises two interfaces: video analysis process interface and video analysis result examine the interface.Video analysis process interface is used at video content analysis process display analysis progress, analysis state and analysis result; The video analysis result examines the result that the interface is used to revise video content analysis.
System business process: system receives the video convergence analysis server instruction of automatic network or this machine video content analysis request of importing from user interface by input interface, task scheduling modules is according to the priority decision video analysis task executions order of task, begin to start the video analysis service, the video flowing acquisition module corresponding video of decoding, the video flowing that decodes is sent to video content analysis module, and video content analysis module comprises that to the video flowing that decodes camera lens cuts apart, the camera lens key-frame extraction, scene is cut apart, the scene key-frame extraction, human face analysis, a series of video content analysis processes such as key frame images analysis; Afterwards, under user's audit mode, video content analysis auditing module as a result can be examined the video content analysis result, after audit is passed through, the video content structured message will pass to video information data base with XML by output interface in form, under non-audit mode, the video content structured message that video content analysis module produces will directly upload to video information data base with the XML form.
Should be appreciated that the general description of front of the present invention and detailed description subsequently all are exemplary and indicative, purpose provides the further explanation of desired invention.
Description of drawings
Fig. 1 is an overall system frame diagram of the present invention
Fig. 2 is the structural drawing of video content analysis submodule of the present invention
Fig. 3 is video analysis process of the present invention interface
Fig. 4 is that video analysis result of the present invention examines the interface
Fig. 5 is the form that video content analysis information of the present invention is preserved with the XML file
Embodiment
As shown in Figure 1, the present invention mainly comprises video flowing acquisition module, video content analysis module, video content analysis auditing module, input interface, output interface, task scheduling modules and user interface as a result.
System is by input interface receiver, video analysis order, and receive mode has two kinds: connect from the receiver, video analysis order of video convergence analysis server and the video analysis order of obtaining the user from this locality by network TCP.Wherein video convergence analysis server is the overall dispatch server of video analysis, is used for the distribution of video analysis instruction.The every information that comprises the video file that needs analyze in order comprises the essential information (for the video content analysis interface display) of video analysis task ID (being called PID among the present invention), priority (comprising height, common and low three ranks), task essential information (screen length, screen width, frame per second), file.
Task scheduling modules is deposited mission bit stream with the chain sheet form, the task of priority height, morning time of arrival will join the front of task chained list, on the contrary the back that priority is low, the task in evening time of arrival will be placed on the task chained list.
The video flowing acquisition module obtains the video flowing of various forms from external video source, comprises MPEG1, MPEG2, MPEG4 and H.263 waits.Adopt the demoder of increasing income commonly used at present, decode, with the decoding of whole video stream or the I frame of decoded video only as Xvid, ffmpeg, ffdshow etc.
Video content analysis module is used for carrying out the video content structured analysis through decoded video stream, as shown in Figure 2, and comprising six submodules:
● camera lens is cut apart submodule
Camera lens is the minimal physical unit that video flowing is handled, and in same set of shots, it is stable that the characteristics of image of frame of video keeps.Color is the important low-level image feature of image, and the present invention adopts the cutting algorithm based on color histogram, with H (f, k) the pixel sum of corresponding color k in the expression frame f color histogram.The scope of k is [0, N], and N is the maximal value in the discrete codomain interval of color.Distance between the color histogram adopts histogram to ask the method tolerance of friendship, as follows apart from d (f, f ') computing formula between two width of cloth image f and the f ':
During specific implementation, adopt the mode of moving window, the window default size is 16, obtains the frame of histogram variable in distance maximum in each window, and distance is d
Max, calculating the mean value of histogram variable in distance in the same window simultaneously, distance is d
Avr, it is T that threshold value is set, and works as d
Max/ d
AvrDuring＞T, think that this point is the camera lens cut point, otherwise, think and do not have cut point in the current window.The influence that this method can avoid burr that camera lens is cut apart effectively.
According to the needs of different application and different video, moving window size and threshold value can be adjusted.
● camera lens key-frame extraction submodule
Clustering method is widely used in fields such as artificial intelligence, pattern-recognition and speech recognitions, and the present invention adopts the key-frame extraction algorithm based on cluster.
If certain camera lens S
iComprise n picture frame, can be expressed as S
i={ F
I1..., F
In, F wherein
I1Headed by frame and F
InBe the tail frame.Similarity between adjacent two frames is defined as the similarity of these adjacent two frame color histograms, the density of a threshold value δ control of predefine cluster.
Calculate present frame F
ImAnd the distance between existing certain cluster barycenter, if should be worth greater than δ, then distance is bigger between this frame and this cluster, F
ImDo not add in this cluster.
If F
ImAnd the distance between existing all cluster barycenter is all greater than δ, F
ImForm new cluster, F
ImBarycenter for new cluster; Otherwise this frame is joined in the cluster of spending maximum similarly, make the centroid distance minimum of this frame and this cluster, and this cluster barycenter of following corresponding adjustment:
centrod＝centrod×F
n/(F
n+1)+1/(F
n+1)×F
im
Wherein, centrod ', centrod and F
nBe respectively that the original barycenter of cluster, cluster are upgraded back barycenter and this cluster frame number.
By top method with camera lens S
iThe n that an is comprised picture frame, be referred to different clusters respectively after, just can select key frame.Extract the representative frame from nearest this cluster of conduct of cluster barycenter from each cluster, the representative frame of all clusters has just constituted the key frame of camera lens.
To cluster result, algorithm has added some constraint conditions, stipulates that the totalframes of arbitrary cluster can not be less than 10% of camera lens totalframes, and the cluster similar to barycenter merges.
Threshold value δ can adjust according to the needs of different application different video in the algorithm, to obtain the camera lens key frame of varying number.
● scene is cut apart submodule
Scene is higher level of abstraction notion and the semantic expression that video contains, for feature film, native system adopts the algorithm based on the camera lens cluster, be about to the video lens key frame and carry out cluster by clustering algorithm, video lens continuous in time, that key frame belongs to same cluster is merged into scene, and the scene of finishing feature film is cut apart; For news video, according to the characteristics that news video had---often comprise a complete news footage between two hosts, the present invention adopts the scene partitioning algorithm based on anchor shots, at first call the human face analysis submodule video lens key frame is carried out the detection of people's face, the camera lens that will comprise people's face is decided to be candidate's anchor shots, afterwards, the characteristics that have according to the variance of anchor shots duration (as greater than 5 seconds) and camera lens frame of video color histogram variable in distance (as variance less than 0.025), reject a part of pseudo-anchor shots, call the human face analysis submodule adopts recognition of face to remaining anchor shots method at last, extract correct anchor shots, constitute a scene with the camera lens between two anchor shots that occur continuously, the scene of finishing news video is cut apart.
● scene key-frame extraction submodule
The present invention adopts the scene key-frame extraction algorithm based on camera lens key frame cluster, and all camera lens key frames that belong to scene are carried out cluster, and clustering algorithm and the camera lens key-frame extraction class of algorithms of being said before seemingly extract the scene key frame of representing scene information.
● key frame images is analyzed submodule
The present invention extracts color, texture and three characteristic parameters of shape to key frame images, and the method for expressing of color characteristic has methods such as color histogram, color correlogram, color moment; The method for expressing of textural characteristics has methods such as co-occurrence matrix, Tamura textural characteristics, Gabor feature; The Representation of Form Features method has Fourier descriptors, small echo profile description etc.These methods all are the known technologies of this area.
● the human face analysis submodule
This module can be carried out detection and location of people's face and recognition of face to frame of video, camera lens key frame and scene key frame.People's face detection and location algorithm of the present invention adopts the method based on Adaboost, detailed description about algorithm please refer to document " Rapid Object Detection usinga Boosted Cascade of Simple Features " [Paul Viola and MichaelJones, Computer Vision and Pattern Recognition, Vol.1, pp:511-518,2001].Face identification method adopts Fisher face algorithm, detailed description about algorithm please refer to document " Eigenfaces vs.Fisherfaces:Recognition Using Class Specific Linear Projection " [BelhumeurP.N., Hespanha J.P., Kriegman D.J..IEEE Transactions onPattern Analysis and Machine Intelligence, Vol.19, Issue7, pp:711-720,1997].
Video content analysis is auditing module as a result, is used to examine the video content analysis result and whether has error.When moving, system whether loads this module by user's dynamic-configuration, when the user disposes this module of loading, the video content analysis result that the video content analysis module analysis produces must pass through the video content analysis audit of auditing module as a result, the user can examine the place that error is arranged among the interface modification video content analysis result by the video analysis result, and audit just can be uploaded to video information data base by the rear video analysis result; When user's configuration did not load this module, the video content analysis result can directly be uploaded to video information data base.Wherein, video information data base is used to store the metadata information relevant with video, video content analysis object information, audio-frequency information and video caption information.
Output interface is used for preserving and output video content analysis result.After through video content analysis, video content analysis result audit, the present invention adopts the form of XML file to preserve the video content analysis result, this XML file designation is: PID_text.xml (PID represents the ID of this task), and concrete form such as Fig. 5, it thes contents are as follows:
1) metadata information of the video file of being analyzed (comprising video file name, video file path, video file type, video content structured message entry time etc.);
2) video lens information (comprising camera lens start time, concluding time, camera lens key frame quantity);
3) video lens key frame information (time point, key frame numbering, the key frame figure title that comprise the key frame place);
4) video scene information (comprising scene start time, concluding time, the number of shots that is comprised, scene quantity of key frames);
5) video scene key frame information (time point, key frame numbering, the key frame figure title that comprise the key frame place);
6) key frame images information (colouring information, texture information and the shape information that comprise key frame);
7) people's face information (comprising time point, the people's face numbering of people's face place frame, personage's name of people's face correspondence).
If the current instruction of finishing the work and sending for from Internet video convergence analysis server, after then analysis task finishes, with task termination state information notification video convergence analysis server, and with corresponding video content analysis as a result the XML file be uploaded to video information data base.
If the instruction that current task is sent for this machine user then directly is saved in this machine with the result.
The present invention adopts XML form store video content analysis result information, in the practical application, also can adopt alternate manner.
User interface mainly comprises two interfaces: video analysis process interface and video analysis result examine the interface.Video analysis process interface is used at video content analysis process display analysis progress, analysis state and analysis result, as Fig. 3; The video analysis result examines the interface and is used to make things convenient for the user can pass through the result of interface modification video content analysis, as Fig. 4.
Video analysis process interface as Fig. 3, mainly is divided into five sub-pieces, and video content analysis information LOG hurdle 21 is used for the video analysis process and brings in constant renewal in the camera lens cut-point position of demonstration generation, scene cut-point position, people's face information etc.; Video playback hurdle 22 is used at video analysis process displaying video, and broadcasting speed is identical with the analysis speed of system, and promptly the current broadcast frame of system is identical with system present analysis frame position; Video information hurdle 23 is used to show every information of present analysis video comprise video file name, file layout, file size, video longer duration, video location etc.; System state hurdle 24 is used to show the connection status of current system and video convergence analysis server, the video analysis order that has received, finishes the video file name etc. of video analysis; Key frame of video Information 25 is used to bring in constant renewal in the current key frame of video picture that has analyzed of demonstration.
Results for video audit interface as Fig. 4, mainly is divided into four sub-pieces, and video file hurdle 31 shows the current video file title that needs audit video content analysis result with tabular form; Video analysis object information hurdle 32 shows the video content analysis result of current audit with tabular form; Frame of video Information 33 is used to show the frame of video of the video of examining, and can directly add, deletes and revise the operation of camera lens and scene; Key frame hurdle 34 is used to show the key frame picture of the video of current audit; Video playback hurdle 35 is used to play current audit video, can respond video lens and scene that user command is play appointment; Video information hurdle 36 is used to show the attribute information of present analysis video, comprises video file name, file layout, file size, video longer duration, video location etc.The user examines and revises the video analysis result by results for video audit interface, and the same and XML document form of the result after revising is saved in video information data base or this locality.
Claims (23)
1. video content analysis system, it is characterized in that: this system comprises:
An input interface is used for receiver, video content analysis instruction;
A task scheduling modules is used to dispatch video content analysis task executions order;
A video flowing acquisition module is used for obtaining video flowing according to a definite decoding rule from external video source;
A video content analysis module, be used for the video content structured analysis, comprising six submodules: is that the camera lens of a series of basic camera lenses is cut apart submodule with video by content segmentation, cut apart the camera lens key-frame extraction submodule that from camera lens, extracts frame of video that can the representative shot main contents after finishing at camera lens, camera lens cut apart with the camera lens key-frame extraction after have the scene of the video scene of semantic meaning to cut apart submodule with lens group is synthetic, extract the scene key-frame extraction submodule of frame representative in the scene, from camera lens key frame and scene key frame, extract the key frame images of two field picture bottom-up information and analyze submodule, from video, extract the human face analysis submodule of people's face information;
Video content analysis is auditing module as a result, and whether have error, and can carry out the manual amendment to the place that produces error if being used to examine the result that video content analysis module produces;
An output interface is used for the video content analysis result is uploaded to video information data base;
User interface comprises that a video analysis process interface and a video analysis result examine the interface;
Interface with other related system comprises: with the interface of video convergence analysis server, with the interface of video information data base.
2. video content analysis system as claimed in claim 1, it is characterized in that: input interface, both can receive user's analysis local video order by user interface, also can connect the video analysis order that receives from video convergence analysis server by the TCP/IP network that system has.
3. video content analysis system as claimed in claim 1 is characterized in that: the video flowing acquisition module, wherein, external video source can be video file or video input apparatus.
4. video content analysis system as claimed in claim 1 is characterized in that: the video flowing acquisition module, and support to comprise MPEG1, MPEG2, MPEG4, H.263 wait the decoding of video stream format.
5. video content analysis system as claimed in claim 1 is characterized in that: the video flowing acquisition module has two kinds of forms during decoding: decoding whole video file or the I frame in the decoded video file only.
6. video content analysis system as claimed in claim 1, it is characterized in that: user interface, the status information of video analysis process interface display wherein comprises the information with the connection status of video convergence analysis server, the video analysis order that has received and video content analysis process.
7. video content analysis system as claimed in claim 1, it is characterized in that: user interface, video analysis process interface wherein can be real-time the current frame of video of analyzing of broadcast, show current camera lens key frame that has analyzed and scene key frame images, can also show the cutting time point of current camera lens of cutting apart and scene simultaneously.
8. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis module, six submodules wherein, in the specific implementation, can load required module by user's request, can all load, also can a loading section module, finish the partial function of repertoire or user's appointment.
9. video content analysis system as claimed in claim 1 is characterized in that: video content analysis module, camera lens is wherein cut apart submodule, adopts the camera lens partitioning algorithm based on sliding window and histogram distance.
10. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis module, camera lens key-frame extraction submodule is wherein cut apart the result of submodule according to video lens, frame of video in the camera lens is carried out cluster analysis, the key frame that generation can representative shot information.
11. video content analysis system as claimed in claim 1 is characterized in that: video content analysis module, scene are wherein cut apart the design feature of submodule according to the respective classes video, can finish cutting apart of video scene.
12. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis module, scene is wherein cut apart submodule and must just can be carried out after the function that camera lens is cut apart submodule and camera lens key-frame extraction submodule is finished, and needs to call the human face analysis submodule simultaneously.
13. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis module, scene key-frame extraction submodule is wherein cut apart the result of submodule according to scene, choose the key frame of the camera lens that comprises in the scene, carry out cluster analysis, produce the key frame of representing scene information.
14. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis module, key frame images is wherein analyzed submodule, and the video lens key frame and the video scene key frame images that extract are carried out the information extraction of color, texture and three kinds of features of shape.
15. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis module, human face analysis submodule wherein carries out people's face to frame of video, video lens key frame and video scene key frame and detects and recognition of face, extracts the people's face information that comprises in the video.
16. video content analysis system as claimed in claim 1 is characterized in that: output interface according to the video analysis result that video content analysis module obtains, generates video content structured message XML file.
17. video content analysis system as claimed in claim 1, it is characterized in that: video content analysis is auditing module as a result, this module is optional, dispose decision by the user, need not examine if be configured to, then video content structured analysis result without the audit directly into video information data base, if need to be configured to the audit, then video content structured analysis result need the user examine by after just upload to video information data base.
18. video content analysis system as claimed in claim 9 is characterized in that: camera lens is cut apart submodule, the moving window size and the cutting threshold value of camera lens partitioning algorithm can change, to adapt to the needs of different application, different video.
19. video content analysis system as claimed in claim 10 is characterized in that: camera lens key-frame extraction submodule can change the threshold value of clustering algorithm, to change the camera lens quantity of key frames.
20. video content analysis system as claimed in claim 11, it is characterized in that: scene is cut apart submodule, comprising the scene partitioning algorithm at news video, algorithm comprises the processes such as variance analysis, the detection of camera lens key frame people face and the recognition of face of camera lens key frame of the analysis of camera lens duration, camera lens frame of video histogram variable in distance.
21. video content analysis system as claimed in claim 13 is characterized in that: scene key-frame extraction submodule can change the threshold value of clustering algorithm, to change the scene quantity of key frames.
22. video content analysis system as claimed in claim 16, it is characterized in that: video content structured message XML file comprises the colouring information of video file metadata information, video lens information, video lens key frame information, video scene information, video scene key frame information, key frame images, the texture information of key frame images, shape information and people's face information of key frame images.
23. video content analysis system as claimed in claim 22, it is characterized in that: video content structured message XML file, video file metadata information wherein comprises: video file name, video file path, video file type, video content structured message entry time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101408348A CN100545856C (en) | 2006-10-11 | 2006-10-11 | Video content analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101408348A CN100545856C (en) | 2006-10-11 | 2006-10-11 | Video content analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101021904A CN101021904A (en) | 2007-08-22 |
| CN100545856C true CN100545856C (en) | 2009-09-30 |
Family
ID=38709663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2006101408348A Expired - Fee Related CN100545856C (en) | 2006-10-11 | 2006-10-11 | Video content analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100545856C (en) |
Families Citing this family (45)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5493709B2 (en) | 2009-03-13 | 2014-05-14 | 株式会社リコー | Video editing device |
| CN101599179B (en) * | 2009-07-17 | 2011-06-01 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| CN101833569A (en) * | 2010-04-08 | 2010-09-15 | 中国科学院自动化研究所 | Method for automatically identifying film human face image |
| CN101860663A (en) * | 2010-04-29 | 2010-10-13 | 公安部第三研究所 | Chip for realizing video structuring description treatment and method thereof |
| CN101867729B (en) * | 2010-06-08 | 2011-09-28 | 上海交通大学 | Method for detecting news video formal soliloquy scene based on features of characters |
| CN101901620A (en) * | 2010-07-28 | 2010-12-01 | 复旦大学 | Automatic generation method and edit method of video content index file and application |
| CN102156707A (en) * | 2011-02-01 | 2011-08-17 | 刘中华 | Video abstract forming and searching method and system |
| CN102819528B (en) * | 2011-06-10 | 2016-06-29 | 中国电信股份有限公司 | The method and apparatus generating video frequency abstract |
| CN102945234A (en) * | 2011-08-15 | 2013-02-27 | 联想(北京)有限公司 | Data information inquiry method and electronic device |
| CN102572514A (en) * | 2012-01-11 | 2012-07-11 | 复旦大学 | Service system based on video content epitome |
| CN103313122B (en) * | 2012-03-09 | 2018-02-27 | 联想(北京)有限公司 | A kind of data processing method and electronic equipment |
| CN104050599A (en) * | 2013-03-17 | 2014-09-17 | 北京智慧农业有限公司 | Edible agricultural product quality safety traceability system and method based on video playback |
| CN104216925A (en) * | 2013-06-05 | 2014-12-17 | 中国科学院声学研究所 | Repetition deleting processing method for video content |
| CN103327304B (en) * | 2013-06-13 | 2016-04-20 | 北京林业大学 | A kind of flower growth key-frame extraction system based on Accumulation Mechanism |
| CN103366163B (en) * | 2013-07-15 | 2016-07-20 | 北京丰华联合科技有限公司 | Face detection system and method based on incremental learning |
| KR102131099B1 (en) * | 2014-02-13 | 2020-08-05 | 삼성전자 주식회사 | Dynamically modifying elements of User Interface based on knowledge graph |
| CN105323634B (en) * | 2014-06-27 | 2019-01-04 | Tcl集团股份有限公司 | A kind of reduced graph generating method and system of video |
| CN104270553B (en) * | 2014-09-28 | 2017-12-08 | 北京奇艺世纪科技有限公司 | A kind of switching detection method of video scene and device |
| CN104298748A (en) * | 2014-10-13 | 2015-01-21 | 中南民族大学 | Device and method for face search in videos |
| CN104320670A (en) * | 2014-11-17 | 2015-01-28 | 东方网力科技股份有限公司 | Summary information extracting method and system for network video |
| CN104735468B (en) * | 2015-04-03 | 2018-08-31 | 北京威扬科技有限公司 | A kind of method and system that image is synthesized to new video based on semantic analysis |
| CN106162222B (en) * | 2015-04-22 | 2019-05-24 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
| CN104902279B (en) * | 2015-05-25 | 2018-11-13 | 浙江大学 | A kind of method for processing video frequency and device |
| CN104881880B (en) * | 2015-06-18 | 2017-10-10 | 福建师范大学 | A kind of shot segmentation method based on sequential nature and subspace clustering |
| CN105096228B (en) * | 2015-07-09 | 2019-05-24 | 东方网力科技股份有限公司 | Video image information treating method and apparatus |
| CN105450987A (en) * | 2015-11-12 | 2016-03-30 | 北京弘恒科技有限公司 | Intelligent recognition platform video monitoring early warning system |
| CN107329821B (en) * | 2016-04-29 | 2019-12-31 | 中国电信股份有限公司 | Video data block abstract task scheduling method and device |
| CN106126590A (en) * | 2016-06-20 | 2016-11-16 | 北京航空航天大学 | A kind of unmanned plane based on key message scouts video retrieval method |
| CN106504242A (en) * | 2016-10-25 | 2017-03-15 | Tcl集团股份有限公司 | Object detection method and system |
| US11328159B2 (en) * | 2016-11-28 | 2022-05-10 | Microsoft Technology Licensing, Llc | Automatically detecting contents expressing emotions from a video and enriching an image index |
| CN106778653A (en) * | 2016-12-27 | 2017-05-31 | 北京光年无限科技有限公司 | Towards the exchange method and device based on recognition of face Sample Storehouse of intelligent robot |
| CN106686441A (en) * | 2016-12-30 | 2017-05-17 | 中广热点云科技有限公司 | Video interaction method |
| CN110169055B (en) * | 2017-01-20 | 2021-06-15 | 华为技术有限公司 | Method and device for generating lens information |
| CN107995518B (en) * | 2017-12-22 | 2021-02-26 | 海信视像科技股份有限公司 | Image display method, apparatus and computer storage medium |
| CN110035098A (en) * | 2018-01-12 | 2019-07-19 | 上海杰轩智能科技有限公司 | The method for realizing recognition of face terminal data transmission by XML format |
| CN108416013B (en) * | 2018-03-02 | 2020-12-18 | 北京奇艺世纪科技有限公司 | Video matching, retrieving, classifying and recommending methods and devices and electronic equipment |
| CN108600254A (en) * | 2018-05-07 | 2018-09-28 | 龚麟 | A kind of audio and video identifying system |
| CN109063667B (en) * | 2018-08-14 | 2021-02-19 | 视云融聚（广州）科技有限公司 | Scene-based video identification mode optimization and pushing method |
| CN109472197A (en) * | 2018-09-28 | 2019-03-15 | 中国科学院自动化研究所 | A kind of video human face labeling method |
| CN109525892B (en) * | 2018-12-03 | 2021-09-10 | 易视腾科技股份有限公司 | Video key scene extraction method and device |
| CN110852289A (en) * | 2019-11-16 | 2020-02-28 | 公安部交通管理科学研究所 | Method for extracting information of vehicle and driver based on mobile video |
| CN111414517B (en) * | 2020-03-26 | 2023-05-19 | 成都市喜爱科技有限公司 | Video face analysis method, device and server |
| CN113542725B (en) * | 2020-04-22 | 2023-09-05 | 百度在线网络技术（北京）有限公司 | Video auditing method, video auditing device and electronic equipment |
| CN111988561B (en) * | 2020-07-13 | 2022-05-03 | 浙江大华技术股份有限公司 | Adaptive adjustment method and device for video analysis, computer equipment and medium |
| CN112651336B (en) * | 2020-12-25 | 2023-09-29 | 深圳万兴软件有限公司 | Method, apparatus and computer readable storage medium for determining key frame |
-
2006
- 2006-10-11 CN CNB2006101408348A patent/CN100545856C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN101021904A (en) | 2007-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100545856C (en) | Video content analysis system | |
| CN111866585B (en) | Video processing method and device | |
| WO2021232978A1 (en) | Video processing method and apparatus, electronic device and computer readable medium | |
| CN112163122B (en) | Method, device, computing equipment and storage medium for determining label of target video | |
| US10410679B2 (en) | Producing video bits for space time video summary | |
| US20080162561A1 (en) | Method and apparatus for semantic super-resolution of audio-visual data | |
| CN109117777A (en) | The method and apparatus for generating information | |
| WO2022184117A1 (en) | Deep learning-based video clipping method, related device, and storage medium | |
| US20140093174A1 (en) | Systems and methods for image management | |
| CN109871464B (en) | Video recommendation method and device based on UCL semantic indexing | |
| CN111368141B (en) | Video tag expansion method, device, computer equipment and storage medium | |
| CN101369281A (en) | Retrieval method based on video abstract metadata | |
| CN102236714A (en) | Extensible markup language (XML)-based interactive application multimedia information retrieval method | |
| CN100365622C (en) | Method for segmenting a compressed video | |
| CN111708913A (en) | Label generation method and device and computer readable storage medium | |
| Smeaton et al. | TRECVID 2003-an overview | |
| CN113627402A (en) | Image identification method and related device | |
| Otani et al. | Video summarization using textual descriptions for authoring video blogs | |
| CN114390368A (en) | Live video data processing method and device, equipment and readable medium | |
| CN107369450A (en) | Recording method and collection device | |
| Tseng et al. | Hierarchical video summarization based on context clustering | |
| Minu et al. | Scrutinizing the video and video retrieval concept | |
| CN115379301A (en) | Video processing method and related equipment | |
| CN115442540A (en) | Music video generation method and device, computer equipment and storage medium | |
| CN114782879A (en) | Video identification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: BEIJING NUFRONT NETWORK TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: BAO DONGSHAN Effective date: 20080201 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20080201 Address after: A, building 16, building 1, building 8, Qinghua science park, No. 100084, Zhongguancun East Road, Beijing, Haidian District, China Applicant after: Beijing Nufront Software Technology Co., Ltd. Address before: A, building 16, building 1, building 8, Qinghua science park, No. 100084, Zhongguancun East Road, Beijing, Haidian District, China Applicant before: Bao Dongshan |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090930 Termination date: 20131011 |