CN102156707A - Video abstract forming and searching method and system - Google Patents
Video abstract forming and searching method and system Download PDFInfo
- Publication number
- CN102156707A CN102156707A CN2011100344015A CN201110034401A CN102156707A CN 102156707 A CN102156707 A CN 102156707A CN 2011100344015 A CN2011100344015 A CN 2011100344015A CN 201110034401 A CN201110034401 A CN 201110034401A CN 102156707 A CN102156707 A CN 102156707A
- Authority
- CN
- China
- Prior art keywords
- video
- moving target
- frequency abstract
- video frequency
- forms
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a video abstract forming and searching method and system. The method comprises the following steps: A, separating a motion target and a background from an original video; B, re-organizing the extracted motion target, and overlapping the motion target to the back of the background to form a video abstract; and C, establishing a searching index of the motion target according to characteristic parameters of the target, and directly searching the corresponding motion target according to the characteristic parameters.
Description
Technical field
The present invention relates to method, system that a kind of video frequency abstract forms and searches for.
Background technology
Video has brought very big challenge for people's fast browsing and retrieval as a kind of non-structured data.The video data of magnanimity is especially all arranged at internet video industry and dedicated video monitoring trade, and people will browse and search specific incident in video will be very time-consuming thing.The technology that presses for the A and I structure of similar books front is applied in the structuring processing of video.Therefore video frequency abstract formation and search technique occur for addressing this problem.
Video summarization technique mainly contains two kinds of patterns at present: video is slightly look at and the video outline.It mainly is to extract key frame on the basis that camera lens is cut apart that video is slightly look at, and is organized into video frequency abstract with the key frame of camera lens.The video outline mainly is the continuity and the consistance that concentrate and guarantee the video plot that realizes video.
Present existing patent mainly concentrate on video slightly look at and the video outline technical, do not retrieve identical with this patent or similar patent documentation as yet.。
Summary of the invention
The method, the system that the object of the present invention is to provide a kind of video frequency abstract to form and search for, behind video analysis technology separating background and moving target, reorganize time and order that a plurality of moving targets show simultaneously in background video, set up the search of video frequency abstract fragment and moving target.
Video frequency abstract that this patent proposed forms and the technology of search has significantly different with existing video frequency abstract pattern: 1) this patent is the foreground target that obtains behind the algorithm process analysis video frame data by video analysis in the video.2) reorganize time and the sequencing that target shows in video, can be according to the time requirement that generates the video frequency abstract fragment, allow a plurality of targets do not block with overlapping basis on synchronization be simultaneously displayed in the video pictures.3) set up search according to the characteristic parameter of moving target.
In addition, this patent does not relate to the semantic analysis of video content, video frequency abstract has reorganized the time that occurs and the order of moving target in the video in video, lack the high-rise technical Analysis of understanding to videos such as semantic analysis between the moving target in the video and plot analysis.
A kind of video frequency abstract provided by the invention forms and method, the system of search are achieved in that
The method that a kind of video frequency abstract forms and searches for, the method comprising the steps of:
A) separating background and moving target from original video;
B) form video frequency abstract on the time of reorganization moving target appearance and the order and the background that is added to;
C) set up search according to the characteristic parameter of moving target.
Also further comprise in the step b) and judge whether moving target blocks and moving target time of occurrence method in proper order.
Also further be included in the moving target system of selection that synchronization occurs simultaneously in the frame of video in the step b).
Also further be included in the synthetic method of background that moving target and context update Maintenance Model produce in the step b).
The system that a kind of video frequency abstract forms and searches for, this system comprises:
A) original video acquisition module;
B) moving target and background separation extraction module;
C) moving target time of occurrence and order computation module;
D) avoid moving target to block and select module with moving target
E) moving target and video background synthetic video summarization module.
By technique scheme as can be known, the present invention has following characteristics and advantage:
1, owing to be the video frequency abstract of on the basis of video content analysis, setting up, compares the video frequency abstract that key frame is formed, can reduce the data volume of video frequency abstract file greatly, and guarantee that former objects in video can both occur in video frequency abstract.
2, owing to reorganized time and order that moving target occurs in video, can occur simultaneously, allow the user can browse to a plurality of not blocking and overlapping target simultaneously at a plurality of moving targets of synchronization.Concentrate the density of target on background greatly and lowered video data redundance spatially.Thereby greatly reduce the user and browse time with retrieve video.
Description of drawings
Fig. 1 is the process flow diagram of the method embodiment 1 of a kind of video frequency abstract formation of the present invention and search;
Fig. 2 is the video frequency abstract formation of a kind of enforcement of the present invention and the process flow diagram of search system;
Fig. 3 is the process flow diagram of a kind of moving target of the present invention and background separation extraction module;
Fig. 4 is the process flow diagram of a kind of moving target time of occurrence of the present invention and order computation module;
Fig. 5 blocks the process flow diagram of selecting module with moving target for a kind of moving target of the present invention;
Fig. 6 is the process flow diagram of a kind of moving target of the present invention and video background synthetic video summarization module;
Fig. 7 is the video frequency abstract formation of a kind of enforcement of the present invention and the treatment facility structured flowchart of search system.
Embodiment
The central idea of the method that a kind of video frequency abstract of the present invention forms and searches for is: by analysis and the processing to video content, objects in video is carried out reorganization on time and the space, allow target as much as possible in video, show simultaneously and remain on relativeness and invariant position in the original video.Can reduce the data redudancy in the video greatly,, reduce the time of user's browsing video significantly and for providing technique guarantee according to the characteristic parameter searched targets in the video frequency abstract file and the search that guarantee to form under the situation that moving target is not lost compression.
In order to make those skilled in the art person understand the present invention program better, the present invention is described in further detail below in conjunction with drawings and embodiments.
The present invention is method, the system that a kind of video frequency abstract forms and searches for, treat that the original video that will carry out the video frequency abstract processing can be, but be not limited to, conventional multimedia video frequency file, TV programme, film and have the network multimedia file etc. of sound and video also can be the video file that the video file gathered from the video monitoring system of special use and network video monitor and control system are gathered.
Embodiment 1 accompanying drawing is a kind of implementation method process flow diagram that original video files is carried out video frequency abstract formation and search.As a kind of embodiment of the present invention, original video source can be conventional video multimedia file, also can be the video file of collection of special-purpose video monitoring system and the video file that network monitoring system is gathered.
Step S101: separating background and moving target from original video.
The method of separating background and moving target can be separated moving target from the background of complicated and variation, to upgrade and safeguard the background model of dynamic self-adapting simultaneously, this model algorithm can adapt to light gradual change at sunshine, and small random motion object disturbs and boisterous interference.
Step S102: reorganize the moving target and the background that is added to and form video frequency abstract.
On the basis of separating background and moving target, moving target is reorganized time and the order that occurs in video, and guarantee not block with overlapping between the moving target.Relativeness between the moving target can not cause confusion.This step comprises moving target time of occurrence and order computation method; Avoid moving target to block and the moving target system of selection; Moving target and video background synthetic video method of abstracting.
Step S103: foreground target is set up search according to the clarification of objective parameter.Can carry out the classification of target according to the moving target that extracts: 1, people's feature: recognition of face feature, the feature of kinematic parameter feature 2, car: car plate recognition feature, color, volume, the feature of travel speed 3, thing: color, volume and the speed of travel.Set up the index database of moving target by characteristic parameter.
The characteristic parameter module that also further comprises the target image that extraction will be searched among the step S103 according to the index database of the characteristic parameter searching moving target of obtaining, judges whether the moving target of coupling.
The system that a kind of video frequency abstract that the present invention also provides simultaneously forms and searches for, this system can carry out Treatment Analysis after the third party system obtains original video, behind separating background and the moving target, form video frequency abstract on the background that is added to after the time of reorganization moving target and the order.
The video frequency abstract that shown in the accompanying drawing 2 is a kind of enforcement of the present invention forms and the search system example.In embodiment of the present invention, comprise original video acquisition module S201, the original video that carries out video frequency abstract formation and search can be the video data that special-purpose video monitoring system is gathered, or the video data of network video monitor and control system collection, also can be local multimedia video frequency file.In concrete embodiment of the present invention, original video provides system to be positioned at different positions geographically with the system of this example, for example different countries, the third party system can be connected with the system of this example by communication network, communication network does not have concrete restriction, can be wired, wireless, the internet, LAN (Local Area Network) and Metropolitan Area Network (MAN) etc.
Another kind of instantiation of the present invention, the system that implementation system of the present invention can provide original video with the third party is in same network or in the same equipment, and such as network hard disk video recorder, or the network storage equipment is medium.In this case, implementation system of the present invention and provide that communication mode can be an internal data bus between the system of original video, data communication interface or similarly communicate to connect mode.
In the concrete implementation system of the present invention, comprise moving target and background separation extraction module S202; The original video that this module will be handled carries out moving target to be separated with background, a plurality of moving targets and background extracting in the video can be come out.This module can be extracted the clarification of objective parameter after being separated to moving target.The detailed description of concrete this module is asked for an interview accompanying drawing 3.
In the concrete implementation system of the present invention, also comprise moving target time of occurrence and order computation module S203; This module is mainly analyzed the relative time relation between the moving target.Guarantee that the moving target time that occurs is consistent with order with original video in video frequency abstract.The main judgement time consistency of moving target in video frequency abstract and the duration of moving target.The detailed description of concrete this module is asked for an interview accompanying drawing 4.
In the concrete implementation system of the present invention, comprise that also avoiding moving target to block with moving target selects module S204.This module mainly is the position of judging between moving target, avoids blocking mutually with overlapping, can select those moving targets can appear in the present frame in the video frequency abstract in view of the above.The detailed description of concrete this module is asked for an interview accompanying drawing Fig. 5.
In the concrete implementation system of the present invention, further comprise moving target and video background synthetic video summarization module s205.This module mainly is finish moving target and video background synthetic.Moving target according to a last module is selected will form the video frequency abstract file on its background that is added to.The detailed description of concrete this module is asked for an interview accompanying drawing 6.
In the concrete implementation system of the present invention, further comprise moving target characteristic parameter search module S206.This module mainly is to extract the clarification of objective parameter to be checked of user's input, and with the video frequency abstract process in the inquiry of comparing of the moving target characteristic parameter index database set up.Judge whether the target of coupling.The target to be checked of user's input can be image or one section video, or directly import the clarification of objective parameter, in concrete implementation system, can obtain its characteristic parameter, and compare retrieval by the moving target parameter in its parameter and the video frequency abstract index database by the technology of Flame Image Process.
The original video acquisition module, moving target and background separation extraction module, moving target time of occurrence and order computation module, avoiding moving target to block with moving target selects module to reside in one or more calculating treatmenting equipments, these calculating treatmenting equipments include but not limited to, computing machine, server or similar calculating treatmenting equipment.Instantiation is described and is asked for an interview accompanying drawing 7.
Concrete embodiment of the present invention is shown in Figure of abstract.The original video of input comprises the video of a doggie and a bird.Separating background and object module S101 be the background frames data of analyzing and processing video at first, obtain moving target and background.S102 reorganizes the module of moving target and background synthetic video summary with the moving target doggie and bird and the background stack formation video frequency abstract that obtain.The S103 search module can be according to parameter retrieval and inquisition moving target in video of moving target.
Business model of the present invention can realize in several ways, include but not limited to, a kind of pattern is that video summarization system offers the user as separate equipment or service, and the video frequency abstract that this equipment or service can be finished the input video source forms and search work.Another kind of pattern is that video summarization system can be used as program residence in user's calculating treatmenting equipment, carries out the task that video frequency abstract forms and searches for.
Accompanying drawing 3 is moving target and background separation extraction module, in concrete embodiment of the present invention, this module will adopt the program computing method of mixed Gauss model to judge that a certain pixel is background or moving target according to the Changing Pattern of background pixel and moving target pixel.In different embodiments of the present invention, can adopt different programmed algorithms to judge that a certain pixel in the frame of video is background or target, include but not limited to, the algorithm of average background subtraction, the algorithm of particle filter, the algorithm of mean shift, the algorithm of frame difference, different algorithms is selected in different use occasions according to the present invention, mainly is to consider computation complexity and computing time.
In concrete embodiment of the present invention, moving target and background separation module also will comprise the maintenance and the update module of background, comprising: adapt to the unexpected variation of background light, and the moving target in the background, the target that stops and walking about, the random vibration of camera is disturbed.
In a concrete embodiment of the present invention, moving target and background separation module also comprise the characteristic parameter extraction module of moving target.This module is set up the search of moving target characteristic parameter.Characteristic parameter that can be dissimilar in the concrete embodiment according to setting up of dissimilar moving targets, such as, face characteristic, vehicle license plate characteristic etc.
Accompanying drawing 4 is moving target time of occurrence and order computation module, in a concrete embodiment of the present invention, this module is mainly analyzed the relative time relation between the moving target, judges the time consistency of moving target in video frequency abstract and the duration of moving target.Guarantee that the moving target time that occurs is consistent with order with original video in video frequency abstract.
In the concrete embodiment of the present invention, moving target time of occurrence and order computation module also comprise the sequencing queue administration module of moving target, and the formation of moving target is set up and safeguarded to this module after the relative time relation of determining between the moving target.This module also comprises the insertion of responsible moving target and the algorithm routine of deletion.
Accompanying drawing 5 is to avoid moving target sheltering analysis and moving target to select module.This module mainly is the position relation of judging between moving target, avoids blocking mutually with overlapping, can select those moving targets to appear in the present frame in the video frequency abstract in view of the above.
In the concrete embodiment of the present invention, avoid moving target to block with moving target and select module also to comprise moving target selection module, this module mainly is to decide according to the energy function minimum of calculating moving target to select those moving targets to appear in the current video frequency abstract.The computational item of definition energy function comprises the time consistency cost function of moving target, the cost function that target occurs and the cost function of target occlusion.
Accompanying drawing 6 is moving target and video background synthetic video summarization module.This module mainly is finish moving target and video background synthetic.Moving target according to a last module is selected will form the video frequency abstract file on its background that is added to.
In the concrete embodiment of the present invention, moving target and video background synthetic video summarization module also comprise background frames selection module, and this module will guarantee that the background frames that chooses changes, and also represents the background of moving target simultaneously.
In the concrete embodiment of the present invention, moving target and video background synthetic video summarization module also comprise background frames and goal congruence analysis module.Since do not accomplish the cutting apart of moving target and background absolute accurately, the background frames that this module principal security chooses is consistent with the peripheral color of moving target.
Accompanying drawing 7 is a kind of video frequency abstract formation of enforcement and the treatment facility structured flowchart of search system.Comprise that video acquisition device 101 and original video import module 102, calculation processing apparatus 200.Calculation processing apparatus 200 further includes, but not limited to CPU (central processing unit) (CPU), treatment facility support circuit plate and memory device etc.Memory device comprises dynamically or static RAM, electromagnetism or semi-conductive storer etc., resident executable module comprises original video acquisition module S201 in the memory device, moving target and background separation module s202, moving target time of occurrence and order computation module s203, avoid moving target sheltering analysis and moving target to select module s204, moving target and video background synthetic video summarization module s205, moving target characteristic parameter search module S206.The operating system in the memory device and the algorithm routine of a kind of concrete embodiment of the present invention combine and operate in the calculation processing apparatus 200.
More than disclosed only be preferred implementation of the present invention; but the present invention is not limited thereto; any those skilled in the art can think do not have a creationary variation, and, all should drop in protection scope of the present invention not breaking away from some improvements and modifications of being done under the principle of the invention prerequisite.
Claims (21)
1. a video frequency abstract forms and the method for search, it is characterized in that the method comprising the steps of:
A. separating background and moving target from original video;
B. reorganize the time of moving target appearance and form video frequency abstract in proper order and on the background that is added to;
C. set up search according to the characteristic parameter of moving target.
2. the method that video frequency abstract as claimed in claim 1 forms and searches for, it is characterized in that original video packets is drawn together the video file of conventional multimedia video frequency file, the collection of special-purpose supervisory system and/or the video file that network video monitor and control system is gathered in the step a).
3. the method that video frequency abstract as claimed in claim 2 forms and searches for is characterized in that the multimedia video file of described routine comprises TV programme, film, has the network multimedia file of sound and video.
4. the method that video frequency abstract as claimed in claim 1 forms and searches for is characterized in that, separating background and moving target need be set up the background model of automatic renewal and the characteristic parameter of extraction moving target from original video.
5. the method that video frequency abstract as claimed in claim 1 forms and searches for, it is characterized in that, according to detected operational objective, a plurality of moving targets are organized according to the time of position in the visual field and appearance again, and formed video frequency abstract in the background that is added to.
6. the method that video frequency abstract as claimed in claim 1 forms and searches for is characterized in that, behind separating background and the moving target, sets up target search according to the characteristic parameter of moving target.
7. the method that video frequency abstract as claimed in claim 4 forms and searches for is characterized in that, sets up the context update model of dynamic self-adapting, needs model algorithm can adapt to light gradual change at sunshine, and small random motion object disturbs and boisterous interference.
8. the method that video frequency abstract as claimed in claim 5 forms and searches for, it is characterized in that, after separate targets and background, difference priority object appearing constantly reorganizes in the same background, allows different object appearing constantly show with synchronization under same background.
9. the method that video frequency abstract as claimed in claim 6 forms and searches for is characterized in that the method that described characteristic parameter according to moving target is set up target search is:
A) set up the classification of target: 1, people's feature: recognition of face parameter, the feature of motion feature 2, car: car plate identification parameter, color, volume, the feature of travel speed 3, thing: color, volume and gait of march
B) set up the index database of moving target;
C) the target image characteristic parameter extraction that will search for according to the index database of the characteristic parameter searching moving target of obtaining, judges whether the target of coupling.
10. the method that video frequency abstract as claimed in claim 9 forms and searches for, it is characterized in that, step c) further comprises the clarification of objective parameter module that will inquire about that extracts user's input, and what the user imported can be video or image file, perhaps directly imports the clarification of objective parameter.
11. video frequency abstract as claimed in claim 7 forms and the method for search, it is characterized in that, sets up dynamic self-adapting context update model, and sets up the adaptability of the maintenance program assurance background of dynamic background.
12. video frequency abstract as claimed in claim 4 forms and the method for search, it is characterized in that, sets up the moving target extraction that just can realize behind the context update model of dynamic self-adapting and the maintenance program in the video data.
13. video frequency abstract as claimed in claim 8 forms and the method for search, it is characterized in that the process of setting up video frequency abstract comprises:
A). extract background video;
B). calculate the order and the duration of moving target time of occurrence;
C). select moving target in video frequency abstract, whether to occur and time of occurrence;
D). with moving target and the final video frequency abstract of the synthetic formation of background video.
14. the system that video frequency abstract forms and searches for is characterized in that, comprising:
A) original video acquisition module is used for from other inside or external system is obtained the original video data of pending analysis, the video conversion of different-format can be become the video data of consolidation form;
B) moving target and background separation extraction module are used for from original video separating background and moving target;
C) moving target time of occurrence and order computation module are used for the computational analysis moving target in video frequency abstract time of occurrence and order;
D) avoid moving target to block and moving target is selected module, be used for blocking between the computational analysis moving target and concern with overlapping position of waiting needs analysis and select which target can appear at video frequency abstract;
E) moving target and video background synthetic video summarization module are used for moving target of selecting and video background synthetic video summary.
15. video frequency abstract as claimed in claim 14 forms and search system, it is characterized in that, also comprises moving target characteristic parameter search module, can be according to the target in the target image retrieve video of input.
16. video frequency abstract as claimed in claim 14 forms and search system, it is characterized in that, original video in the step a) further comprises conventional multimedia video frequency file, TV programme, film and the network multimedia file that has sound and video, and the video file of the video file of special-purpose supervisory system collection and network video monitor and control system collection.
17. video frequency abstract as claimed in claim 16 forms and search system, it is characterized in that the multimedia video file of described routine comprises TV programme, film and the network multimedia file that has sound and video.
18. video frequency abstract as claimed in claim 14 forms and search system, it is characterized in that, further comprises in the step b): the context update maintenance module of dynamic self-adapting and moving target extraction module.
19. video frequency abstract as claimed in claim 12 forms and search system, it is characterized in that, further comprises in the step c): time sequencing module that moving target occurs in summarized radio and duration computing module.
20. video frequency abstract as claimed in claim 14 forms and search system, it is characterized in that, further comprises in the step d): do not have the moving target of selecting when blocking in the present video frequency abstract at moving target and select module.
21. one kind comprises, and the described video frequency abstract of one of claim 14-19 forms and the equipment of search system, it is characterized in that this equipment also comprises: video acquisition device and original video import module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100344015A CN102156707A (en) | 2011-02-01 | 2011-02-01 | Video abstract forming and searching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100344015A CN102156707A (en) | 2011-02-01 | 2011-02-01 | Video abstract forming and searching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102156707A true CN102156707A (en) | 2011-08-17 |
Family
ID=44438206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100344015A Pending CN102156707A (en) | 2011-02-01 | 2011-02-01 | Video abstract forming and searching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102156707A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102572407A (en) * | 2012-03-07 | 2012-07-11 | 深圳市信义科技有限公司 | Searching and analyzing method on base of standardization of video information |
| CN102799637A (en) * | 2012-06-27 | 2012-11-28 | 北京邮电大学 | Method for automatically generating main character abstract in television program |
| CN102930061A (en) * | 2012-11-28 | 2013-02-13 | 安徽水天信息科技有限公司 | Video abstraction method and system based on moving target detection |
| CN102984601A (en) * | 2012-12-11 | 2013-03-20 | 常州环视高科电子科技有限公司 | Generation system for video abstract of camera |
| CN103020260A (en) * | 2012-12-24 | 2013-04-03 | 中国科学院半导体研究所 | Video query method |
| CN103020275A (en) * | 2012-12-28 | 2013-04-03 | 苏州千视通信科技有限公司 | Video analysis method based on video abstraction and video retrieval |
| CN103092930A (en) * | 2012-12-30 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Method of generation of video abstract and device of generation of video abstract |
| CN103106910A (en) * | 2011-11-11 | 2013-05-15 | 詹宝珠 | Abstract image and manufacturing method thereof |
| CN103150319A (en) * | 2012-11-16 | 2013-06-12 | 佳都新太科技股份有限公司 | CS (Client Server) framework-based feature retrieval rear video abstraction retrieval system |
| CN103150375A (en) * | 2013-03-11 | 2013-06-12 | 浙江捷尚视觉科技有限公司 | Quick video retrieval system and quick video retrieval method for video detection |
| CN103366163A (en) * | 2013-07-15 | 2013-10-23 | 北京丰华联合科技有限公司 | Human face detection system and method based on incremental learning |
| CN103605652A (en) * | 2013-08-30 | 2014-02-26 | 北京桓润世嘉科技有限公司 | Video retrieval and browsing method and device based on object zone bits |
| CN103686095A (en) * | 2014-01-02 | 2014-03-26 | 中安消技术有限公司 | Video concentration method and system |
| CN103778159A (en) * | 2012-10-26 | 2014-05-07 | 苏州千视通信科技有限公司 | Video detection process based on video abstraction and video retrieval |
| CN103838750A (en) * | 2012-11-23 | 2014-06-04 | 苏州千视通信科技有限公司 | Video investigation technique for obtaining vehicle features based on video retrieval abstract |
| CN104159158A (en) * | 2013-05-15 | 2014-11-19 | 中兴通讯股份有限公司 | Hotspot playing method and device of video file |
| CN104239309A (en) * | 2013-06-08 | 2014-12-24 | 华为技术有限公司 | Video analysis retrieval service side, system and method |
| CN104284158A (en) * | 2014-10-23 | 2015-01-14 | 南京信必达智能技术有限公司 | Event-oriented intelligent camera monitoring method |
| CN104469547A (en) * | 2014-12-10 | 2015-03-25 | 西安理工大学 | Video abstraction generation method based on arborescence moving target trajectory |
| CN104504397A (en) * | 2014-12-31 | 2015-04-08 | 云智视像科技（上海）有限公司 | Monitoring video abstraction method and system based on face identification |
| CN104581437A (en) * | 2014-12-26 | 2015-04-29 | 中通服公众信息产业股份有限公司 | Video abstract generation and video backtracking method and system |
| CN104639994A (en) * | 2013-11-08 | 2015-05-20 | 杭州海康威视数字技术股份有限公司 | Video abstraction generating method, system and network storage equipment based on moving objects |
| CN104636413A (en) * | 2013-11-07 | 2015-05-20 | 三星泰科威株式会社 | Video search system and method |
| CN104717573A (en) * | 2015-03-05 | 2015-06-17 | 广州市维安电子技术有限公司 | Video abstract generation method |
| WO2015169165A1 (en) * | 2014-05-06 | 2015-11-12 | The Hong Kong University Of Science And Technology | Method and system for creating replate videos |
| CN105205171A (en) * | 2015-10-14 | 2015-12-30 | 杭州中威电子股份有限公司 | Image retrieval method based on color feature |
| CN105224535A (en) * | 2014-05-29 | 2016-01-06 | 浙江航天长峰科技发展有限公司 | Based on the concern target quick reference system of massive video |
| CN105554456A (en) * | 2015-12-21 | 2016-05-04 | 北京旷视科技有限公司 | Video processing method and apparatus |
| WO2016090652A1 (en) * | 2014-12-12 | 2016-06-16 | 深圳Tcl新技术有限公司 | Video compression method and device |
| CN105872452A (en) * | 2015-02-10 | 2016-08-17 | 韩华泰科株式会社 | System and method for browsing summary image |
| WO2017049577A1 (en) * | 2015-09-25 | 2017-03-30 | Qualcomm Incorporated | Systems and methods for video processing |
| CN107944017A (en) * | 2017-12-11 | 2018-04-20 | 浙江捷尚视觉科技股份有限公司 | The search method of non-motor vehicle in a kind of video |
| CN109871815A (en) * | 2019-02-26 | 2019-06-11 | 新华三技术有限公司 | A kind of method and device of query monitor information |
| CN111107376A (en) * | 2019-12-09 | 2020-05-05 | 国网辽宁省电力有限公司营口供电公司 | Video enhancement concentration method suitable for security protection of power system |
| CN111160068A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Target picture generation method and device and electronic equipment |
| CN113873200A (en) * | 2021-09-26 | 2021-12-31 | 珠海研果科技有限公司 | Image identification method and system |
| CN116233569A (en) * | 2023-05-06 | 2023-06-06 | 石家庄铁道大学 | Video abstract generation method based on motion information assistance |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100312331B1 (en) * | 1998-02-14 | 2001-12-28 | 이계철 | System and method for searching image based on contents |
| CN101021904A (en) * | 2006-10-11 | 2007-08-22 | 鲍东山 | Video content analysis system |
| CN101262568A (en) * | 2008-04-21 | 2008-09-10 | 中国科学院计算技术研究所 | A method and system for generating video outline |
| CN101631237A (en) * | 2009-08-05 | 2010-01-20 | 青岛海信网络科技股份有限公司 | Video monitoring data storing and managing system |
| CN101778260A (en) * | 2009-12-29 | 2010-07-14 | 公安部第三研究所 | Method and system for monitoring and managing videos on basis of structured description |
-
2011
- 2011-02-01 CN CN2011100344015A patent/CN102156707A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100312331B1 (en) * | 1998-02-14 | 2001-12-28 | 이계철 | System and method for searching image based on contents |
| CN101021904A (en) * | 2006-10-11 | 2007-08-22 | 鲍东山 | Video content analysis system |
| CN101262568A (en) * | 2008-04-21 | 2008-09-10 | 中国科学院计算技术研究所 | A method and system for generating video outline |
| CN101631237A (en) * | 2009-08-05 | 2010-01-20 | 青岛海信网络科技股份有限公司 | Video monitoring data storing and managing system |
| CN101778260A (en) * | 2009-12-29 | 2010-07-14 | 公安部第三研究所 | Method and system for monitoring and managing videos on basis of structured description |
Cited By (57)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106910A (en) * | 2011-11-11 | 2013-05-15 | 詹宝珠 | Abstract image and manufacturing method thereof |
| CN102572407B (en) * | 2012-03-07 | 2014-05-28 | 深圳市信义科技有限公司 | Searching and analyzing method on base of standardization of video information |
| CN102572407A (en) * | 2012-03-07 | 2012-07-11 | 深圳市信义科技有限公司 | Searching and analyzing method on base of standardization of video information |
| CN102799637A (en) * | 2012-06-27 | 2012-11-28 | 北京邮电大学 | Method for automatically generating main character abstract in television program |
| CN103778159A (en) * | 2012-10-26 | 2014-05-07 | 苏州千视通信科技有限公司 | Video detection process based on video abstraction and video retrieval |
| CN103150319A (en) * | 2012-11-16 | 2013-06-12 | 佳都新太科技股份有限公司 | CS (Client Server) framework-based feature retrieval rear video abstraction retrieval system |
| CN103150319B (en) * | 2012-11-16 | 2016-06-29 | 佳都新太科技股份有限公司 | The rearmounted video frequency abstract searching system of a kind of characteristic key based on CS framework |
| CN103838750A (en) * | 2012-11-23 | 2014-06-04 | 苏州千视通信科技有限公司 | Video investigation technique for obtaining vehicle features based on video retrieval abstract |
| CN102930061A (en) * | 2012-11-28 | 2013-02-13 | 安徽水天信息科技有限公司 | Video abstraction method and system based on moving target detection |
| CN102984601B (en) * | 2012-12-11 | 2016-08-03 | 常州展华机器人有限公司 | Camera video summarization generation system |
| CN102984601A (en) * | 2012-12-11 | 2013-03-20 | 常州环视高科电子科技有限公司 | Generation system for video abstract of camera |
| CN103020260A (en) * | 2012-12-24 | 2013-04-03 | 中国科学院半导体研究所 | Video query method |
| CN103020275A (en) * | 2012-12-28 | 2013-04-03 | 苏州千视通信科技有限公司 | Video analysis method based on video abstraction and video retrieval |
| CN103092930A (en) * | 2012-12-30 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Method of generation of video abstract and device of generation of video abstract |
| CN103092930B (en) * | 2012-12-30 | 2017-02-08 | 贺江涛 | Method of generation of video abstract and device of generation of video abstract |
| CN103150375A (en) * | 2013-03-11 | 2013-06-12 | 浙江捷尚视觉科技有限公司 | Quick video retrieval system and quick video retrieval method for video detection |
| CN104159158A (en) * | 2013-05-15 | 2014-11-19 | 中兴通讯股份有限公司 | Hotspot playing method and device of video file |
| CN104239309A (en) * | 2013-06-08 | 2014-12-24 | 华为技术有限公司 | Video analysis retrieval service side, system and method |
| CN103366163A (en) * | 2013-07-15 | 2013-10-23 | 北京丰华联合科技有限公司 | Human face detection system and method based on incremental learning |
| 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 |
| CN103605652B (en) * | 2013-08-30 | 2017-11-07 | 北京桓润世嘉科技有限公司 | Video frequency searching and the method and apparatus browsed based on object flag position |
| CN103605652A (en) * | 2013-08-30 | 2014-02-26 | 北京桓润世嘉科技有限公司 | Video retrieval and browsing method and device based on object zone bits |
| CN104636413B (en) * | 2013-11-07 | 2019-04-19 | 韩华泰科株式会社 | Video searching system and method |
| CN104636413A (en) * | 2013-11-07 | 2015-05-20 | 三星泰科威株式会社 | Video search system and method |
| CN104639994B (en) * | 2013-11-08 | 2018-10-09 | 杭州海康威视数字技术股份有限公司 | Method, system and the network storage equipment of video frequency abstract are generated based on moving target |
| CN104639994A (en) * | 2013-11-08 | 2015-05-20 | 杭州海康威视数字技术股份有限公司 | Video abstraction generating method, system and network storage equipment based on moving objects |
| CN103686095A (en) * | 2014-01-02 | 2014-03-26 | 中安消技术有限公司 | Video concentration method and system |
| CN103686095B (en) * | 2014-01-02 | 2017-05-17 | 中安消技术有限公司 | Video concentration method and system |
| WO2015169165A1 (en) * | 2014-05-06 | 2015-11-12 | The Hong Kong University Of Science And Technology | Method and system for creating replate videos |
| CN105224535A (en) * | 2014-05-29 | 2016-01-06 | 浙江航天长峰科技发展有限公司 | Based on the concern target quick reference system of massive video |
| CN104284158A (en) * | 2014-10-23 | 2015-01-14 | 南京信必达智能技术有限公司 | Event-oriented intelligent camera monitoring method |
| CN104469547B (en) * | 2014-12-10 | 2017-06-06 | 西安理工大学 | A kind of video abstraction generating method based on tree-shaped movement objective orbit |
| CN104469547A (en) * | 2014-12-10 | 2015-03-25 | 西安理工大学 | Video abstraction generation method based on arborescence moving target trajectory |
| WO2016090652A1 (en) * | 2014-12-12 | 2016-06-16 | 深圳Tcl新技术有限公司 | Video compression method and device |
| CN104581437B (en) * | 2014-12-26 | 2018-11-06 | 中通服公众信息产业股份有限公司 | A kind of video frequency abstract generates and the method and system of video backtracking |
| CN104581437A (en) * | 2014-12-26 | 2015-04-29 | 中通服公众信息产业股份有限公司 | Video abstract generation and video backtracking method and system |
| CN104504397A (en) * | 2014-12-31 | 2015-04-08 | 云智视像科技（上海）有限公司 | Monitoring video abstraction method and system based on face identification |
| CN105872452A (en) * | 2015-02-10 | 2016-08-17 | 韩华泰科株式会社 | System and method for browsing summary image |
| CN105872452B (en) * | 2015-02-10 | 2020-05-15 | 韩华泰科株式会社 | System and method for browsing abstract images |
| CN104717573B (en) * | 2015-03-05 | 2018-04-13 | 广州市维安电子技术有限公司 | A kind of generation method of video frequency abstract |
| CN104717573A (en) * | 2015-03-05 | 2015-06-17 | 广州市维安电子技术有限公司 | Video abstract generation method |
| WO2017049577A1 (en) * | 2015-09-25 | 2017-03-30 | Qualcomm Incorporated | Systems and methods for video processing |
| CN108028969A (en) * | 2015-09-25 | 2018-05-11 | 高通股份有限公司 | system and method for video processing |
| US10708673B2 (en) | 2015-09-25 | 2020-07-07 | Qualcomm Incorporated | Systems and methods for video processing |
| CN105205171A (en) * | 2015-10-14 | 2015-12-30 | 杭州中威电子股份有限公司 | Image retrieval method based on color feature |
| CN105205171B (en) * | 2015-10-14 | 2018-09-21 | 杭州中威电子股份有限公司 | Image search method based on color characteristic |
| CN105554456A (en) * | 2015-12-21 | 2016-05-04 | 北京旷视科技有限公司 | Video processing method and apparatus |
| CN107944017A (en) * | 2017-12-11 | 2018-04-20 | 浙江捷尚视觉科技股份有限公司 | The search method of non-motor vehicle in a kind of video |
| CN107944017B (en) * | 2017-12-11 | 2021-06-25 | 浙江捷尚视觉科技股份有限公司 | Method for searching non-motor vehicle in video |
| CN111160068A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Target picture generation method and device and electronic equipment |
| CN111160068B (en) * | 2018-11-07 | 2024-01-26 | 杭州海康威视数字技术股份有限公司 | Target picture generation method and device and electronic equipment |
| CN109871815A (en) * | 2019-02-26 | 2019-06-11 | 新华三技术有限公司 | A kind of method and device of query monitor information |
| CN109871815B (en) * | 2019-02-26 | 2021-07-20 | 新华三技术有限公司 | Method and device for inquiring monitoring information |
| CN111107376A (en) * | 2019-12-09 | 2020-05-05 | 国网辽宁省电力有限公司营口供电公司 | Video enhancement concentration method suitable for security protection of power system |
| CN113873200A (en) * | 2021-09-26 | 2021-12-31 | 珠海研果科技有限公司 | Image identification method and system |
| CN113873200B (en) * | 2021-09-26 | 2024-02-02 | 珠海研果科技有限公司 | Image identification method and system |
| CN116233569A (en) * | 2023-05-06 | 2023-06-06 | 石家庄铁道大学 | Video abstract generation method based on motion information assistance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102156707A (en) | Video abstract forming and searching method and system | |
| CN110235138A (en) | System and method for appearance search | |
| CN101778260B (en) | Method and system for monitoring and managing videos on basis of structured description | |
| JP4553650B2 (en) | Image group representation method, descriptor derived by representation method, search method, apparatus, computer program, and storage medium | |
| US10867376B2 (en) | Analysis apparatus, analysis method, and storage medium | |
| CN110263613A (en) | Monitor video processing method and processing device | |
| US20120170803A1 (en) | Searching recorded video | |
| CN106295489B (en) | Information processing method, information processing device and video monitoring system | |
| EP2659672A2 (en) | Searching recorded video | |
| CN116188821B (en) | Copyright detection method, system, electronic device and storage medium | |
| CN102231820A (en) | Monitoring image processing method, device and system | |
| CN115002414A (en) | Monitoring method, monitoring device, server and computer readable storage medium | |
| CN110543584B (en) | Method, device, processing server and storage medium for establishing face index | |
| KR20110035662A (en) | Intelligent image search method and system using surveillance camera | |
| CN111522974A (en) | Real-time filing method and device | |
| RU2710308C1 (en) | System and method for processing video data from archive | |
| CN102254396B (en) | Intrusion detection method and device based on video | |
| CN105554595A (en) | Video abstract intelligent extraction and analysis system | |
| CN102244769A (en) | Object and key person monitoring system and method thereof | |
| KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
| KR101509593B1 (en) | Image classification method and apparatus for preset tour camera | |
| WO2023165219A1 (en) | Target retrieval method and device, and storage medium | |
| KR101891992B1 (en) | Server, method, wearable device for supporting maintenance of military apparatus based reasoning, classification and decision of case on augmented reality | |
| CN102244770A (en) | Object monitoring system and method | |
| Cavallaro | Adding Privacy Constraints to Video-Based Applications. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110817 |