CN103106250A - Intelligent analysis and retrieval method for video surveillance and system thereof - Google Patents
Intelligent analysis and retrieval method for video surveillance and system thereof Download PDFInfo
- Publication number
- CN103106250A CN103106250A CN201310012753XA CN201310012753A CN103106250A CN 103106250 A CN103106250 A CN 103106250A CN 201310012753X A CN201310012753X A CN 201310012753XA CN 201310012753 A CN201310012753 A CN 201310012753A CN 103106250 A CN103106250 A CN 103106250A
- Authority
- CN
- China
- Prior art keywords
- video
- module
- moving target
- sport
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention belongs to the field of security technologies and relates to an intelligent analysis and retrieval method for video surveillance and a system thereof. The intelligent analysis and retrieval method for video surveillance and the system thereof resolve the technical problems that an existing technology design is not reasonable enough and the like. The intelligent analysis and retrieval method for video surveillance comprises the following steps: (1) video enhancement and (2) video retrieval, wherein the step of the video retrieval comprises dynamic analysis, coding recombination, result marking and behavior analysis. A dynamic analysis module is connected with a coding recombination module. A result marking module and a behavior analysis module are both connected with the coding recombination module. A video enhancement module is connected with the dynamic analysis module or the coding recombination module. The intelligent analysis and retrieval method for video surveillance and the system thereof have the advantages of combining image enhancement, retrieval compression, intelligent analysis and abstract statistics into one, embodying five characteristics of being advanced, high-efficiency, reliable, convenient and practical in use, achieving the enhancement of video images, the retrieval and compression of video documents, the intelligent analysis of behaviors of people and automobiles, and the like, thus obtaining the needed information rapidly and accurately and being capable of providing strong and effective criminal investigation supports for public security officers to scout and solve a case.
Description
Technical field
The invention belongs to technical field of security and protection, relate to video monitoring, especially relate to a kind of video monitoring intellectual analysis search method and system thereof.
Background technology
Further develop along with socioeconomic, China wants quality, wants police strength, wants fighting capacity to become the theme of current public security department to science and technology for a large amount of man power and material of criminal investigation aspect input.Along with going deep into of safe city system and society's monitoring Large scale construction, solved the problem that the urban pavement video gathers and preserves reliably, accumulated the first-hand on-site supervision image document of a large amount of preciousnesses, for providing strong support in investigation, utilizing monitor video to search clue to solve the case has become means the most frequently used in criminal investigation and case detection, has hit dramatically the criminal offence of illegal one's share of expenses for a joint undertaking.Yet present stage, also there were problems in the safe city supervisory system:
1, in the face of rugged surroundings, supervisory system night dark low light cross bright situation hypograph quality according to, dense fog sand and dust inclement weather or local light and greatly reduce, cause the poor camera acquisition of video image quality to poor image quality, upper giant-screen is of poor quality, Video Document is of poor quality, the policeman in charge of the case can't therefrom obtain useful information, cause the clear up a criminal case difficulty, inefficiency.
2, video monitoring ubiquity camera position is unreasonable present stage, the shortcomings such as effective information is few, often need to spend a large amount of manpowers, time and check the magnanimity Video Document in case evidence obtaining and analytic process, seriously restricted its detection efficient, also there is the inevitably artificial erroneous judgement etc. of failing to judge in the retrieval evidence obtaining work of Traditional Man, and needs solution badly therefore public security video in the actual combat that utilizes the monitoring video investigation is examined the problem of inefficiency.
3, present stage is in most cases to dispatch the associated monitoring data by criminal investigation group to the application personnel of relevant department after the incident, carrying out artificial semi-automatic search judges again, reason due to site environment, the image of taking is unsatisfactory, can't see details clearly, be not easy to public security department or vehicle supervision department and monitor processing, in the situation that the low public security police of video quality is substantially at a loss what to do, in the face of the examination one by one that the video monitoring data of magnanimity also can only waste time and energy, the criminal investigation people's police feel this to be sorely distressed.
4, watch for a long time the low video of quality may increase the weight of the burden of people's eyes, easily produce visual fatigue, even can have a dizzy spell, the contrast of scene image and color all can be changed or degenerate under rugged surroundings, the many features that contain in image all are capped or are fuzzy, and what obtain is degraded image.
For this reason, people have carried out long-term exploration, have proposed various solutions.For example, Chinese patent literature discloses a kind of video automatic concentration method [application number: 201110208090.X] based on video surveillance network, it is to obtain the first video source and the second video source and to moving Object Segmentation and tracking, extract background image and video surveillance network movement locus from two video cameras with overlapping region; Generate panoramic picture based on video surveillance network according to background image, obtain two video cameras separately corresponding to the projection matrix of panoramic picture and the real-time update panoramic picture based on the video surveillance network background; Utilize the projection matrix of two video camera panoramic pictures, track is projected to the panoramic picture space obtain projected footprint; Adopt the figure coupling, based on the projected footprint coupling of random walk thought to the video source of two video cameras, obtain matching track pair, the matching track of overlapping region is selected and merged, obtain complete large scene track; The large scene track was rearranged by the time, on panoramic picture, complete large scene track is represented, obtain based on the video of panoramic picture concentrated." computer engineering and application " the 25th phase in 2008 discloses the video retrieval method (author: Xue Liqin that a kind of based on motion is analyzed; Zhang Xiujuan), introduce people from different application purposes, proposed the method for motion analysis in many different videos.Sum up, these analytical approachs can be divided into four classes: light stream estimation algorithm, motion vector estimation algorithm, based on histogrammic statistical analysis technique, parameterized global motion analytic approach.
Although such scheme has improved video analysis efficient to a certain extent, be difficult to obtain easily needed information in video but still exist, be only the length that has shortened whole video, and any processing is not made in association between the effect of video, details, video etc.
Summary of the invention
The objective of the invention is for the problems referred to above, provide a kind of and significantly video time is shortened, can obtain easily needed information in video, the video monitoring intellectual analysis search method of increasing work efficiency.
Another object of the present invention is to provide a kind ofly can obtain needed information in video, the video monitoring intellectual analysis searching system of increasing work efficiency easily.
For achieving the above object, the present invention has adopted following technical proposal: this video monitoring intellectual analysis search method, it is characterized in that, and this method comprises the steps:
A, video strengthen: by video enhancement techniques with camera collection to video image in the image that exists dark, fuzzy, any one or multiple situation that cross in bright eliminate, obtain the high-quality video file of video enhancing;
B, video frequency searching:
A, performance analysis: the video retrieval technology that utilizes based on motion to analyze, the static segment in the monitoring video video is skipped or F.F. automatically, moving target is provided prompting, and obtain the sport video fragment of intercepting frame by frame;
B, coding restructuring: the sport video fragment that will intercept is frame by frame carried out the video restructuring, the restructuring sport video for selective analysis after obtaining to recombinate;
C, result queue: play simultaneously original image and restructuring sport video picture, and the restructuring sport video that will play distinguishes mark according to different moving targets on the reproduction time axle;
D, behavioural analysis: the moving situation to different motion target in the restructuring sport video is analyzed, if the movement velocity of moving target surpasses the speed threshold values that this moving target is set, sends alerting signal.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned step c, set the time period separator that the personage moves that only has of having play and show the first color, the time period separator that vehicle movement is only arranged of having play shows the second color, has the time period separator of personage and vehicle movement to show the 3rd color when playing.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned steps d, set the speed that the personage normally walks about and be not more than 2m/s, if meet or exceed 2m/s for running, and personage's signal that gives the alarm when running; The speed of setting normal vehicle operation is not more than 22m/s, is overspeed of vehicle if meet or exceed 22m/s, and the signal that gives the alarm during overspeed of vehicle.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned step B, also comprise:
E, video frequency abstract: the same moving target that different time is occurred carries out respectively the sectional drawing backup, form the summary picture, and show the concrete time on the summary picture, elected in during a certain summary picture, automatically play coherent front some seconds and rear some seconds in the video segment of this summary picture place.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned step B, also comprise:
F, trace labelling: the moving target in selected restructuring sport video, and this moving target is made a mark, and when selected moving target continues motion, described mark accompany movement object synchronization motion.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned step B, also comprise:
G, GIS interlock: utilize geography information and binding time extract relevant sport video fragment and automatically to each camera collection to relevant sport video fragment recombinate according to time and space, form moving target and move continuous videos fragment constantly.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned step B, also comprise:
H, play up compensation: after a certain two field picture was filed, then the image at the same visual angle of the same camera of analog capture again under the good visual condition carried out the later rendering compensation according to the image that captures to the image that files, and contrast is provided.
In above-mentioned video monitoring intellectual analysis search method, in above-mentioned steps A, described video strengthen comprise that front-end collection strengthens, screen shows strengthens and video segment in strengthening any one or multiple; Described front-end collection strengthens the front-end collection that passes through to connect for the video enhancing and strengthens the module realization between camera and memory storage; Described screen shows strengthens the broadcast of passing through to connect for the video enhancing and strengthens the module realization between memory storage and display screen; Described video segment strengthens by video image selected in memory storage is saved to memory storage after the video enhancing workstation that is used for the video enhancing is processed standby.
Above-mentioned video monitoring intellectual analysis search method is implemented in following video monitoring intellectual analysis searching system, and native system comprises:
Video strengthens module, be used for by video enhancement techniques with camera collection to the image that exists of video image dark, fuzzy, any one or multiple situation that cross in bright eliminate, obtain the high-quality video file of video enhancing;
The performance analysis module for the video retrieval technology that utilizes based on motion to analyze, is skipped the static segment in the monitoring video video or F.F. automatically, and moving target is provided prompting, and obtains the sport video fragment of intercepting frame by frame;
Coding recombination module, the sport video fragment that is used for intercepting frame by frame carry out the video restructuring, the restructuring sport video for selective analysis after obtaining to recombinate;
The result queue module be used for playing simultaneously original image and restructuring sport video picture, and the restructuring sport video that will play distinguishes mark according to different moving targets on the reproduction time axle;
The behavioural analysis module is used for the moving situation of restructuring sport video different motion target is analyzed, if the movement velocity of moving target surpasses the speed threshold values that this moving target is set, sends alerting signal;
Described performance analysis module is connected with the coding recombination module, and described result queue module and behavioural analysis module all are connected on the coding recombination module, and described video strengthens module and is connected with performance analysis module or coding recombination module.
In above-mentioned video monitoring intellectual analysis searching system, native system also comprises:
The video frequency abstract module, be used for the same moving target that different time occurs is carried out respectively the sectional drawing backup, form the summary picture, and show the concrete time on the summary picture, in elected during a certain summary picture, automatically play coherent front some seconds and rear some seconds in the video segment of this summary picture place;
The trace labelling module is used for the moving target of selected restructuring sport video, and this moving target is made a mark, and when selected moving target continues motion, described mark accompany movement object synchronization motion;
The GIS interlocking module, be used for utilizing geography information and binding time extract relevant sport video fragment and automatically to each camera collection to relevant sport video fragment recombinate according to time and space, form moving target and move continuous videos fragment constantly;
Play up compensating module, after being used for a certain two field picture is filed, then the image at the same visual angle of the same camera of analog capture again under the good visual condition carries out the later rendering compensation according to the image that captures to the image that files, and contrast is provided;
Described video frequency abstract module, trace labelling module, GIS interlocking module and play up compensating module respectively with the coding recombination module be connected.
Compared with prior art, this video monitoring intellectual analysis search method and advantage of system thereof are: skip or the F.F. video in static segment, video time is significantly shortened, can obtain easily needed information in video, significantly save time, increase work efficiency, and can retrieve and mark required information easily, set up contact in video between discontinuous information, easy operating is implemented.Integrating figure image intensifying, retrieval compression, intellectual analysis, summary adds up, advanced, efficient, reliable, convenient and five practical large characteristics have been embodied, the enhancing to video image, the retrieval compression of video file, the behavior intellectual analysis of personage's vehicle etc. have been realized, thereby obtain quickly and accurately required information, can provide powerful effective criminal investigation to support for public security cadres and police scout to solve a case.
Description of drawings
Fig. 1 is structural representation provided by the invention.
Fig. 2 is that front end video provided by the invention strengthens structural representation.
Fig. 3 is that displaying video provided by the invention strengthens structural representation.
Fig. 4 is that the video of video worktable provided by the invention strengthens structural representation.
In figure, camera 1, memory storage 2, front-end collection strengthen module 3, display screen 4, broadcast enhancing module 5, video enhancing workstation 6, video enhancing module 7, performance analysis module 8, coding recombination module 9, result queue module 10, behavioural analysis module 11, video frequency abstract module 12, trace labelling module 13, GIS interlocking module 14, play up compensating module 15.
Embodiment
This video monitoring intellectual analysis search method comprises the steps:
A, video strengthen: by video enhancement techniques with camera collection to video image in the image that exists dark, fuzzy, any one or multiple situation that cross in bright eliminate, obtain the high-quality video file of video enhancing;
B, video frequency searching:
A, performance analysis: the video retrieval technology that utilizes based on motion to analyze, the static segment in the monitoring video video is skipped or F.F. automatically, moving target is provided prompting, and obtain the sport video fragment of intercepting frame by frame;
B, coding restructuring: the sport video fragment that will intercept is frame by frame carried out the video restructuring, the restructuring sport video for selective analysis after obtaining to recombinate;
C, result queue: play simultaneously original image and restructuring sport video picture, and the restructuring sport video that will play distinguishes mark according to different moving targets on the reproduction time axle;
D, behavioural analysis: the moving situation to different motion target in the restructuring sport video is analyzed, if the movement velocity of moving target surpasses the speed threshold values that this moving target is set, sends alerting signal.
In the present invention, as shown in Fig. 2,3 and 4, video strengthen comprise that front-end collection strengthens, screen shows strengthens and video segment in strengthening any one or multiple.Front-end collection strengthens the front-end collection that passes through to connect for the video enhancing and strengthens module 3 realizations between camera 1 and memory storage 2; Screen shows strengthens the broadcast of passing through to connect for the video enhancing and strengthens module 5 realizations between memory storage 2 and display screen 4; Video segment strengthens by video image selected in memory storage 2 is saved to memory storage 2 after the video enhancing workstation 6 that is used for the video enhancing is processed standby.
The safe city video monitoring system that present stage has built, the front-end collection environment division is comparatively backward, can't well capture the real scene under various rugged surroundings, night dark low light cross bright situation hypograph quality according to, dense fog sand and dust inclement weather or local light and greatly reduce, can't therefrom obtain useful information, and watch for a long time the low video of quality may increase the weight of the burden of people's eyes, easily produce visual fatigue, even can have a dizzy spell.The contrast of scene image and color all can be changed or degenerate under rugged surroundings, and the many features that contain in image all are capped or are fuzzy, and what obtain is degraded image.For this reason, the application of image enhancement technique seem particularly in the urgent need to, can scout to wait for handling a case provide effective reconnaissane tool, greatly increases work efficiency.As shown in Figure 2, it is FPGA plate (supporting BNC HDMI interface) that front-end collection strengthens module 3, thereby obtains high-quality video file when making the rear end storage.Play enhancing module 5 and be the FPAG plate on the final node that is attached to transmission of video, the key video sequence image can be rendered on giant-screen and analyze for inquiring into.Video strengthens workstation 6 and is used for the key video sequence image of the memory storages 2 such as web camera, DVR, video server is strengthened analysis, rediscover scene and personage.Wherein, video enhancing workstation 6 is existing equipment in prior art.Wherein, the algorithm of above-mentioned various video enhancings comprises: image is dark to be strengthened; The image mist elimination strengthens; The zone picture strengthens; Wide dynamic process; Vedio noise reduction; Video stabilization; Image removes motion blur; The regional area super-resolution strengthens.Above-mentioned algorithm all can adopt existing algorithm in prior art, and this paper does not give unnecessary details.
In above-mentioned step c, set the time period separator that the personage moves that only has of having play and show the first color, the time period separator that vehicle movement is only arranged of having play shows the second color, has the time period separator of personage and vehicle movement to show the 3rd color when playing.For example the blue time period represents the personage, and the red time period represents vehicle etc., and personage and vehicle time of occurrence section simultaneously are green, and the other times section is shown as black.In above-mentioned steps d, set the speed that the personage normally walks about and be not more than 2m/s, if meet or exceed 2m/s for running, and personage's signal that gives the alarm when running; The speed of setting normal vehicle operation is not more than 22m/s, is overspeed of vehicle if meet or exceed 22m/s, and the signal that gives the alarm during overspeed of vehicle.Retrieval analysis for vehicle can be sorted out summary to features such as vehicle color, vehicle volume, the number-plate numbers (under high-resolution), same car is occurred 2 times within the time of association and above emphasis ejection warning.The condition of retrieval can custom parameter (sensitivity), comprise movement velocity, article size, color, number etc., different parameters is the different configuration file of output automatically, can be used as the retrieval prediction scheme and preserves, and convenient case to same type compares.
In above-mentioned step B, also comprise:
E, video frequency abstract: the same moving target that different time is occurred carries out respectively the sectional drawing backup, form the summary picture, and show the concrete time on the summary picture, elected in during a certain summary picture, automatically play coherent front some seconds and rear some seconds in the video segment of this summary picture place.In the present embodiment, automatically play in the video segment of this summary picture place coherent front ten seconds and rear ten seconds.
In above-mentioned step B, also comprise:
F, trace labelling: the moving target in selected restructuring sport video, and this moving target is made a mark, and when selected moving target continues motion, described mark accompany movement object synchronization motion.
In above-mentioned step B, also comprise:
G, GIS interlock: utilize geography information and binding time extract relevant sport video fragment and automatically to each camera collection to relevant sport video fragment recombinate according to time and space, form moving target and move continuous videos fragment constantly.
In above-mentioned step B, also comprise:
H, play up compensation: after a certain two field picture was filed, then the image at the same visual angle of the same camera of analog capture again under the good visual condition carried out the later rendering compensation according to the image that captures to the image that files, and contrast is provided.
As shown in Fig. 1-4, this video monitoring intellectual analysis searching system comprises:
Video strengthens module 7, be used for by video enhancement techniques with camera collection to the image that exists of video image dark, fuzzy, any one or multiple situation that cross in bright eliminate, obtain the high-quality video file of video enhancing;
Native system also comprises:
Video frequency abstract module 12, be used for the same moving target that different time occurs is carried out respectively the sectional drawing backup, form the summary picture, and show the concrete time on the summary picture, in elected during a certain summary picture, automatically play coherent front some seconds and rear some seconds in the video segment of this summary picture place;
Play up compensating module 15, after being used for a certain two field picture is filed, then the image at the same visual angle of the same camera of analog capture again under the good visual condition carries out the later rendering compensation according to the image that captures to the image that files, and contrast is provided;
Video frequency abstract module 12, trace labelling module 13, GIS interlocking module 14 and play up compensating module 15 respectively with the coding recombination module 9 be connected.
Specific embodiment described herein is only to the explanation for example of the present invention's spirit.Those skilled in the art can make various modifications or replenish or adopt similar mode to substitute described specific embodiment, but can't depart from spirit of the present invention or surmount the defined scope of appended claims.
Although this paper has more used camera 1, memory storage 2, front-end collection to strengthen module 3, display screen 4, play and strengthen module 5, video and strengthen workstation 6, video and strengthen module 7, performance analysis module 8, coding recombination module 9, result queue module 10, behavioural analysis module 11, video frequency abstract module 12, trace labelling module 13, GIS interlocking module 14, play up the term such as compensating module 15, do not get rid of the possibility of using other term.Using these terms is only in order to describe more easily and explain essence of the present invention; They are construed to any additional restriction is all contrary with spirit of the present invention.
Claims (10)
1. a video monitoring intellectual analysis search method, is characterized in that, this method comprises the steps:
A, video strengthen: by video enhancement techniques with camera collection to video image in the image that exists dark, fuzzy, any one or multiple situation that cross in bright eliminate, obtain the high-quality video file of video enhancing;
B, video frequency searching:
A, performance analysis: the video retrieval technology that utilizes based on motion to analyze, the static segment in the monitoring video video is skipped or F.F. automatically, moving target is provided prompting, and obtain the sport video fragment of intercepting frame by frame;
B, coding restructuring: the sport video fragment that will intercept is frame by frame carried out the video restructuring, the restructuring sport video for selective analysis after obtaining to recombinate;
C, result queue: play simultaneously original image and restructuring sport video picture, and the restructuring sport video that will play distinguishes mark according to different moving targets on the reproduction time axle;
D, behavioural analysis: the moving situation to different motion target in the restructuring sport video is analyzed, if the movement velocity of moving target surpasses the speed threshold values that this moving target is set, sends alerting signal.
2. video monitoring intellectual analysis search method according to claim 1, it is characterized in that, in above-mentioned step c, set the time period separator that the personage moves that only has of having play and show the first color, the time period separator that vehicle movement is only arranged of having play shows the second color, has the time period separator of personage and vehicle movement to show the 3rd color when playing.
3. video monitoring intellectual analysis search method according to claim 1, is characterized in that, in above-mentioned steps d, set the speed that the personage normally walks about and be not more than 2m/s, if meet or exceed 2m/s for running, and personage's signal that gives the alarm when running; The speed of setting normal vehicle operation is not more than 22m/s, is overspeed of vehicle if meet or exceed 22m/s, and the signal that gives the alarm during overspeed of vehicle.
4. video monitoring intellectual analysis search method according to claim 1, is characterized in that, in above-mentioned step B, also comprises:
E, video frequency abstract: the same moving target that different time is occurred carries out respectively the sectional drawing backup, form the summary picture, and show the concrete time on the summary picture, elected in during a certain summary picture, automatically play coherent front some seconds and rear some seconds in the video segment of this summary picture place.
5. video monitoring intellectual analysis search method according to claim 1, is characterized in that, in above-mentioned step B, also comprises:
F, trace labelling: the moving target in selected restructuring sport video, and this moving target is made a mark, and when selected moving target continues motion, described mark accompany movement object synchronization motion.
6. video monitoring intellectual analysis search method according to claim 1, is characterized in that, in above-mentioned step B, also comprises:
G, GIS interlock: utilize geography information and binding time extract relevant sport video fragment and automatically to each camera collection to relevant sport video fragment recombinate according to time and space, form moving target and move continuous videos fragment constantly.
7. video monitoring intellectual analysis search method according to claim 1, is characterized in that, in above-mentioned step B, also comprises:
H, play up compensation: after a certain two field picture was filed, then the image at the same visual angle of the same camera of analog capture again under the good visual condition carried out the later rendering compensation according to the image that captures to the image that files, and contrast is provided.
8. the described video monitoring intellectual analysis of any one search method according to claim 1-7, it is characterized in that, in above-mentioned steps A, described video strengthen comprise that front-end collection strengthens, screen shows strengthens and video segment in strengthening any one or multiple; Described front-end collection strengthens the front-end collection that passes through to connect for the video enhancing and strengthens module (3) realization between camera (1) and memory storage (2); Described screen shows strengthens the broadcast of passing through to connect for the video enhancing and strengthens module (5) realization between memory storage (2) and display screen (4); Described video segment strengthens by video image selected in memory storage (2) is saved to memory storage (2) after the video enhancing workstation (6) that is used for the video enhancing is processed standby.
9. a video monitoring intellectual analysis searching system, is characterized in that, native system comprises:
Video strengthens module (7), be used for by video enhancement techniques with camera collection to the image that exists of video image dark, fuzzy, any one or multiple situation that cross in bright eliminate, obtain the high-quality video file of video enhancing;
Performance analysis module (8) for the video retrieval technology that utilizes based on motion to analyze, is skipped the static segment in the monitoring video video or F.F. automatically, and moving target is provided prompting, and obtains the sport video fragment of intercepting frame by frame;
Coding recombination module (9), the sport video fragment that is used for intercepting frame by frame carry out the video restructuring, the restructuring sport video for selective analysis after obtaining to recombinate;
Result queue module (10) be used for playing simultaneously original image and restructuring sport video picture, and the restructuring sport video that will play distinguishes mark according to different moving targets on the reproduction time axle;
Behavioural analysis module (11) is used for the moving situation of restructuring sport video different motion target is analyzed, if the movement velocity of moving target surpasses the speed threshold values that this moving target is set, sends alerting signal;
Described performance analysis module (8) is connected with coding recombination module (9), described result queue module (10) and behavioural analysis module (11) all are connected on coding recombination module (9), and described video strengthens module (7) and is connected with performance analysis module (8) or coding recombination module (9).
10. video monitoring intellectual analysis searching system according to claim 9, is characterized in that, native system also comprises:
Video frequency abstract module (12), be used for the same moving target that different time occurs is carried out respectively the sectional drawing backup, form the summary picture, and show the concrete time on the summary picture, in elected during a certain summary picture, automatically play coherent front some seconds and rear some seconds in the video segment of this summary picture place;
Trace labelling module (13) is used for the moving target of selected restructuring sport video, and this moving target is made a mark, and when selected moving target continues motion, described mark accompany movement object synchronization motion;
GIS interlocking module (14), be used for utilizing geography information and binding time extract relevant sport video fragment and automatically to each camera collection to relevant sport video fragment recombinate according to time and space, form moving target and move continuous videos fragment constantly;
Play up compensating module (15), after being used for a certain two field picture is filed, then the image at the same visual angle of the same camera of analog capture again under the good visual condition carries out the later rendering compensation according to the image that captures to the image that files, and contrast is provided;
Described video frequency abstract module (12), trace labelling module (13), GIS interlocking module (14) and play up compensating module (15) respectively with the coding recombination module (9) be connected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310012753.XA CN103106250B (en) | 2013-01-14 | 2013-01-14 | Video monitoring intellectual analysis search method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310012753.XA CN103106250B (en) | 2013-01-14 | 2013-01-14 | Video monitoring intellectual analysis search method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103106250A true CN103106250A (en) | 2013-05-15 |
| CN103106250B CN103106250B (en) | 2016-11-23 |
Family
ID=48314105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310012753.XA Expired - Fee Related CN103106250B (en) | 2013-01-14 | 2013-01-14 | Video monitoring intellectual analysis search method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103106250B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104539897A (en) * | 2014-12-27 | 2015-04-22 | 任文华 | Monitoring camera |
| CN104661078A (en) * | 2013-11-15 | 2015-05-27 | Lg电子株式会社 | Video display device and method for operating the same |
| WO2015117572A1 (en) * | 2014-07-28 | 2015-08-13 | 中兴通讯股份有限公司 | Labelling method for moving objects of concentrated video, and playing method and device |
| CN104936021A (en) * | 2015-06-02 | 2015-09-23 | 无锡天脉聚源传媒科技有限公司 | Video play monitoring method and apparatus |
| CN105007442A (en) * | 2015-07-22 | 2015-10-28 | 深圳市万姓宗祠网络科技股份有限公司 | Marking method for continuously recording video and image |
| CN105306880A (en) * | 2015-03-17 | 2016-02-03 | 四川浩特通信有限公司 | Video concentration method |
| CN105323548A (en) * | 2015-03-17 | 2016-02-10 | 四川浩特通信有限公司 | Intelligent combat system |
| CN105323547A (en) * | 2015-03-17 | 2016-02-10 | 四川浩特通信有限公司 | Video condensing system |
| CN105828030A (en) * | 2016-03-14 | 2016-08-03 | 珠海经济特区远宏科技有限公司 | Video investigation mobile terminal system |
| CN105871872A (en) * | 2016-04-28 | 2016-08-17 | 珠海经济特区远宏科技有限公司 | Movable video investigation method |
| CN106021621A (en) * | 2016-07-16 | 2016-10-12 | 安庆建金智能科技有限公司 | Big-data-processing-based satellite case solving system |
| CN108289194A (en) * | 2017-12-28 | 2018-07-17 | 天津天地伟业信息系统集成有限公司 | Video recording quick playback method and apparatus |
| CN108733821A (en) * | 2018-05-22 | 2018-11-02 | 武汉微创光电股份有限公司 | A kind of distribution of monitor video sectional drawing and methods of exhibiting and system |
| CN108765943A (en) * | 2018-05-30 | 2018-11-06 | 深圳市城市公共安全技术研究院有限公司 | Intelligent vehicle monitoring method, monitoring system and server |
| CN109803112A (en) * | 2017-11-16 | 2019-05-24 | 中兴通讯股份有限公司 | Video analysis management method based on big data, apparatus and system, storage medium |
| CN111147778A (en) * | 2019-12-23 | 2020-05-12 | 浙江大华技术股份有限公司 | Track recording method and device based on digital video recorder and storage medium |
| CN111866428A (en) * | 2019-04-29 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Historical video data processing method and device |
| CN115455275A (en) * | 2022-11-08 | 2022-12-09 | 广东卓维网络有限公司 | Video processing system fusing inspection equipment |
| CN117714814A (en) * | 2023-12-16 | 2024-03-15 | 浙江鼎世科技有限公司 | Video storage access system based on intelligent strategy |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060182357A1 (en) * | 2005-02-15 | 2006-08-17 | Matsushita Electric Co., Ltd. | Intelligent, dynamic, long-term digital surveilance media storage system |
| CN1863295A (en) * | 2004-05-13 | 2006-11-15 | 索尼公司 | Image data processing apparatus, image data processing method, program and recording medium |
| CN102256065A (en) * | 2011-07-25 | 2011-11-23 | 中国科学院自动化研究所 | Automatic video condensing method based on video monitoring network |
| CN102799862A (en) * | 2012-06-29 | 2012-11-28 | 陕西省交通规划设计研究院 | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image |
-
2013
- 2013-01-14 CN CN201310012753.XA patent/CN103106250B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1863295A (en) * | 2004-05-13 | 2006-11-15 | 索尼公司 | Image data processing apparatus, image data processing method, program and recording medium |
| US20060182357A1 (en) * | 2005-02-15 | 2006-08-17 | Matsushita Electric Co., Ltd. | Intelligent, dynamic, long-term digital surveilance media storage system |
| CN102256065A (en) * | 2011-07-25 | 2011-11-23 | 中国科学院自动化研究所 | Automatic video condensing method based on video monitoring network |
| CN102799862A (en) * | 2012-06-29 | 2012-11-28 | 陕西省交通规划设计研究院 | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image |
Non-Patent Citations (1)
| Title |
|---|
| 胡宏宇: "基于视频处理的交通事件识别方法研究", 《中国博士论文全文数据库 信息科技辑》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9704536B2 (en) | 2013-11-15 | 2017-07-11 | Lg Electronics Inc. | Video display device and method for operating the same |
| CN104661078A (en) * | 2013-11-15 | 2015-05-27 | Lg电子株式会社 | Video display device and method for operating the same |
| CN104661078B (en) * | 2013-11-15 | 2018-06-05 | Lg电子株式会社 | Video display devices and its operating method |
| WO2015117572A1 (en) * | 2014-07-28 | 2015-08-13 | 中兴通讯股份有限公司 | Labelling method for moving objects of concentrated video, and playing method and device |
| CN104539897A (en) * | 2014-12-27 | 2015-04-22 | 任文华 | Monitoring camera |
| CN105323548B (en) * | 2015-03-17 | 2018-05-15 | 四川浩特通信有限公司 | A kind of intelligence actual combat system |
| CN105323547A (en) * | 2015-03-17 | 2016-02-10 | 四川浩特通信有限公司 | Video condensing system |
| CN105323548A (en) * | 2015-03-17 | 2016-02-10 | 四川浩特通信有限公司 | Intelligent combat system |
| CN105306880A (en) * | 2015-03-17 | 2016-02-03 | 四川浩特通信有限公司 | Video concentration method |
| CN105323547B (en) * | 2015-03-17 | 2018-05-15 | 四川浩特通信有限公司 | A kind of video concentration systems |
| CN104936021A (en) * | 2015-06-02 | 2015-09-23 | 无锡天脉聚源传媒科技有限公司 | Video play monitoring method and apparatus |
| CN105007442A (en) * | 2015-07-22 | 2015-10-28 | 深圳市万姓宗祠网络科技股份有限公司 | Marking method for continuously recording video and image |
| CN105828030A (en) * | 2016-03-14 | 2016-08-03 | 珠海经济特区远宏科技有限公司 | Video investigation mobile terminal system |
| CN105871872A (en) * | 2016-04-28 | 2016-08-17 | 珠海经济特区远宏科技有限公司 | Movable video investigation method |
| CN106021621A (en) * | 2016-07-16 | 2016-10-12 | 安庆建金智能科技有限公司 | Big-data-processing-based satellite case solving system |
| CN106021621B (en) * | 2016-07-16 | 2019-11-01 | 大箴(杭州)科技有限公司 | A kind of satellite based on big data processing is solved a case system |
| CN109803112A (en) * | 2017-11-16 | 2019-05-24 | 中兴通讯股份有限公司 | Video analysis management method based on big data, apparatus and system, storage medium |
| CN108289194A (en) * | 2017-12-28 | 2018-07-17 | 天津天地伟业信息系统集成有限公司 | Video recording quick playback method and apparatus |
| CN108733821A (en) * | 2018-05-22 | 2018-11-02 | 武汉微创光电股份有限公司 | A kind of distribution of monitor video sectional drawing and methods of exhibiting and system |
| CN108765943A (en) * | 2018-05-30 | 2018-11-06 | 深圳市城市公共安全技术研究院有限公司 | Intelligent vehicle monitoring method, monitoring system and server |
| CN111866428A (en) * | 2019-04-29 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Historical video data processing method and device |
| CN111147778A (en) * | 2019-12-23 | 2020-05-12 | 浙江大华技术股份有限公司 | Track recording method and device based on digital video recorder and storage medium |
| CN111147778B (en) * | 2019-12-23 | 2022-06-07 | 浙江大华技术股份有限公司 | Track recording method and device based on digital video recorder and storage medium |
| CN115455275A (en) * | 2022-11-08 | 2022-12-09 | 广东卓维网络有限公司 | Video processing system fusing inspection equipment |
| CN117714814A (en) * | 2023-12-16 | 2024-03-15 | 浙江鼎世科技有限公司 | Video storage access system based on intelligent strategy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103106250B (en) | 2016-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103106250A (en) | Intelligent analysis and retrieval method for video surveillance and system thereof | |
| CN104506804B (en) | Motor vehicle abnormal behaviour monitoring device and its method on a kind of through street | |
| CN107705574A (en) | A kind of precisely full-automatic capturing system of quick road violation parking | |
| CN111800507A (en) | Traffic monitoring method and traffic monitoring system | |
| Lazaridis et al. | Abnormal behavior detection in crowded scenes using density heatmaps and optical flow | |
| KR102035592B1 (en) | A supporting system and method that assist partial inspections of suspicious objects in cctv video streams by using multi-level object recognition technology to reduce workload of human-eye based inspectors | |
| CN102903124A (en) | Moving object detection method | |
| CN103413444A (en) | Traffic flow surveying and handling method based on unmanned aerial vehicle high-definition video | |
| US20110302130A1 (en) | Intelligent video information retrieval apparatus and method capable of multi-dimensional video indexing and retrieval | |
| CN103714325A (en) | Left object and lost object real-time detection method based on embedded system | |
| CN103069434A (en) | Multi-mode video event indexing | |
| CN102665071A (en) | Intelligent processing and search method for social security video monitoring images | |
| CN109063667B (en) | Scene-based video identification mode optimization and pushing method | |
| Lai et al. | Video summarization of surveillance cameras | |
| Li et al. | Improved YOLOv4 network using infrared images for personnel detection in coal mines | |
| CN107480653A (en) | passenger flow volume detection method based on computer vision | |
| CN109766743A (en) | A kind of intelligent bionic policing system | |
| CN104778723A (en) | Method for performing motion detection on infrared image with three-frame difference method | |
| EP3975133A1 (en) | Processing of images captured by vehicle mounted cameras | |
| KR102127276B1 (en) | The System and Method for Panoramic Video Surveillance with Multiple High-Resolution Video Cameras | |
| KR20200071886A (en) | syntax-based method of providing selective video surveillance by use of deep-learning image analysis | |
| CN103077227B (en) | Video concentrates retrieval analysis method and system thereof | |
| CN101877135A (en) | Moving target detecting method based on background reconstruction | |
| Li et al. | Robust real-time detection of abandoned and removed objects | |
| CN115170989A (en) | Rail segmentation method based on enhanced feature extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161123 Termination date: 20190114 |