CN103237192B - A kind of intelligent video monitoring system based on multi-cam data fusion - Google Patents
A kind of intelligent video monitoring system based on multi-cam data fusion Download PDFInfo
- Publication number
- CN103237192B CN103237192B CN201210294950.0A CN201210294950A CN103237192B CN 103237192 B CN103237192 B CN 103237192B CN 201210294950 A CN201210294950 A CN 201210294950A CN 103237192 B CN103237192 B CN 103237192B
- Authority
- CN
- China
- Prior art keywords
- video
- cam
- monitoring
- data fusion
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention proposes a kind of intelligent video monitoring system based on multi-cam data fusion, the processing scheme of multi-cam analog video: when multi-cam directly gathers analog video, adopt vision cable to carry out transmission of video, be converted to the laggard row data fusion of digital video and intelligent video process through video acquisition A/D; The processing scheme of multi-cam digital video: on the basis of the processing scheme of multi-cam analog video, add a video compression plate, and this video compression plate transmits by network after compressing the digital video gathered, decompressed video after host processing system receives compressed video also carries out data fusion and intelligent video process.Intelligent video monitoring system based on multi-cam data fusion of the present invention, can be applicable to traffic surveillance and control system or other system, realizes the functions such as background monitoring is monitored with area-of-interest, target following, target three-dimensional reconstruction.
Description
Technical field
The invention belongs to field of video monitoring systems, be specifically related to a kind of intelligent video monitoring system based on multi-cam data fusion.
Background technology
Along with the development of digital video technology, Video Supervision Technique has become a study hotspot in computer vision research field, and to building a Harmonious Society, safety society is significant.At present, video monitoring system is mainly used in building monitoring, road monitoring, personnel control and the various fields such as identification, deathtrap monitoring, in conjunction with application such as human face detection tech, motion target tracking technology, license plate recognition technologies, there is important practical value and vast potential for future development.But current video monitoring system goes back Shortcomings in some applications, need perfect.
1, background monitoring monitors contradictory problems with area-of-interest
(monitoring refers to and utilizes camera to carry out video acquisition to visual perspective so-called background, and its video monitoring range is large, but resolution is not high for local region of interest.Area-of-interest monitoring refers to and utilizes camera to carry out video acquisition to a certain area-of-interest, but monitoring range will reduce greatly.In actual applications, area-of-interest monitoring can be carried out by the focal length of adjustment overall view monitoring camera, but the ability that will lose large-range monitoring.Such as in road monitoring process, sometimes monitor accident incidents, but do not give prominence to due to details, be difficult to determine the information such as vehicle car plate, driver.If go to extract traffic accident position details information with background camera, by losing the whole monitoring to road, there is video monitoring dead angle thus causing a hidden trouble.Such as, if the data fusion intelligent video monitoring supervisory control system of multi-cam, the direction of one of them monitoring camera and the clear video of focal length acquisition area-of-interest can be adjusted according to monitoring the traffic accident information obtained, namely obtain the clear video of scene of an automobile accident personnel, there will not be suspecting of current doubtful top bag.
Adopt the video monitoring system based on multi-cam, the contradictory problems that background monitoring is monitored with area-of-interest can be solved.A camera can be utilized to monitor background, and another camera is according to the demand of area-of-interest in background, that carries out area-of-interest chooses (adjustment orientation and focal length) and video monitoring, such as can be used for extracting the interested area information of scene of an automobile accident, as vehicle, car plate, occupant, upholstery and article etc.Under multi-cam data fusion intelligent video monitoring system, hit-and-run event, drunk driving top bag event will be frightened.
2, background monitoring and target following contradictory problems
In video monitoring, target following is a kind of important application.Target following technology mainly comprises the technology such as target detection, target identification, target following.Such as utilize face to carry out personage's tracking, utilize car plate to follow the tracks of etc. vehicle.If the camera of background monitoring is used for target monitoring, the target of current visual angle scope only can be followed the tracks of.If carry out camera position control, Focussing etc. carry out target following, must lose the video monitoring to former angular field of view.Adopt multi-cam collaborative work and Data fusion technique, another camera is used for target following for background monitoring to get final product one, by rotating camera and can carry out zoom process, expand target following scope, thus solve background monitoring and target following contradictory problems.For " joyride " behavior more serious at present, generally all to block car plate to evade punishment.If adopt the video monitoring system of dual camera, a video can be adopted to carry out background (scene) monitoring, object detecting and tracking is carried out to its video, and calculate the information such as track, speed, then camera camera position and the focal length of the monitoring of another area-of-interest is adjusted, can in advance monitoring objective by the region of process, over-speed vehicles information (comprising Characteristics of Drivers ' Behavior, upholstery, passenger etc.) can be obtained accurately, particularly face characteristic, can be used for and driving license storehouse coupling, in order to search driver violating the regulations.By adopting this multi-cam supervisory control system, can make to block the behavior that plays truant such as car plate and losing efficacy, thus these illegal " joyrides " of real deterrence personnel, stop " joyride " from source.
3, target three-dimensional reconstruction problem
In video monitoring, three-dimensional reconstruction can be carried out to target.Because target is generally kept in motion, a camera is adopted to be difficult to the three-dimensional reconstruction carrying out target accurately.And adopt the intelligent video monitoring system of multi-cam data fusion, video acquisition can be carried out to target from different perspectives at one time, small sample 3-dimensional reconstruction technology can be utilized to carry out the three-dimensional reconstruction of target, rebuild effect and greatly improve.
4, background monitoring monitors contradictory problems with key protection region
In some key monitoring regions, a camera can be utilized to carry out background (scene) monitoring (large-range monitoring), another camera carries out the monitoring of key protection region, i.e. area-of-interest monitoring, and warn according to the distance etc. between the behavior, facial expression etc. of people and zone of protection, carry out early warning, thus accomplish the surveillance and control measure that overall monitor combines with key monitoring.
5, target retrieval and background monitor contradictory problems
In supervisory control system, target retrieval function can be added, improve system monitoring ability.User can pass through man-machine interface, network (wireless, wired) carries out searched targets setting, then supervisory control system is retrieved real-time video, if retrieve suspicious object, when need examine further, the supervisory control system of single camera will produce the contradiction of scene monitoring and target detail acquisition.And adopt multi-camera system, under the prerequisite ensureing background monitoring, direction and the focal length of another monitoring camera can be adjusted, obtain the target detail video of area-of-interest, thus the various information of target can be obtained further, and the tracking of realize target.
Summary of the invention
In order to solve some not enough in above-mentioned application problems of existing video monitoring system, the invention provides a kind of intelligent video monitoring system based on multi-cam data fusion.
For achieving the above object, the technical solution adopted in the present invention is:
Intelligent video monitoring system based on multi-cam data fusion of the present invention, the processing scheme of multi-cam analog video: when dual camera directly gathers analog video, adopt vision cable to carry out transmission of video, be converted to the laggard row relax of digital video through video acquisition A/D;
The processing scheme of multi-cam digital video: on the basis of the processing scheme of multi-cam analog video, adds a video compression plate, and this video compression plate transmits by network after compressing the digital video gathered.
Preferably, described supervisory control system comprises video processing part, mainly through network reception video, carries out corresponding function treatment again after decompression, comprising the video storage functional module for storing inputted compressed video.
Further, described function treatment is completed by processing module, mainly carries out Face datection, face tracking and identification according to the function of system configuration; Vehicle detection, vehicle tracking and identification; Suspicious item detects, suspicious item is followed the tracks of and identify; Area monitoring and early warning; Video compression stores and these functions of transmission.
Preferably, take in the processing scheme of multi-cam analog video, the dual camera adopted, a background of carrying out wide-angle is monitored, and the knowledge of an extraction monitored according to background according to system carries out the adjustment of monitoring position and focal length to reach the effect of area-of-interest monitoring.
Further, whole system accesses monitor network by LAN interface, both can real-time Transmission compression monitor video, the configuration of monitor network can be realized again, inquire about these functions.
Preferably, described supervisory control system supports warning module, and the early warning mechanism that can divide according to monitor network carries out early warning, and early warning comprises alarm, voice message, these on-the-spot warning functions of blinking red lamp, and distant early warning comprises the function of notice monitor network.
Relative to prior art, the intelligent video monitoring system based on multi-cam data fusion of the present invention, has following useful technique effect:
1, the intelligent video monitoring system of multi-cam data fusion is adopted, in traffic surveillance and control system, can under the prerequisite of global monitoring, carry out monitoring interested according to demand, violate the traffic regulations in event in traffic accident, hypervelocity etc., video information evidence is clearly provided, traffic violations behavior is punished.
2, adopt the intelligent video monitoring system of multi-cam data fusion, the video of same target can be obtained as required from different perspectives, be conducive to the three-dimensional reconstruction of this target.Such as in face identification system, can three-dimensional face information be set up, thus improve the accuracy in the identification of complex illumination environment human face.
3, adopt the intelligent video monitoring system of multi-cam data fusion, can follow the tracks of and anticipation the movement locus of target, be adjusted direction and the focal length of another camera by anticipation knowledge, the clear video of target of area-of-interest can be obtained.Namely this application may be used for the early warning of warning region, also may be used for the clear video acquisition of over-speed vehicles characteristic sum driver.
4, adopt the intelligent video monitoring system of multi-cam data fusion, in target retrieval process, both ensured that former guarded region was constant, clear video and the feature of area-of-interest target can be got again.This technology provides very large facility by for police's work.
Accompanying drawing explanation
Fig. 1 is the supervisory control system block diagram of the dual camera analog video input of a kind of intelligent video monitoring system based on multi-cam data fusion of the present invention.
Fig. 2 is the supervisory control system theory diagram of the dual camera digital video input of a kind of intelligent video monitoring system based on multi-cam data fusion of the present invention.
Fig. 3 is the video monitoring system hardware plan schematic diagram of the dual camera analog video input of a kind of intelligent video monitoring system based on multi-cam data fusion of the present invention.
Fig. 4 is the hardware plan schematic diagram of the supervisory control system of the dual camera digital video input of a kind of intelligent video monitoring system based on multi-cam data fusion of the present invention.
Embodiment
Describe the architecture of the intelligent video monitoring system based on multi-cam data fusion of the present invention below in conjunction with accompanying drawing in detail, but be not construed as limiting the invention.
A kind of system design scheme of the present invention: for realizing the video monitoring of multi-cam, realize background monitoring with area-of-interest monitor, target following, three-dimensional reconstruction walk abreast etc. function, selecting can the high-performance treatments chip of concurrent working, according to the following two kinds of processing schemes of specific requirement design.
1, the processing scheme of multi-cam analog video is taked:
When dual camera directly gathers analog video (as shown in Figure 1), adopt vision cable to carry out transmission of video, be converted to the laggard row relax of digital video through video acquisition A/D.Process completed by processing module, mainly according to system configuration function carry out Face datection, face tracking and identification; Vehicle detection, vehicle tracking and identification; Suspicious item detects, suspicious item is followed the tracks of and identify; Area monitoring and early warning; The functions such as video compression storage and transmission.Wherein Each performs its own functions for dual camera, and a background of carrying out wide-angle is monitored, the knowledge of an extraction monitored according to background according to system, and the adjustment carrying out monitoring position and focal length reaches the effect of area-of-interest monitoring.Whole system accesses monitor network by LAN interface, both can real-time Transmission compression monitor video, the functions such as the configuration of monitor network, inquiry can be realized again.This system supports warning module module, and the early warning mechanism that can divide according to monitor network carry out early warning, and early warning comprises on-the-spot early warning functions such as () alarm, voice message, blinking red lamps, distant early warning (notice monitor network).
2, the processing scheme of multi-cam digital video is taked:
Compared with analog video input scheme (Fig. 1), mainly add a video compression plate (shown in Fig. 2), this plate mainly gathers video, and compresses the digital video gathered, and can be transmitted by network.And for supervisory control system itself, corresponding function treatment, mainly through network reception video, is carried out after decompression again in head end video processing section.Wherein video storage functional module directly stores the compressed video of input.Shown in all the other function setting with Fig. 1, supervisory control system is consistent.
For realizing the real-time of multi-cam supervisory control system, system mainly adopts multimode concurrent working mode to research and develop, and particular hardware design is as described below.
1) the supervisory control system hardware scheme of multi-cam analog video input
Shown in composition graphs 3, in the multi-cam video monitoring system adopting analog video as input, for improving system real time video processing ability, main video pre-filtering module+main control module+video signal processing module three the concurrent working module that adopts is formed.Wherein, video pre-filtering module is mainly according to the configuration information of main control module, preliminary treatment is carried out to the multi-cam video information gathered, comprise the functions such as color of image space transforming, image interlaced/progressive conversion, image enhaucament, histogram calculation, area-of-interest (ROI) extraction, then the video after process is flowed to main control module.Main control module is the core of whole system, carries out the configuration of systemic-function according to the configuration information of user.In Video processing, the video information that main collection video pre-filtering module is carried also is stored in the high speed twoport DARAM shared with signal processing module, then the response video processing function (must video compression be done) of call signal processing module, and read video processing results, the video storing or compressed by Internet Transmission.According to function and the real-time video processing results of system configuration, main control module can be controlled in (adjusting focal length, orientation etc.) two cameras by serial ports by the The Cloud Terrace of multi-cam, reach the effect of area-of-interest monitoring, main control module will store or transmitting, monitoring video.Such as in traffic monitoring, if find in video analysis doubtful traffic accident occurs, main control module can adjust orientation and the focal length of a camera according to analysis result, obtain the clear video of the area-of-interest of scene of an automobile accident and report to the police.If it is on-the-spot that this supervisory control system is applied to Shenzhen accident incidents occurred in the recent period, by clear record scene of an automobile accident details, comprise the inner clear video of accident vehicle, will the dispute of stealthily substituting be there is not.Wherein main control module communicates with signal processing module and follows Client/Server specification, namely main control module only needs the signal processing module of announcement will carry out what kind of process (by configuration information requirement), complex calculations process is undertaken by signal processing module at a high speed, then result is passed to main control module.Main control module also realizes human-computer interaction function, wherein man-machine interaction comprises touch-screen and display screen, radio transmission-receiving function, LAN transmission-receiving function, keyboard and mouse function etc., user can be configured system according to application demand, main control module will adjust video pre-filtering function and the corresponding configuration information of signal processing module accordingly, make system-specific.
2) the supervisory control system hardware scheme of multi-cam digital video input
Shown in composition graphs 4, in the supervisory control system of multi-cam digital video input, mainly comprise video compression plate and monitoring mainboard two parts, video compression buttress carries out preliminary treatment, then compressed video according to the information of monitoring mainboard configuration to the two-path video gathered.The video information of compression gives monitoring mainboard by Internet Transmission.Monitoring mainboard receives the monitoring video information of compression, while store or transmit video, call signal processing module decompresses to the video received on one side, then carries out the corresponding Algorithm Analysis of video according to configuration information, and video processing results is passed to main control module.Wherein main control module communicates with signal processing module and follows Client/Server specification, namely main control module only needs the signal processing module of announcement will carry out what kind of process (by configuration information requirement), complex calculations process is undertaken by signal processing module at a high speed, then result is passed to main control module.Main control module also realizes human-computer interaction function, wherein man-machine interaction comprises touch-screen and display screen, radio transmission-receiving function, LAN transmission-receiving function, keyboard and mouse function etc., user can be configured system according to application demand, main control module will adjust video pre-filtering function and the corresponding configuration information of signal processing module accordingly, make system-specific.
A kind of intelligent video monitoring system software function based on multi-cam data fusion and scheme:
Monitor system software design based on multi-cam mainly comprises two aspects, one is overall application programming, two is that video processnig algorithms API designs and algorithm packaging, overall application program, by calling (the video processnig algorithms application walked abreast by signal processing module) video processnig algorithms API, realizes video processing function.System by the function according to concrete configuration (as Face datection, face tracking and identification; Vehicle detection, vehicle tracking and identification; Suspicious item detects, suspicious item is followed the tracks of and identify; Area monitoring and early warning etc.), enter corresponding processing module, realize the global monitoring to guarded region and area-of-interest monitoring.If select the monitoring scheme of digital video input, then what monitor mainboard reception is the video compressed, and can directly store or transmit.After compressed video is decompressed, data fusion and intelligent video process can be carried out.If the monitoring scheme of analog video input, directly can carry out data fusion and intelligent video process to the video of collection, and then carry out video compression and storage or transmission.Attention: the storage of compressed video or transmission should walk abreast with whole video analysis in systems in which and carry out.
The main switching carrying out function according to configuration information, wherein configuration information can be arranged by Man Machine Interface, communication or cable network.According to configuration information, system can complete following several monitoring mode.
1) traffic and suspicious item monitoring mode
When configuring option and installment 0, enter this monitoring mode.Two cameras carry out video acquisition to guarded region, system in parallel process two-path video, and carry out Intelligent Information Processing to video.When finding suspicious item or traffic problems in the video at a camera, namely by orientation and the focal length of another camera of adjustment, carry out area-of-interest video acquisition and Minutiae extraction.After Video processing completes, two-path video all will be compressed, and then carries out storing or network transmission.If generation traffic accident, then in area-of-interest video, the information such as car plate, character features will be extracted, and can send warning message (passing through network) to traffic police at once.
2) personnel and environmental monitoring pattern
When configuring option and installment 1, enter this monitoring mode.Two cameras carry out video acquisition to guarded region, and carry out person detecting (comprising Face datection).When personage being detected, adjusting another camera at once and carrying out area-of-interest video acquisition, and carrying out human face detection and tracing.If this people is authorized to, then only record behavioural information.If this people's unauthorized, then at once report to the police go forward side by side pedestrian's thing follow the tracks of and movement track differentiate and human face expression and body language differentiation, early warning as early as possible.The video of whole collection can carry out storing or Internet Transmission after compression.
3) security area monitoring mode
When configuring option and installment 2, enter this monitoring mode.A camera is set to area monitoring pattern, and a camera is set to area-of-interest monitoring mode.First system processes the video being applied to area monitoring pattern, and find that there is after people, thing or vehicle enter guarded region, the camera that adjustment is at once used for area-of-interest monitoring carries out details monitoring, obtain enter people, thing and vehicle detailed information.If the problem of finding that there is (as face by people for blocking, vehicle license plate to be blocked etc. problem time), reporting system is reported to the police.System is also followed the tracks of the movement locus of the people normally entered, thing, vehicle and is predicted, and compare with prewarning area (system configuration), if any 90% confidential interval entering prewarning area, then adjust area-of-interest monitoring mode camera and carry out details monitoring, extract feature, and carry out early warning simultaneously.The video of whole collection can carry out storing or Internet Transmission after compression.
4) the video frequency searching monitoring mode of feature based
When configuring option and installment 3, enter this monitoring mode.Under this pattern, mainly according to the retrieval character (people, car plate etc.) of input, real-time retrieval is carried out to the video of guarded region, when finding that suspicious object occurs, adjust another camera and carry out area-of-interest video acquisition, and carry out characteristic matching (face coupling, personage's form fit, vehicle coupling, car plate coupling etc.), as the match is successful, then video tracking carried out to this target and send match information and new feature database information to retrieval side.The video of whole collection can carry out storing or Internet Transmission after compression.
Above-described embodiment, just in order to technical conceive of the present invention and feature are described, its objective is and is one of ordinary skilled in the art can be understood content of the present invention and implement according to this, can not limit the scope of the invention with this.The change of every equivalence done by the essence of content of the present invention or modification, all should be encompassed in protection scope of the present invention.
Claims (5)
1., based on an intelligent video monitoring system for multi-cam data fusion, it is characterized in that,
The processing scheme of multi-cam analog video: when dual camera directly gathers analog video, adopts vision cable to carry out transmission of video, is converted to the laggard row data fusion of digital video and intelligent video process through video acquisition A/D;
The processing scheme of multi-cam digital video: on the basis of the processing scheme of multi-cam analog video, add a video compression plate, and this video compression plate transmits by network after compressing the digital video gathered, host processing system decompresses after receiving compressed video, then data fusion and intelligent video process is carried out, take in the processing scheme of multi-cam analog video, adopt dual camera, a background of carrying out wide-angle is monitored, the knowledge of an extraction monitored according to background according to system carries out the adjustment of monitoring position and focal length to reach the effect of area-of-interest monitoring.
2. the intelligent video monitoring system based on multi-cam data fusion according to claim 1, it is characterized in that, described supervisory control system comprises video processing part, by network reception video, data fusion and corresponding function treatment is carried out again, comprising the video storage functional module for storing inputted compressed video after decompression.
3. the intelligent video monitoring system based on multi-cam data fusion according to claim 2,
It is characterized in that, described function treatment is completed by processing module, and the function according to system configuration carries out Face datection, face tracking and identification; Vehicle detection, vehicle tracking and identification; Suspicious item detects, suspicious item is followed the tracks of and identify; Area-of-interest monitoring and early warning; Video compression stores and these functions of transmission.
4. the intelligent video monitoring system based on multi-cam data fusion according to any one of claim 1-3, it is characterized in that, whole system accesses monitor network by LAN interface, both can real-time Transmission compression monitor video, the configuration of monitor network can be realized again, inquire about these functions.
5. the intelligent video monitoring system based on multi-cam data fusion according to claim 1,
It is characterized in that, described supervisory control system supports warning module, and the early warning mechanism that can divide according to monitor network carries out early warning, and early warning comprises alarm, voice message, these on-the-spot warning functions of blinking red lamp, also comprises the distant early warning function of notice monitor network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210294950.0A CN103237192B (en) | 2012-08-20 | 2012-08-20 | A kind of intelligent video monitoring system based on multi-cam data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210294950.0A CN103237192B (en) | 2012-08-20 | 2012-08-20 | A kind of intelligent video monitoring system based on multi-cam data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103237192A CN103237192A (en) | 2013-08-07 |
| CN103237192B true CN103237192B (en) | 2016-03-30 |
Family
ID=48885205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210294950.0A Expired - Fee Related CN103237192B (en) | 2012-08-20 | 2012-08-20 | A kind of intelligent video monitoring system based on multi-cam data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103237192B (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424627A (en) * | 2013-08-27 | 2015-03-18 | 北京计算机技术及应用研究所 | Multipath image fusion system and image fusion method |
| CN104202578A (en) * | 2014-09-27 | 2014-12-10 | 江阴延利汽车饰件股份有限公司 | Method for automatically identifying criminal suspects |
| CN104573637B (en) * | 2014-12-18 | 2020-11-03 | 厦门翼歌软件科技有限公司 | License plate recognition method based on multiple cameras |
| CN104581064B (en) * | 2014-12-26 | 2019-04-26 | 深圳市海蕴新能源有限公司 | A kind of method and device of camera warning message integration |
| CN105844634B (en) * | 2016-03-18 | 2019-04-05 | 阜阳师范学院 | A kind of multiple mobile object tracking monitor method |
| CN111784615A (en) | 2016-03-25 | 2020-10-16 | 北京三星通信技术研究有限公司 | Method and device for processing multimedia information |
| CN105933650A (en) * | 2016-04-25 | 2016-09-07 | 北京旷视科技有限公司 | Video monitoring system and method |
| CN107124586A (en) * | 2017-05-05 | 2017-09-01 | 华东师范大学 | Camera intelligent screening system |
| CN107194991B (en) * | 2017-05-17 | 2021-01-01 | 西南科技大学 | Three-dimensional global visual monitoring system construction method based on skeleton point local dynamic update |
| CN107426542A (en) * | 2017-08-08 | 2017-12-01 | 深圳市安软慧视科技有限公司 | The hardware structure of Real-Time Arltificial Intelligence video system based on edge calculations |
| CN111699679B (en) * | 2018-04-27 | 2023-08-01 | 上海趋视信息科技有限公司 | Traffic system monitoring and method |
| CN109040685A (en) * | 2018-08-21 | 2018-12-18 | 中国联合网络通信集团有限公司 | Method for processing video frequency, system and server |
| CN109272221A (en) * | 2018-09-06 | 2019-01-25 | 济南市市中区综合行政执法局 | City management method, apparatus and electronic equipment |
| CN110896459A (en) * | 2018-09-13 | 2020-03-20 | 广州弘度信息科技有限公司 | Method for freely customizing detection task based on video stream |
| CN109241933A (en) * | 2018-09-21 | 2019-01-18 | 深圳市九洲电器有限公司 | Video linkage monitoring method, monitoring server, video linkage monitoring system |
| CN110008797B (en) * | 2018-10-08 | 2021-12-14 | 杭州中威电子股份有限公司 | Multi-camera multi-face video continuous acquisition method |
| CN110287776B (en) * | 2019-05-15 | 2020-06-26 | 北京邮电大学 | Face recognition method and device and computer readable storage medium |
| CN110430395A (en) * | 2019-07-19 | 2019-11-08 | 苏州维众数据技术有限公司 | Video data AI processing system and processing method |
| CN112712671A (en) * | 2020-12-18 | 2021-04-27 | 济南浪潮高新科技投资发展有限公司 | Intelligent alarm system and method based on 5G |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101293529A (en) * | 2007-04-29 | 2008-10-29 | 余亚莉 | Intelligent monitoring and early warning system for passenger transportation ability and operation safety of vehicle mounted rail traffic |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| KR20120014263A (en) * | 2010-08-09 | 2012-02-17 | 김문근 | Multi cameras recording procedure in multi-cell storage type digital video recorder |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7769227B2 (en) * | 2004-09-15 | 2010-08-03 | Panasonic Corporation | Object detector |
-
2012
- 2012-08-20 CN CN201210294950.0A patent/CN103237192B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101293529A (en) * | 2007-04-29 | 2008-10-29 | 余亚莉 | Intelligent monitoring and early warning system for passenger transportation ability and operation safety of vehicle mounted rail traffic |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| KR20120014263A (en) * | 2010-08-09 | 2012-02-17 | 김문근 | Multi cameras recording procedure in multi-cell storage type digital video recorder |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103237192A (en) | 2013-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103237192B (en) | A kind of intelligent video monitoring system based on multi-cam data fusion | |
| CN103248867A (en) | Surveillance method of intelligent video surveillance system based on multi-camera data fusion | |
| US9721168B2 (en) | Directional object detection | |
| US10930151B2 (en) | Roadside parking management method, device, and system based on multiple cameras | |
| US10789840B2 (en) | Systems, apparatuses and methods for detecting driving behavior and triggering actions based on detected driving behavior | |
| CN105913559B (en) | A kind of ATM in bank intelligent control method based on body-sensing technology | |
| CN103366565B (en) | Method and system of detecting pedestrian running red light based on Kinect | |
| CN100446043C (en) | Video safety prevention and monitoring method based on biology sensing and image information fusion | |
| Trivedi et al. | Distributed interactive video arrays for event capture and enhanced situational awareness | |
| CN204155449U (en) | A kind of Car license recognition comparison high-definition camera and supervisory system | |
| CN100555348C (en) | Intelligent video monitoring system of bank self-aid apparatus | |
| CN103419750A (en) | Vehicle tracking method and system integrating multiple camera images | |
| KR102039277B1 (en) | Pedestrian face recognition system and method thereof | |
| CN101493979A (en) | Method and instrument for detecting and analyzing intelligent network vision target | |
| CN109671299A (en) | It is a kind of based on crossing camera probe to the system and method for pedestrian's danger early warning | |
| CN110650322A (en) | Security and protection system based on cloud service, Internet of things and AR security and protection glasses | |
| CN109544936A (en) | Motor vehicle zebra stripes based on radar video camera do not give precedence to pedestrian's early warning capturing system | |
| CN104660969A (en) | System and method for achieving high-definition intelligent toll-gate management based on GIS map and video | |
| CN114360210A (en) | Vehicle fatigue driving early warning system | |
| CN114170272A (en) | Accident reporting and storing method based on sensing sensor in cloud environment | |
| EP3857528A1 (en) | Traffic monitoring and evidence collection system | |
| WO2022121196A1 (en) | Telescopic vision computing system | |
| CN114140719A (en) | AI traffic video analysis technology | |
| KR20100077662A (en) | Inteligent video surveillance system and method thereof | |
| US11616932B1 (en) | Car security camera triggering mechanism |
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: 20160330 Termination date: 20200820 |