CN202422425U - Video-detection-based intelligent signal control system for crossing - Google Patents

Video-detection-based intelligent signal control system for crossing Download PDF

Info

Publication number
CN202422425U
CN202422425U CN2011205500602U CN201120550060U CN202422425U CN 202422425 U CN202422425 U CN 202422425U CN 2011205500602 U CN2011205500602 U CN 2011205500602U CN 201120550060 U CN201120550060 U CN 201120550060U CN 202422425 U CN202422425 U CN 202422425U
Authority
CN
China
Prior art keywords
vehicle
video
detection
crossing
vehicles
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
Application number
CN2011205500602U
Other languages
Chinese (zh)
Inventor
钱红波
韩皓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Maritime University
Original Assignee
Shanghai Maritime University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Maritime University filed Critical Shanghai Maritime University
Priority to CN2011205500602U priority Critical patent/CN202422425U/en
Application granted granted Critical
Publication of CN202422425U publication Critical patent/CN202422425U/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The utility model discloses a video-detection-based intelligent signal control system for a crossing. On the basis of the conventional jaywalking snap-shot system, a group of cameras is added to acquire recorded videos in which vehicles on approaches approach stop lines, and vehicle tracking detection areas are arranged on lanes which are a certain length behind the stop lines of the approaches at each crossing to track all the vehicles in the tracking detection areas; and if a certain vehicle gets in the dilemma of the yellow light when a yellow light is turned on, the yellow light is delayed for 1 second in real time to enable the vehicle to cross the stop line before the yellow light is turned off, the driving statuses of the vehicles in the detection areas are judged again 1 to 2 seconds before the yellow light is turned off, the turning-on of a green light of the next phase is delayed in real time if a certain vehicle is in a jaywalking status, and a jaywalking snap-shot system is started at the same time to perform snap-shot evidence collection operation on the jaywalking of the vehicle.

Description

Crossing intelligent signal control system based on Video Detection
Technical field
The utility model relates to traffic signals control field, specially refers to a kind of crossing intelligent signal control system based on Video Detection.
Background technology
Vehicle its main function of capturing system of making a dash across the red light is that video camera writes down crossing vehicles running red light violating the regulations automatically; Can be implemented in that panoramic video and the car plate feature video to vehicles running red light carries out Taking Pictures recording under the unattended condition, the punishment of enforcing the law provides reliable basis to vehicles running red light for public safety traffic management department.
At present, the vehicle triggering mode classification that product on this market of capturing system captures according to vehicles peccancy of making a dash across the red light mainly contains two kinds at home, i.e. ground induction coil triggering mode and video virtual coil triggering mode.It is to detect cut ring Wiring trough on the track, burying inductive coil (or inductive rod) then underground that ground induction coil triggers.Vehicle through the time inductive coil can send signal and give relevant device, more accurate to vehicle detection.But owing to need strengthen difficulty of construction and improve engineering cost simultaneously at the underground inductive coil of burying underground.The circle of also need heavily sunkening cord during pavement maintenance, in addition northern cold icy freeze under the weather and the bad situation of pavement quality under maintenance workload to coil bigger, need the periodic replacement coil.In addition, the ground induction coil triggering mode generally can't accurately pick out the vehicle operating track owing to be installed in few fixed zone on the road surface, goes lane change violating the regulations, acts of violating regulations such as exception parking thereby can't differentiate not according to the track sign.
The principle of work that the video virtual coil triggers is similar to buried coil checker; The defining virtual coil replaces the ground induction coil on the actual road surface on the corresponding lane position on the site traffic video image that obtains through video camera but the user only needs; System carries out the module tracks coupling through the image recognition processing technology to front and back two continuous frames picture, changes simulating vehicle to press ground induction coil to form with the virtual coil module and captures signal.
Based on ground induction coil vehicle detection technology and all comparatively ripe based on the virtual coil video detection technology present technology of capturing system of making a dash across the red light, there are the relevant matured products of many families to release on the market, can accomplish vehicles running red light preferably and capture evidence obtaining work.But all in the market capturing systems that make a dash across the red light all have a fatal weakness; Be that this type systematic only can make a dash across the red light this act of violating regulations generation back through capturing evidence obtaining at vehicle; For punishment is from now on produced evidence; Whether they are neither can be before vehicles peccancy makes a dash across the red light differentiates this vehicle according to the distance of the situation of signal lamp timing at that time and vehicle distances stop line and travel speed information and can make a dash across the red light; Show thereby adjust the signal light color in real time, avoid vehicles running red light and other collision happens, reduce the generation of traffic hazard.
In sum, to the defective of prior art, need a kind of crossing intelligent signal control system especially, with the problem of mentioning more than solving based on Video Detection.
The utility model content
The purpose of the utility model is to provide the crossing intelligent signal control system based on Video Detection; Overcome can only afterwards collecting evidence of traditional capturing system existence of making a dash across the red light; Can not differentiate the defective of the behavior of making a dash across the red light in advance; And can adjust the controlling schemes of traffic lights accordingly, reached the purpose that reduces traffic hazard.
The technical matters that the utility model solved can adopt following technical scheme to realize:
Crossing intelligent signal control system based on Video Detection comprises front end capturing system, the information transmission system and center processing control system; It is characterized in that; Said front end capturing system comprises main frame, the connected traffic signals detection system of difference and automobile video frequency detection system; Main frame upper control traffic signals detection system and automobile video frequency detection system, the information transmission system connects front end capturing system and center processing control system.
In an embodiment of the utility model, said automobile video frequency detection system comprises through vehicles feature video camera, left turning vehicle feature video camera and the panoramic camera that is installed on behind the stop line, and the vehicle tracking that is installed on the intersection exit place detects video camera.
Crossing intelligent signal control system based on Video Detection is characterized in that said method comprises the steps:
1) image-taking system obtains video image in real time, and the vehicle tracking monitored area is set;
2) global calibration and coordinate conversion are carried out in the vehicle tracking monitored area, obtain the corresponding relation of image coordinate and three-dimensional world coordinate;
3) video image is carried out context update, image binaryzation and patch analyzing and processing, obtain the patch cluster areas, then the vehicle in the patch cluster areas is positioned and trace analysis;
4) extract the speed of a motor vehicle v of vehicle in the vehicle tracking monitored area according to location and the result of trace analysis, apart from the distance L of stop line, main frame combines apart from amber light end residual time length t 1, the design maximum retarded velocity a of vehicle and driver's reaction time t 2, set up corresponding vehicle running state discrimination model;
5) if amber light opens when bright to be differentiated the transport condition of the vehicle in the detection zone, if vehicle v.t is wherein arranged 1<L and t 2.v+v 2/ 2a>L judges that then this vehicle is absorbed in the in a dilemma district of amber light, prolongs amber light in real time and lets this vehicle can catch up with before amber light finishes in 1 second to cross stop line;
Once more the transport condition of the vehicle in the detection zone was differentiated in preceding 1~2 second in the amber light end, if find wherein to have vehicle v.t 1<L and v 2/ 2a>L; Judge that then this vehicle both can not cross stop line before amber light finishes; Can not be before amber light finishes before stop line emergency, judge that this vehicle is in the transport condition that makes a dash across the red light, the green light of postponing next phase place in real time opens the bright time; Start the front end capturing system simultaneously, this vehicle is made a dash across the red light capture evidence obtaining work.
Description of drawings
Fig. 1 is the process flow diagram of the described crossing intelligent signal control system based on Video Detection of the utility model.
Fig. 2 is the synoptic diagram of the described crossing intelligent signal control system based on Video Detection of the utility model.
Fig. 3 is that procedure chart is captured in the behavior of making a dash across the red light of the described vehicle of the utility model;
Embodiment
For technological means, creation characteristic that the utility model is realized, reach purpose and be easy to understand understanding with effect, below in conjunction with embodiment, further set forth the utility model.
As shown in Figure 2, the described crossing intelligent signal control system based on Video Detection of the utility model comprises front end capturing system 100, the information transmission system 200 and center processing control system 300; Said front end capturing system 100 comprises main frame 110, connected traffic signals detection system 120 and 130 draws of automobile video frequency detection system respectively; Main frame 110 upper control traffic signals detection systems 120 detect 130 with automobile video frequency, and the information transmission system 200 connects front end capturing system 100 and center processing control system 300.
Wherein front end capturing system 100 adopts video virtual coils or ground induction coil to trigger the technology of candid photograph, is responsible for accomplishing under red light phase, captures the vehicle behavior of making a dash across the red light.The information transmission system 200 can adopt different communication modes such as fibre-optic transmission system (FOTS), wireless transmitting system and wideband transmission system; The picture that it captures front end capturing system 100 in time transfers on the server of rear end center processing control system 300 with relevant information (time, place, information of vehicles, car plate picture etc.), is " lifeline " that connects front end and rear end.Rear end center processing control system is accomplished through background manage software front end system is transmitted the work that the picture of returning is handled; Through the information such as vehicle pictures (comprise the car plate picture, pass through information such as place, time, number plate recognition result) that server receiving front-end system beams back, record stores and also writes database; And the docking of other system in completion and the public security net, other system being called easily originally make a dash across the red light all resources of capturing system is the social security management service, realizes data sharing.
Make a dash across the red light and differentiate and intelligent signal control needs the following process of experience in the described crossing based on Video Detection of the utility model: steps such as hardware system makes up with the video picture recording and obtains, video picture recording demarcation and coordinate conversion, context update, image binaryzation, patch analysis, vehicle triggering and detection, vehicle tracking, traffic parameter extraction, vehicle running state differentiation, signal controlling project setting.
1, hardware system makes up with the video picture recording and obtains
Certain distance is installed through vehicles feature shooting 1, left turning vehicle feature video camera 2, panoramic camera 3 behind crossing inlet road stop line; Obtain vehicle gets into the crossing through stop line video image; Near the intersection exit road, be installed into the stomatodeum vehicle tracking and detect video camera 8; Obtain the video image of vehicle approaching stop line
2, global calibration and coordinate conversion
The track that will detect in the selecting video record image; Virtual coil 5 behind the virtual coil 4 and left turning vehicle stop line is set before and after the left turn lane stop line before the left turning vehicle stop line; Virtual coil 7 behind the virtual coil 6 and through vehicles stop line is set before and after the Through Lane stop line before the through vehicles stop line; Behind the Through Lane stop line, through vehicles is set and follows the tracks of surveyed area 9 to about 40 meters zone; Behind the left turn lane stop line, left turning vehicle is set and follows the tracks of surveyed area 10, through vehicles is followed the tracks of surveyed area 9 follow the tracks of surveyed area 10 with left turning vehicle and be set to area-of-interest, utilize the calibration algorithm of vanishing point and the constant theorem of double ratio to realize the coordinate transform of former figure area-of-interest and vertical view to about 40 meters zone; Obtain the corresponding relation of image coordinate and three-dimensional world coordinate; Create the vertical view in research track, all follow-up processing are all carried out overlooking on the mapping graph.
3, context update
Utilize adaptive median filter AMF algorithm to obtain initial background, in conjunction with the context update of motion mask in the Surendra algorithm and AMF algorithm realization vertical view.Make the motion mask according to the zone that has had vehicle in the track and candidate's vehicle region (patch zone), context update is not carried out in the zone in this mask, but not masks area then can be realized context update rapidly according to the AMF algorithm.
4, image binaryzation and patch analysis
Convert the colored vertical view that obtains to gray-scale map, behind the context update, prospect is split through image partition method; Being reflected on the binary map is connected region one by one, is referred to as patch, and the patch analysis need be extracted the essential information of all patches in the binary map; Again according to the position and the colouring information of patch; Polymerization or cut apart patch, and last deletion do not meet the patch of vehicle size shape, accomplishes the patch cluster.
5, vehicle triggers and detects
Result through obtaining after the above-mentioned patch cluster obtains candidate's vehicle region, i.e. the zone of patch after the cluster; Each candidate's vehicle in the monitoring and detection zone; Find the position and the size of the vehicle of new entering surveyed area, and go out, realize the detection and the triggering of actual vehicle with the square frame frame.
6, vehicle tracking
Under the situation of not blocking, use patch to follow the tracks of, the back occurs blocking with Mean shift track algorithm.The vehicle tracking method is through identifying the pixel that meets vehicle characteristics in the traffic scene image; Carry out image Segmentation; And the characteristic that foundation extracts is mated vehicle in the frame of front and back; The vehicle that through vehicles is followed the tracks of in surveyed area 9 and the left turning vehicle tracking surveyed area 10 interior videos positions and follows the tracks of, and realizes the Accurate Analysis to the movement locus of vehicle.
7, traffic parameter extracts
According to trace analysis, detect in real time the speed of a motor vehicle v (meter per second) that follows the tracks of vehicle in the detection zone, apart from the distance L (rice) of stop line, and send it to the crossing candid photograph main frame 110 that makes a dash across the red light the vehicle movement track.
8, vehicle running state is differentiated and the signal controlling project setting
Make a dash across the red light and capture the operation of main frame 110 through signal detection system 120 real-time pilot signal timing schemes; Open when bright at amber light the distance of following the tracks of the vehicle distances stop line in the surveyed area and the transport condition of vehicle are differentiated, if find wherein to have vehicle v.t 1<L and t 2.v+v 2/ 2a>L; Judge that then this vehicle is absorbed in the in a dilemma district of amber light; The prolongation amber light let this vehicle can catch up with before amber light finishes in 1 second and crosses stop line in real time, once more the transport condition of the vehicle in the detection zone was differentiated in preceding 1~2 second in the amber light end, if find wherein to have vehicle v.t 1<L and v 2/ 2a>L; Judge that then this vehicle both can not cross stop line before amber light finishes; Can not be before amber light finishes before stop line emergency, judge that this vehicle is in the transport condition that makes a dash across the red light, the green light of postponing next phase place in real time opens the bright time; Start the capturing system that makes a dash across the red light simultaneously, this vehicle is made a dash across the red light capture evidence obtaining work.
It is as shown in Figure 3 that process is captured in the vehicle behavior of making a dash across the red light, when red signal, after motor vehicle is pressed in stop line on first coil the time; 130 first trigger pips of automobile video frequency detection system are made a dash across the red light to the crossing and are captured main frame 110, and main frame 110 gives video camera first candid photograph signal, and the camera motor-car is pressed in the photo on the stop line; Shown in Fig. 3 (a), when motor vehicle leaves first coil, when getting into second coil; Automobile video frequency detection system 130 is given 110 second signals of main frame, and main frame 110 captures signal, the photo that the camera motor-car leaves stop line and continues to move ahead for second in video camera; Shown in Fig. 3 (b), when vehicle leaves second coil, the automobile video frequency detection system is given the 3rd signal of main frame 110; Main frame 110 captures signal for the 3rd in video camera, and the photo that the camera motor-car continues to move ahead is shown in Fig. 3 (c).
More than show and described ultimate principle of the utility model and the advantage of principal character and the utility model.The technician of the industry should understand; The utility model is not restricted to the described embodiments; The principle of describing in the foregoing description and the instructions that the utility model just is described; Under the prerequisite that does not break away from the utility model spirit and scope, the utility model also has various changes and modifications, and these variations and improvement all fall in the utility model scope that requires protection.The utility model requires protection domain to be defined by appending claims and equivalent thereof.

Claims (2)

1. based on the crossing intelligent signal control system of Video Detection, comprise front end capturing system, the information transmission system and center processing control system; It is characterized in that; Said front end capturing system comprises main frame, the connected traffic signals detection system of difference and automobile video frequency detection system; Main frame upper control traffic signals detection system and automobile video frequency detection system, the information transmission system connects front end capturing system and center processing control system.
2. the crossing intelligent signal control system based on Video Detection according to claim 1; It is characterized in that; Said automobile video frequency detection system comprises through vehicles feature video camera, left turning vehicle feature video camera and the panoramic camera that is installed on behind the stop line, and the vehicle tracking that is installed on the intersection exit place detects video camera.
CN2011205500602U 2011-12-23 2011-12-23 Video-detection-based intelligent signal control system for crossing Expired - Fee Related CN202422425U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2011205500602U CN202422425U (en) 2011-12-23 2011-12-23 Video-detection-based intelligent signal control system for crossing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2011205500602U CN202422425U (en) 2011-12-23 2011-12-23 Video-detection-based intelligent signal control system for crossing

Publications (1)

Publication Number Publication Date
CN202422425U true CN202422425U (en) 2012-09-05

Family

ID=46747163

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2011205500602U Expired - Fee Related CN202422425U (en) 2011-12-23 2011-12-23 Video-detection-based intelligent signal control system for crossing

Country Status (1)

Country Link
CN (1) CN202422425U (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496285A (en) * 2011-12-23 2012-06-13 上海海事大学 Method for determining red-light running of vehicles at intersection based on video detection and signal control system
CN103886754A (en) * 2014-03-31 2014-06-25 姜廷顺 System and method for rapidly finding out abnormally-stopped vehicle at signal lamp control intersection
CN103985253A (en) * 2014-05-26 2014-08-13 北京易华录信息技术股份有限公司 System and method for fast finding abnormal stopping in road junction controlled by signal lamp
CN104346927A (en) * 2014-10-30 2015-02-11 无锡悟莘科技有限公司 Things internet-based red light-running vehicle monitoring and shooting system
CN104408928A (en) * 2014-10-28 2015-03-11 合肥指南针电子科技有限责任公司 Whole-process red light running monitoring system and method
CN104408929A (en) * 2014-10-28 2015-03-11 合肥指南针电子科技有限责任公司 Anti-error-shooting red light runner monitoring system and method
CN104658279A (en) * 2015-02-17 2015-05-27 公安部交通管理科学研究所 Real-time optimization signal control method and system based on video traffic state monitoring
CN105632172A (en) * 2015-12-30 2016-06-01 桂林金铱星科技发展有限公司 Detection system for illegal red-light running behavior on road
CN105654750A (en) * 2015-07-15 2016-06-08 宇龙计算机通信科技(深圳)有限公司 Control method and controller
CN111932906A (en) * 2020-08-07 2020-11-13 深圳市深汕特别合作区智慧城市研究院有限公司 Automatic control system of emergency traffic signal lamp linked with multifunctional intelligent rod

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496285B (en) * 2011-12-23 2013-10-02 上海海事大学 Method for determining red-light running of vehicles at intersection based on video detection and signal control system
CN102496285A (en) * 2011-12-23 2012-06-13 上海海事大学 Method for determining red-light running of vehicles at intersection based on video detection and signal control system
CN103886754A (en) * 2014-03-31 2014-06-25 姜廷顺 System and method for rapidly finding out abnormally-stopped vehicle at signal lamp control intersection
CN103985253A (en) * 2014-05-26 2014-08-13 北京易华录信息技术股份有限公司 System and method for fast finding abnormal stopping in road junction controlled by signal lamp
CN103985253B (en) * 2014-05-26 2016-05-25 北京易华录信息技术股份有限公司 The system and method for exception parking in the crossing of a kind of quick discovery signals lamp control
CN104408929B (en) * 2014-10-28 2017-04-19 合肥指南针电子科技有限责任公司 Anti-error-shooting red light runner monitoring system and method
CN104408928A (en) * 2014-10-28 2015-03-11 合肥指南针电子科技有限责任公司 Whole-process red light running monitoring system and method
CN104408929A (en) * 2014-10-28 2015-03-11 合肥指南针电子科技有限责任公司 Anti-error-shooting red light runner monitoring system and method
CN104346927A (en) * 2014-10-30 2015-02-11 无锡悟莘科技有限公司 Things internet-based red light-running vehicle monitoring and shooting system
CN104658279A (en) * 2015-02-17 2015-05-27 公安部交通管理科学研究所 Real-time optimization signal control method and system based on video traffic state monitoring
CN105654750A (en) * 2015-07-15 2016-06-08 宇龙计算机通信科技(深圳)有限公司 Control method and controller
CN105632172A (en) * 2015-12-30 2016-06-01 桂林金铱星科技发展有限公司 Detection system for illegal red-light running behavior on road
CN111932906A (en) * 2020-08-07 2020-11-13 深圳市深汕特别合作区智慧城市研究院有限公司 Automatic control system of emergency traffic signal lamp linked with multifunctional intelligent rod
CN111932906B (en) * 2020-08-07 2021-07-09 深圳市深汕特别合作区智慧城市研究院有限公司 Automatic control system of emergency traffic signal lamp linked with multifunctional intelligent rod

Similar Documents

Publication Publication Date Title
CN102496285B (en) Method for determining red-light running of vehicles at intersection based on video detection and signal control system
CN202422425U (en) Video-detection-based intelligent signal control system for crossing
CN102521983B (en) Vehicle violation detection system based on high definition video technology and method thereof
CN102254429B (en) Video identification-based detection method of detection device of violation vehicles
CN201655024U (en) Junction traffic information comprehensive measurement alarm system
CN100578562C (en) Method for monitoring vehicle offences by video
CN101799987B (en) Self-adaptive intelligent traffic light and control method thereof
CN103065470B (en) Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces
CN101593422B (en) Traffic violation detection method based on video tracking and pattern recognition
CN102768801B (en) Method for detecting motor vehicle green light follow-up traffic violation based on video
CN105427614A (en) Model classification system and method
CN202077142U (en) Vehicle-mounted intelligent video detecting and analyzing system
CN102201165A (en) Monitoring system of vehicle traffic violation at crossing and method thereof
CN101231786A (en) Vehicle checking method based on video image characteristic
CN104658279A (en) Real-time optimization signal control method and system based on video traffic state monitoring
CN102005120A (en) Traffic intersection monitoring technology and system based on video image analysis
CN101964145A (en) Automatic license plate recognition method and system
CN103354029A (en) Multi-functional intersection traffic information collection method
CN104504896A (en) System and method for traffic violation automatic recording
CN104464290A (en) Road traffic parameter collecting and rule violation snapshot system based on embedded double-core chip
CN106485927A (en) A kind of intelligent transportation violation information harvester and acquisition method
CN103646546A (en) An intelligent traffic system with a large-scale vehicle passing-forbidding function
CN103268703A (en) Snapshot system for bus lane
CN105679043A (en) 3D radar intelligent bayonet system and processing method thereof
CN202472943U (en) Vehicle violation detecting system based on high definition video technology

Legal Events

Date Code Title Description
C14 Grant of patent or utility model
GR01 Patent grant
EXPY Termination of patent right or utility model
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20120905

Termination date: 20141223