CN103366568B - Traffic section vehicle queue's video detecting method and system - Google Patents
Traffic section vehicle queue's video detecting method and system Download PDFInfo
- Publication number
- CN103366568B CN103366568B CN201310260168.1A CN201310260168A CN103366568B CN 103366568 B CN103366568 B CN 103366568B CN 201310260168 A CN201310260168 A CN 201310260168A CN 103366568 B CN103366568 B CN 103366568B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- track
- traffic
- queue
- road
- 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
Abstract
The present invention discloses a kind of traffic section vehicle queue's video detecting method and system.The method gathers traffic video by setting up monitoring camera on road, after video decode, by computer vision and image processing techniques, vehicle queue's detection and vehicle Flow Detection is carried out to section need be detected, draw each track vehicle queue physical length and average speed, and by obtain information by network delivery to Control and Schedule module.The method can detect multiple track simultaneously, and can detect that same track exists the situation of multiple queue.The present invention pushes the processing procedure of traffic video signal to terminal device, decreases the transmitted data amount of network, has saved bandwidth, alleviates the pressure of control center to data processing; By detecting each section vehicle queue in city situation, for disperseing the volume of traffic of crowded section of highway, reasonable distribution time of traffic lights, improve the Data support that conevying efficiency provides science.
Description
Technical field
The invention belongs to technical field of intelligent traffic, particularly relate to a kind of traffic section vehicle queue's video detecting method and system.
Background technology
In order to improve the urban traffic conditions increasingly blocked up, alleviate traffic pressure, build comfortable safe outside environment, need by road construction of making rational planning on the one hand, Optimum Path web frame, pay attention to the hardware construction such as road surface maintenance and realize, also need by scientific and effective management on the other hand, the measures such as rational control, scheduling make full use of path resource, improve road utilization rate, ensure the unimpeded of traffic.
Traffic congestion is in city one very distinct issues, and vehicle queue is then a congested in traffic typical performance.In more than ten years in the past, people have carried out large quantifier elimination to vehicle queue, have and adopt simple detection method, also have and adopt complicated theoretical model.China's road network interweaves huge, participates in the varied of the main body of traffic, and motor vehicle, bicycle, pedestrian etc. make the traffic system of China become typical mixed traffic system.Traffic conditions is complicated and changeable, makes some adopt the method for probability model often unsatisfactory in the use procedure of reality, does not reach the Detection results of expection.And adopt the mode installation and maintenance cost of detecting device all larger.
Summary of the invention
Goal of the invention: for above problem, the present invention proposes traffic section vehicle queue's video detecting method and system.
Technical scheme: traffic section vehicle queue video detecting method, comprises the steps,
Step one: the initialization of completion system equipment and major parameter;
Step 2: calculate or read road essential information: if system is initiating switchup, then utilize Man Machine Interface to carry out driveway partition, edge, track is consistent with the actual lane line of road; Determine world coordinates representation, adopt the road video lower left corner to be reference origin, adopt right-handed coordinate system, be ground y-axis positive dirction along road direction, road cross-directional is x-axis; According to video camera imaging principle, derive the transformational relation that pixel coordinate converts world coordinates to; By above-mentioned track marginal information, reference origin world coordinates and the preservation such as pixel coordinate, image transformation relation; If non-initiating switchup, directly reads data;
Step 3: the average speed extracting road traffic and each track;
Step 4: judged whether that track average speed is lower than preset value, if so, carries out road vehicle queuing and detects, otherwise, perform step 5;
Step 5: the vehicle queue's situation obtained by above-mentioned steps and vehicle flowrate data encapsulation are become Frame, is transmitted through the network to traffic control scheduler module.
Traffic section vehicle queue video detection system, comprise monitoring camera equipment, Video decoding module, core processing module, Control and Schedule module, memory module, described monitoring camera equipment is by video flowing after Video decoding module decoding, and input core processing module processes; The result of described core processing module is transmitted through the network to Control and Schedule module; Described core processing module is from memory module access road essential information.
The present invention adopts technique scheme, has following beneficial effect: (1) adopts the camera collection vision signal being easy to installation and maintenance, carries out extra on-the-spot civil construction, economical and effective, safety and environmental protection without the need to suspending traffic; (2) Video processing is pushed to the terminal processing device be arranged on road, the effective information only after transmission process, saves the network bandwidth, alleviates the processing pressure of rear control center computing machine; (3) adopt the real-time detection that described method can realize simultaneously to multilane vehicle queue and information of vehicle flowrate, and can detect that there is the situation of multiple queue in same track; (4) sending Control and Schedule center, rear by existing wireless or cable network to by processing the information obtained, without the need to laying transmission line in addition, facilitating feasible.The information of transmission is the reasonable diffluence realizing traffic, alleviates traffic pressure and plays a role.The Data support of science is provided by the setting that the statistics of busy section road conditions also be can be to traffic lights.
Accompanying drawing explanation
Fig. 1 is vehicle queue's scene schematic diagram of the embodiment of the present invention
Fig. 2 is the system architecture diagram of the embodiment of the present invention;
Fig. 3 is the method flow schematic diagram of the embodiment of the present invention;
Fig. 4 is vehicle queue's detection method process flow diagram of the embodiment of the present invention.
Embodiment
Below in conjunction with specific embodiment, illustrate the present invention further, these embodiments should be understood only be not used in for illustration of the present invention and limit the scope of the invention, after having read the present invention, the amendment of those skilled in the art to the various equivalent form of value of the present invention has all fallen within the application's claims limited range.
Fig. 1 is vehicle queue's schematic diagram of the present embodiment, and wherein 1. label represents stop line, and 2. label represents left-lane, in left-lane, vehicle queue is not from stop line, and in a track, having multiple queuing to exist, 3. label represents right lane, queues up from stop line place.Little rectangle frame in dotted line in figure is the virtual little surveyed area of setting, can think virtual coil.Virtual region length is close to the length of a car, and width is the width in track.Because video exists near big and far smaller problem, the size of virtual region also presents near big and far smaller rule.Each track is split by virtual little surveyed area, vehicle queue's detection is carried out to each virtual zonule, then the virtual detection region existed of queuing up will be had to merge, just can obtain having several queue to exist in the queue length in each track and each track.
It is the module frame chart of the present embodiment shown in Fig. 2.This system comprises monitoring camera equipment, Video decoding module, core processing module, Control and Schedule module, memory module.By being erected at the real-time road video information of monitoring camera equipment collection on road, after Video decoding module decoding, video flowing being inputted core processing module and processes; Core processing module mainly completes vehicle queue and detects and magnitude of traffic flow detection; Needed to calculate or read road information before detection starts, if edge, track and pixel coordinate are to the transformational relation of world coordinates; After extracting queue length and vehicle flowrate, by wired or wireless Internet Transmission to traffic Control and Schedule module, Control and Schedule module can make Rational Decision according to condition of road surface.
Fig. 3 is the process flow diagram of this method.Mainly comprise the following steps:
(1), during system initialization, the initialization of finishing equipment and major parameter, makes it to be in normal operating conditions;
(2) calculate or read road essential information.If system starts first time, then need to utilize Man Machine Interface to carry out driveway partition, edge, track is consistent with the actual lane line of road; Determine world coordinates representation, as adopted the road video lower left corner to be reference origin, adopt right-handed coordinate system, be ground y-axis positive dirction along road direction, road cross-directional is x-axis; According to video camera imaging principle, derive the transformational relation that pixel coordinate converts world coordinates to; By above-mentioned track marginal information, reference origin world coordinates and the preservation such as pixel coordinate, image transformation relation.If not first time is detected, directly data can be read;
(3) average speed in road traffic and each track is extracted according to method for testing motion;
(4) if having the average speed in track lower than certain value, as 5 kilometers per hour, then vehicle queue's detection is carried out.The flow process that vehicle queue is detected is main as shown in Figure 4.According to the actual size of image transformation relation in (1) and a car, determine longitudinal pixel number that a car occupies from road stop line, be laterally as the criterion with lane width, determine the terminal in first virtual detection region; Then with the ending of first virtual region for starting point determines the terminal in second virtual detection region in the same way; The like, determine the virtual detection region in each track; There is detection and Vehicle Moving Detection to carrying out vehicle in each virtual detection region, if virtual detection region exists vehicle and exceedes certain frame number without motion, then thinking that this place exists vehicle queue; The queuing situation in each track can be obtained by detecting each virtual detection region.Likely there is the situation of several queue in a track, does the ending of queuing initial sum judge each queuing in each track; Finally by image transformation relation, calculate actual queue length;
(5) the vehicle queue's situation obtained by above-mentioned steps and vehicle flowrate data encapsulation are become Frame, by existing wired or wireless Internet Transmission to traffic Control and Schedule module.
Core processing module of the present invention can realize on hardware chip, as adopted field programmable gate array (FPGA), digital signal processing chip (DSP) etc.
Claims (3)
1. traffic section vehicle queue video detecting method, is characterized in that, comprise the steps,
Step one: the initialization of completion system equipment and major parameter;
Step 2: calculate or read road essential information: if system is initiating switchup, then utilize Man Machine Interface to carry out driveway partition, edge, track is consistent with the actual lane line of road; Determine world coordinates representation, adopt the road video lower left corner to be reference origin, adopt right-handed coordinate system, be ground y-axis positive dirction along road direction, road cross-directional is x-axis; According to video camera imaging principle, derive the transformational relation that pixel coordinate converts world coordinates to; Above-mentioned track marginal information, reference origin, world coordinates and pixel coordinate and image transformation relation are preserved; If non-initiating switchup, directly reads data;
Step 3: the average speed extracting road traffic and each track;
Step 4: judged whether that track average speed is lower than preset value, if so, carries out road vehicle queuing and detects, then perform step 5, otherwise, directly perform step 5;
Step 5: the vehicle queue's situation obtained by above-mentioned steps and vehicle flowrate data encapsulation are become Frame, is transmitted through the network to traffic control scheduler module;
The road vehicle queuing detection method of described step 4 is: track virtual detection regional assignment; There is detection in vehicle; Vehicle Moving Detection; Actual vehicle is queued up and is judged; Pixel coordinate converts ground coordinate to; Calculate actual queue length;
In described step 4, vehicle queue detects and detects multiple track, detects the situation that same track exists multiple queue simultaneously.
2. traffic section vehicle queue as claimed in claim 1 video detecting method, is characterized in that: in described step 3, extracts the average speed in road traffic and each track according to method for testing motion.
3. traffic section vehicle queue video detection system, comprise monitoring camera equipment, Video decoding module, core processing module, Control and Schedule module and memory module, it is characterized in that: described monitoring camera equipment is by video flowing after Video decoding module decoding, and input core processing module processes; The result of described core processing module is transmitted through the network to Control and Schedule module; Described core processing module is from memory module access road essential information;
Described core processing module is carried out vehicle queue and is detected and magnitude of traffic flow detection; Vehicle queue's detection method is: track virtual detection regional assignment; There is detection in vehicle; Vehicle Moving Detection; Actual vehicle is queued up and is judged; Pixel coordinate converts ground coordinate to; Calculate actual queue length;
Described vehicle queue detects and detects multiple track, detects the situation that same track exists multiple queue simultaneously.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310260168.1A CN103366568B (en) | 2013-06-26 | 2013-06-26 | Traffic section vehicle queue's video detecting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310260168.1A CN103366568B (en) | 2013-06-26 | 2013-06-26 | Traffic section vehicle queue's video detecting method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103366568A CN103366568A (en) | 2013-10-23 |
CN103366568B true CN103366568B (en) | 2015-10-07 |
Family
ID=49367812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310260168.1A Expired - Fee Related CN103366568B (en) | 2013-06-26 | 2013-06-26 | Traffic section vehicle queue's video detecting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103366568B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9922560B2 (en) | 2016-03-14 | 2018-03-20 | International Business Machines Corporation | Interactive camera viewpoint and adjustment sharing system |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103985251B (en) * | 2014-04-21 | 2016-03-02 | 东南大学 | A kind of method and system of vehicle queue length measuring and calculating |
CN106971567A (en) * | 2017-05-18 | 2017-07-21 | 上海博历机械科技有限公司 | A kind of the intensive traffic section vehicle queue video detection system |
CN108629988A (en) * | 2018-05-15 | 2018-10-09 | 青岛永辉光电科技有限公司 | Traffic lights regulate and control method, apparatus and electronic equipment |
CN108922187B (en) * | 2018-07-20 | 2021-09-07 | 上海久揽视讯科技有限公司 | Intelligent transportation system |
CN110365942B (en) * | 2019-07-18 | 2021-08-20 | 北京工业大数据创新中心有限公司 | Real-time video intelligent analysis method and system |
CN111081008B (en) * | 2019-12-06 | 2022-09-23 | 英华达(上海)科技有限公司 | Road marking control method and road marking control system |
CN111814527A (en) * | 2020-01-16 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Urban road occupation construction monitoring method, storage medium, vehicle-mounted terminal and monitoring terminal |
CN111597700B (en) * | 2020-05-09 | 2023-08-15 | 北京百度网讯科技有限公司 | Signal control algorithm evaluation method and device, electronic equipment and readable storage medium |
CN112150811A (en) * | 2020-09-27 | 2020-12-29 | 安徽达尔智能控制系统股份有限公司 | Urban road intersection traffic information acquisition system based on image recognition technology |
CN112907978A (en) * | 2021-03-02 | 2021-06-04 | 江苏集萃深度感知技术研究所有限公司 | Traffic flow monitoring method based on monitoring video |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3816887B2 (en) * | 2002-04-04 | 2006-08-30 | エルエス産電株式会社 | Apparatus and method for measuring length of vehicle queue |
CN201203419Y (en) * | 2007-12-26 | 2009-03-04 | 河海大学常州校区 | Single frame image detection device of city road crossing vehicle queue length |
CN101936730A (en) * | 2010-06-28 | 2011-01-05 | 汉王科技股份有限公司 | Vehicle queue length detection method and device |
CN202373137U (en) * | 2011-12-13 | 2012-08-08 | 长安大学 | Queuing length detection device for vehicles at road crossing |
CN102768804A (en) * | 2012-07-30 | 2012-11-07 | 江苏物联网研究发展中心 | Video-based traffic information acquisition method |
CN102867414A (en) * | 2012-08-18 | 2013-01-09 | 湖南大学 | Vehicle queue length measurement method based on PTZ (Pan/Tilt/Zoom) camera fast calibration |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101104625B1 (en) * | 2010-05-06 | 2012-01-12 | 한국산업기술대학교산학협력단 | Apparatus for yielding traffic information of intelligent transport system and method thereof |
-
2013
- 2013-06-26 CN CN201310260168.1A patent/CN103366568B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3816887B2 (en) * | 2002-04-04 | 2006-08-30 | エルエス産電株式会社 | Apparatus and method for measuring length of vehicle queue |
CN201203419Y (en) * | 2007-12-26 | 2009-03-04 | 河海大学常州校区 | Single frame image detection device of city road crossing vehicle queue length |
CN101936730A (en) * | 2010-06-28 | 2011-01-05 | 汉王科技股份有限公司 | Vehicle queue length detection method and device |
CN202373137U (en) * | 2011-12-13 | 2012-08-08 | 长安大学 | Queuing length detection device for vehicles at road crossing |
CN102768804A (en) * | 2012-07-30 | 2012-11-07 | 江苏物联网研究发展中心 | Video-based traffic information acquisition method |
CN102867414A (en) * | 2012-08-18 | 2013-01-09 | 湖南大学 | Vehicle queue length measurement method based on PTZ (Pan/Tilt/Zoom) camera fast calibration |
Non-Patent Citations (2)
Title |
---|
基于视频分析的车辆排队长度检测;杨永辉;《计算机应用研究》;20110331;第28卷(第3期);第1037-1041页 * |
基于视频图像处理的车辆排队长度检测;贺晓峰;《交通与计算机》;20061128;第24卷(第5期);第43-46页 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9922560B2 (en) | 2016-03-14 | 2018-03-20 | International Business Machines Corporation | Interactive camera viewpoint and adjustment sharing system |
Also Published As
Publication number | Publication date |
---|---|
CN103366568A (en) | 2013-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103366568B (en) | Traffic section vehicle queue's video detecting method and system | |
CN103208191B (en) | The optimization method of signal coordinated control under a kind of urban road intersection supersaturated condition | |
CN103680157B (en) | A kind of vehicle queue's overflow pre-judging method towards city bottleneck road | |
CN106469507A (en) | Dynamic green wave system and method automatically adjusted based on Real-Time Traffic Volume data | |
CN103680129B (en) | A kind of method and system of public transit vehicle operation monitoring | |
CN104299426B (en) | A kind of traffic signal control system and method based on to pedestrian detection counting statistics | |
CN103236164B (en) | Vehicle controlling method for guaranteeing public transport vehicle prior passing | |
CN102982678A (en) | Traffic data information service system and method for realizing traffic data information service | |
CN106448193A (en) | Urban traffic control system and method | |
CN104332058A (en) | Intelligent traffic light controlling method and system | |
CN109389836A (en) | Control method, device, system and the controller of traffic lights | |
WO2020244624A1 (en) | Method and device for calculating duration when green light is given to empty road at intersection | |
CN108922205A (en) | The traffic lights switching time control system and method for level-crossing congestion situation | |
CN202694581U (en) | Intelligent traffic control system | |
CN204204198U (en) | Based on the traffic hazard detection system that multi-cam real-time linkage is followed the tracks of | |
CN104700632B (en) | Intelligent traffic light control method and its system | |
CN103345840A (en) | Video detection method of road crossing event at cross road | |
CN105844925B (en) | Urban traffic control device, system and method based on mobile phone wireless net | |
CN206147948U (en) | Urban traffic control system | |
CN106781554A (en) | Intelligent traffic signal control system | |
CN106530695A (en) | Urban trunk road vehicle travel time real-time prediction method based on Internet of vehicles | |
CN107705590B (en) | Intelligent phase control method and system for tramcar passing intersection | |
CN205670385U (en) | Urban traffic control device based on mobile phone wireless net | |
CN104575020A (en) | Dynamic timing method for mobile traffic lamp based on RFID (Radio Frequency Identification Device) information acquisition | |
CN111968363A (en) | Zebra crossing present pedestrian detection system based on vehicle-road cooperation |
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: 20151007 Termination date: 20190626 |