CN105513342A - Video-tracking-based vehicle queuing length calculating method - Google Patents
Video-tracking-based vehicle queuing length calculating method Download PDFInfo
- Publication number
- CN105513342A CN105513342A CN201510831555.5A CN201510831555A CN105513342A CN 105513342 A CN105513342 A CN 105513342A CN 201510831555 A CN201510831555 A CN 201510831555A CN 105513342 A CN105513342 A CN 105513342A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- queuing
- video
- queue
- tracking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
Disclosed in the invention is a video-tracking-based vehicle queuing length calculating method. On the basis of a video tracking result, a moving or stopping state of a vehicle on a road is analyzed effectively and a road traffic state is determined; and whether a queue congestion state occurs is determined. According to a vehicle tracking path, whether a same vehicle stops at a parking line position is determined in real time; if a parking queue occurs, a moving track of a tacked vehicle on the road is analyzed and the queue length is determined. Therefore, accurate road traffic vehicle queue length information can be obtained and thus a basis is provided for analyzing and managing the road traffic scientifically.
Description
Technical field
The present invention relates to intelligent transportation field, especially a kind of computing method of vehicle queue length.
Background technology
Along with city size expands, motor vehicles increase fast, and congestion in road has become seriously " big city is sick ".By detecting real-time road traffic information, scientific analysis, management urban traffic road significantly can alleviate the difficult problems such as congestion in road.Accurate acquisition, analyze that road vehicles queue length is the effective means of scientific analysis to road traffic road conditions and management.Vehicle queue length detection method at present based on video mainly contains: the vehicle queue length based on sciagraphy detects, detect based on the vehicle queue length of edge segmentation.
Based on the method that the vehicle queue length of sciagraphy detects, be the brightness of surveyed area projected on road direction, according to the difference of bright (vehicle), dark (road) classification, computed segmentation threshold value, extracts queuing vehicle length.The method is easily subject to natural scene impact, and threshold value is not fixed.Adaptive threshold method is also difficult effectively to be judged vehicle tail of the queue.
Based on the method that the vehicle queue length of edge segmentation detects, be utilize the difference between queuing vehicle and road background, the especially significant difference characteristic of both junctions, extracts a kind of method of object edge.From scene, be partitioned into queuing vehicle by object edge, calculate queue length.The method is subject to the very large and queuing vehicle afterbody difficulty of roadside architectural shadow impact and determines.
In vehicle queue's video analysis of reality, said method is unstable, and accuracy rate is low.Therefore, need a kind of new technical scheme to solve the problems of the technologies described above.
Summary of the invention
The object of the invention is to obtain road vehicles queue length information more accurately, in different application scene, moving vehicle in real-time follow-up surveyed area, accurately calculates vehicle queue length, judge road traffic condition, effectively analyze and management road traffic.
For achieving the above object, the present invention can adopt following technical scheme:
Based on vehicle queue length computing method for video tracking, comprise the following steps:
(1), video sensing area is set, this video sensing area comprises the stop line of detection line and the other end being positioned at one end, video sensing area, vehicle detection region that Autonomous test alignment stop line direction sets gradually, vehicle tracking region, parking queuing judging area; The end of described parking queuing judging area is set to stop line; And detect video camera by the video of fixing visual field, the vehicle entering video sensing area is carried out to real time video collection and is transferred to graphics processing unit;
(2), the moving vehicle entering video sensing area is detected, is determined the attribute of moving vehicle; Described attribute comprises vehicle, color, current location;
(3), real time tracking motion vehicle, record moving vehicle movement locus;
(4), the generation of queuing up of stopping is judged whether to the vehicle entering parking queuing surveyed area;
(5), when road occurs to stop queuing, analyze the movement locus of the tracked vehicle of tracing area, determine queuing afterbody, calculate queuing vehicle length in the picture.
Compared with prior art, the present invention utilizes video tracking result, effectively analyzes road vehicles motion or halted state, determines road traffic state, judges whether that queuing occurs blocks up.According to vehicle tracking track, whether real-time judge stop line position has same car to stop, and stops and queues up, analyze the tracked vehicle movement track of road, determine queue length if having.Thus the information of road vehicles queue length accurately can be obtained, for scientific analysis and management road traffic provide foundation.
Accompanying drawing explanation
Fig. 1 is the overview flow chart of this method;
Fig. 2 is the vehicle queue length calculation flow chart based on video tracking.
Fig. 3 is the layout exemplary plot of this method in real road traffic application.
Embodiment
Below in conjunction with accompanying drawing, embodiments of the present invention are elaborated comprehensively, the embodiment that describes only exemplarily illustrate, be not limitation of the present invention.The video processing module that specific embodiment of the invention needs some common, as pre-service, background modeling, no longer elaborates here.The present invention is applicable in urban road traffic information detection system.The road vehicle data queued information obtained can be sent to traffic signal controlling machine and carry out road optimal control, also can be sent to traffic information collection centring system, for scientific analysis, management road traffic provide and can continue foundation.
First as shown in Figure 3, need to arrange video sensing area, this video sensing area comprise the stop line of detection line and the other end being positioned at one end, video sensing area, vehicle detection region that Autonomous test alignment stop line direction sets gradually, vehicle tracking region, parking queuing judging area; The end of described parking queuing judging area is set to stop line.
On the basis that video sensing area is set, shown in Fig. 1, be the process flow diagram according to the vehicle queue length detection method based on video tracking of the present invention, comprise:
Video acquisition, in 101, detects video camera by the video of fixing visual field, the vehicle entering video sensing area is carried out to real time video collection and is transferred to graphics processing unit;
Vehicle detection, in 102, detects to the moving vehicle entering video sensing area, determines the attribute of moving vehicle; Described attribute comprises vehicle, color, current location; Think vehicle tracking service;
Vehicle tracking, in 103, real time tracking motion vehicle, the movement locus of record moving vehicle;
Queue up and judge, in 104, the generation of queuing up of stopping is judged whether to the vehicle entering parking queuing surveyed area;
Statistical queue length, in 105, when road occurs to stop queuing, analyzes the movement locus of the tracked vehicle of tracing area, determines queuing afterbody, calculate queuing vehicle length in the picture
Please again shown in composition graphs 2, according to vehicle queue length calculation process 5 steps based on video tracking of the present invention.Comprise:
The first step, in 201, to the vehicle analysis in parking queuing surveyed area, if there be same car (vehicle tracking result) long-time (arranging threshold value) to stop, road occurs to stop and queues up, otherwise does not have.
Second, in 202, between before and after tracked vehicle, position coordinates is less than certain threshold value (according to actual set), and this vehicle commander's time not large distance (setting threshold value) is mobile, determines that this car is queued up.
3rd step, in 203, from stop line, successively to the tracked vehicle of post analysis, by current vehicle position coordinate and the attribute of moving displacement and time, judge this car whether in queue queue, until last car satisfied condition, obtain queuing tail of the queue coordinate.
4th step, in 204, with queue length (pixel is unit) in stop line coordinate and queuing tail of the queue coordinate computed image, by the mapping relations of camera model, is converted into actual queue length (in units of rice) by this length.
5th step, in 205, will obtain road parking queue length timed sending to traffic signaling equipment or control center, by the scientific analysis to queue length, decision-making and management road traffic, to reach optimum state.
In addition, a lot, the above is only the preferred embodiment of the present invention for concrete methods of realizing of the present invention and approach.It should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.The all available prior art of each ingredient not clear and definite in the present embodiment is realized.
Claims (3)
1., based on vehicle queue length computing method for video tracking, it is characterized in that, comprise the following steps:
(1), video sensing area is set, this video sensing area comprises the stop line of detection line and the other end being positioned at one end, video sensing area, vehicle detection region that Autonomous test alignment stop line direction sets gradually, vehicle tracking region, parking queuing judging area; The end of described parking queuing judging area is set to stop line; And detect video camera by the video of fixing visual field, the vehicle entering video sensing area is carried out to real time video collection and is transferred to graphics processing unit;
(2), the moving vehicle entering video sensing area is detected, is determined the attribute of moving vehicle; Described attribute comprises vehicle, color, current location;
(3), real time tracking motion vehicle, record moving vehicle movement locus;
(4), the generation of queuing up of stopping is judged whether to the vehicle entering parking queuing surveyed area;
(5), when road occurs to stop queuing, analyze the movement locus of the tracked vehicle of tracing area, determine queuing afterbody, calculate queuing vehicle length in the picture.
2. the vehicle queue length computing method based on video tracking according to claim 1, it is characterized in that: in step (4), be arranged on threshold value down time of parking queuing judging area, to the vehicle analysis in parking queuing judging area, if the down time having same car excess parking period threshold value to arrange, be then judged as that then road occurs to stop and queue up.
3. the vehicle queue length computing method based on video tracking according to claim 2, it is characterized in that: in step (5), distance threshold between adjacent two vehicles in front and back being arranged on parking queuing judging area, between before and after tracked vehicle, the spacing of position coordinates is less than this distance threshold certain, and this car is not moved beyond described distance threshold within the time of above-mentioned threshold value setting down time, is judged as that this car is queued up; And from stop line, judge tracked vehicle successively whether in queue queue, until meet last car of queue conditions, obtain queuing tail of the queue coordinate; Distance between stop line coordinate and queuing tail of the queue coordinate is queue length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510831555.5A CN105513342A (en) | 2015-11-25 | 2015-11-25 | Video-tracking-based vehicle queuing length calculating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510831555.5A CN105513342A (en) | 2015-11-25 | 2015-11-25 | Video-tracking-based vehicle queuing length calculating method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105513342A true CN105513342A (en) | 2016-04-20 |
Family
ID=55721288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510831555.5A Pending CN105513342A (en) | 2015-11-25 | 2015-11-25 | Video-tracking-based vehicle queuing length calculating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105513342A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781542A (en) * | 2016-12-30 | 2017-05-31 | 迈锐数据（北京）有限公司 | A kind of vehicle queue length detecting system, method and apparatus |
| CN106781493A (en) * | 2016-12-30 | 2017-05-31 | 迈锐数据（北京）有限公司 | A kind of vehicle queue length simulation system, method and apparatus |
| CN107644529A (en) * | 2017-08-03 | 2018-01-30 | 浙江浩腾电子科技股份有限公司 | A kind of vehicle queue length detection method based on motion detection |
| CN107644528A (en) * | 2017-08-02 | 2018-01-30 | 浙江工业大学 | A kind of vehicle queue length detection method based on vehicle tracking |
| CN109050916A (en) * | 2018-08-30 | 2018-12-21 | 深圳市研本品牌设计有限公司 | A kind of cruise unmanned plane and storage medium |
| CN109087515A (en) * | 2018-08-30 | 2018-12-25 | 深圳市研本品牌设计有限公司 | Unmanned plane expressway road conditions cruise method and system |
| CN109409264A (en) * | 2018-10-12 | 2019-03-01 | 浙江浙大中控信息技术有限公司 | Overflow detection method is lined up based on the video locally tracked |
| CN109544915A (en) * | 2018-11-09 | 2019-03-29 | 同济大学 | A kind of queue length distribution estimation method based on sample path data |
| CN110287905A (en) * | 2019-06-27 | 2019-09-27 | 浙江工业大学 | A kind of traffic congestion region real-time detection method based on deep learning |
| CN112509315A (en) * | 2020-11-04 | 2021-03-16 | 杭州远眺科技有限公司 | Traffic accident detection method based on video analysis |
| CN113129595A (en) * | 2021-04-23 | 2021-07-16 | 济南金宇公路产业发展有限公司 | Traffic signal control method, equipment and medium for road intersection |
| CN113435483A (en) * | 2021-06-10 | 2021-09-24 | 宁波帅特龙集团有限公司 | Fixed-point snapshot method and system |
| CN116819483A (en) * | 2023-08-28 | 2023-09-29 | 南京隼眼电子科技有限公司 | Intersection vehicle queuing length detection method and device, storage medium and terminal |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070127774A1 (en) * | 2005-06-24 | 2007-06-07 | Objectvideo, Inc. | Target detection and tracking from video streams |
| CN101470955A (en) * | 2007-12-26 | 2009-07-01 | 奥城同立科技开发（北京）有限公司 | Integrated control system for road junction traffic |
| JP2012190249A (en) * | 2011-03-10 | 2012-10-04 | Sumitomo Electric Ind Ltd | Traffic index calculation device, traffic index calculation method, and traffic index calculation program |
| CN103383816A (en) * | 2013-07-01 | 2013-11-06 | 青岛海信网络科技股份有限公司 | Method and device for controlling traffic signals of multipurpose electronic police mixed traffic flow detection |
| CN103456170A (en) * | 2013-04-22 | 2013-12-18 | 天津工业大学 | Vehicle speed and vehicle queue length detection method based on machine vision |
| CN103903445A (en) * | 2014-04-22 | 2014-07-02 | 北京邮电大学 | Vehicle queuing length detection method and system based on video |
| CN104361753A (en) * | 2014-11-26 | 2015-02-18 | 浙江宇视科技有限公司 | Method and device for obtaining evidences of rule and regulation breaking of vehicles not running in alternating mode |
| CN105046954A (en) * | 2015-06-18 | 2015-11-11 | 无锡华通智能交通技术开发有限公司 | Crossing-traffic-state dynamic detection system based on video intelligence analysis and method thereof |
-
2015
- 2015-11-25 CN CN201510831555.5A patent/CN105513342A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070127774A1 (en) * | 2005-06-24 | 2007-06-07 | Objectvideo, Inc. | Target detection and tracking from video streams |
| CN101470955A (en) * | 2007-12-26 | 2009-07-01 | 奥城同立科技开发（北京）有限公司 | Integrated control system for road junction traffic |
| JP2012190249A (en) * | 2011-03-10 | 2012-10-04 | Sumitomo Electric Ind Ltd | Traffic index calculation device, traffic index calculation method, and traffic index calculation program |
| CN103456170A (en) * | 2013-04-22 | 2013-12-18 | 天津工业大学 | Vehicle speed and vehicle queue length detection method based on machine vision |
| CN103383816A (en) * | 2013-07-01 | 2013-11-06 | 青岛海信网络科技股份有限公司 | Method and device for controlling traffic signals of multipurpose electronic police mixed traffic flow detection |
| CN103903445A (en) * | 2014-04-22 | 2014-07-02 | 北京邮电大学 | Vehicle queuing length detection method and system based on video |
| CN104361753A (en) * | 2014-11-26 | 2015-02-18 | 浙江宇视科技有限公司 | Method and device for obtaining evidences of rule and regulation breaking of vehicles not running in alternating mode |
| CN105046954A (en) * | 2015-06-18 | 2015-11-11 | 无锡华通智能交通技术开发有限公司 | Crossing-traffic-state dynamic detection system based on video intelligence analysis and method thereof |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781542B (en) * | 2016-12-30 | 2020-01-31 | 迈锐数据（北京）有限公司 | vehicle queuing length detection system, method and device |
| CN106781493A (en) * | 2016-12-30 | 2017-05-31 | 迈锐数据（北京）有限公司 | A kind of vehicle queue length simulation system, method and apparatus |
| CN106781493B (en) * | 2016-12-30 | 2020-09-18 | 迈锐数据（北京）有限公司 | Vehicle queuing length simulation system, method and device |
| CN106781542A (en) * | 2016-12-30 | 2017-05-31 | 迈锐数据（北京）有限公司 | A kind of vehicle queue length detecting system, method and apparatus |
| CN107644528A (en) * | 2017-08-02 | 2018-01-30 | 浙江工业大学 | A kind of vehicle queue length detection method based on vehicle tracking |
| CN107644529A (en) * | 2017-08-03 | 2018-01-30 | 浙江浩腾电子科技股份有限公司 | A kind of vehicle queue length detection method based on motion detection |
| CN109087515A (en) * | 2018-08-30 | 2018-12-25 | 深圳市研本品牌设计有限公司 | Unmanned plane expressway road conditions cruise method and system |
| CN109050916A (en) * | 2018-08-30 | 2018-12-21 | 深圳市研本品牌设计有限公司 | A kind of cruise unmanned plane and storage medium |
| CN109409264B (en) * | 2018-10-12 | 2022-04-22 | 浙江中控信息产业股份有限公司 | Video queuing overflow detection method based on local tracking |
| CN109409264A (en) * | 2018-10-12 | 2019-03-01 | 浙江浙大中控信息技术有限公司 | Overflow detection method is lined up based on the video locally tracked |
| CN109544915A (en) * | 2018-11-09 | 2019-03-29 | 同济大学 | A kind of queue length distribution estimation method based on sample path data |
| CN110287905A (en) * | 2019-06-27 | 2019-09-27 | 浙江工业大学 | A kind of traffic congestion region real-time detection method based on deep learning |
| CN110287905B (en) * | 2019-06-27 | 2021-08-03 | 浙江工业大学 | Deep learning-based real-time traffic jam area detection method |
| CN112509315A (en) * | 2020-11-04 | 2021-03-16 | 杭州远眺科技有限公司 | Traffic accident detection method based on video analysis |
| CN112509315B (en) * | 2020-11-04 | 2022-02-15 | 杭州远眺科技有限公司 | Traffic accident detection method based on video analysis |
| CN113129595A (en) * | 2021-04-23 | 2021-07-16 | 济南金宇公路产业发展有限公司 | Traffic signal control method, equipment and medium for road intersection |
| CN113129595B (en) * | 2021-04-23 | 2022-06-10 | 山东金宇信息科技集团有限公司 | Traffic signal control method, equipment and medium for road intersection |
| CN113435483A (en) * | 2021-06-10 | 2021-09-24 | 宁波帅特龙集团有限公司 | Fixed-point snapshot method and system |
| CN116819483A (en) * | 2023-08-28 | 2023-09-29 | 南京隼眼电子科技有限公司 | Intersection vehicle queuing length detection method and device, storage medium and terminal |
| CN116819483B (en) * | 2023-08-28 | 2023-11-14 | 南京隼眼电子科技有限公司 | Intersection vehicle queuing length detection method and device, storage medium and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105513342A (en) | Video-tracking-based vehicle queuing length calculating method | |
| CN103021186B (en) | Vehicle monitoring method and vehicle monitoring system | |
| Song et al. | Vehicle behavior analysis using target motion trajectories | |
| KR20210038852A (en) | Method, apparatus, electronic device, computer readable storage medium and computer program for early-warning | |
| CN108776974B (en) | A kind of real-time modeling method method suitable for public transport scene | |
| US9877011B2 (en) | Image display apparatus and image display method | |
| CN105513349A (en) | Double-perspective learning-based mountainous area highway vehicle event detection method | |
| CN103208190B (en) | Traffic flow detection method based on object detection | |
| CN113822285A (en) | Vehicle illegal parking identification method for complex application scene | |
| CN108154146A (en) | A kind of car tracing method based on image identification | |
| CN102426785A (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
| CN107038411A (en) | A kind of Roadside Parking behavior precise recognition method based on vehicle movement track in video | |
| CN107705577B (en) | Real-time detection method and system for calibrating illegal lane change of vehicle based on lane line | |
| US20220237919A1 (en) | Method, Apparatus, and Computing Device for Lane Recognition | |
| CN103646254A (en) | High-density pedestrian detection method | |
| CN114781479A (en) | Traffic incident detection method and device | |
| CN106327880A (en) | Vehicle speed identification method and system based on monitored video | |
| CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
| CN110648538B (en) | Traffic information sensing system and method based on laser radar network | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| Dinh et al. | Development of a tracking-based system for automated traffic data collection for roundabouts | |
| CN105069407B (en) | A kind of magnitude of traffic flow acquisition methods based on video | |
| Abdagic et al. | Counting traffic using optical flow algorithm on video footage of a complex crossroad | |
| CN116563801A (en) | Traffic accident detection method, device, electronic equipment and medium | |
| CN103606280B (en) | A kind of information identifying method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160420 |