CN107038870A - A kind of vehicle peccancy detection method - Google Patents
A kind of vehicle peccancy detection method Download PDFInfo
- Publication number
- CN107038870A CN107038870A CN201710328121.2A CN201710328121A CN107038870A CN 107038870 A CN107038870 A CN 107038870A CN 201710328121 A CN201710328121 A CN 201710328121A CN 107038870 A CN107038870 A CN 107038870A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- prospect
- area
- target
- 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.)
- Withdrawn
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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of vehicle peccancy detection method, each road video flowing is obtained first, clicks on video amplifier display window all the way；According to real road graticule manual drawing straightway and specified different road areas in the video window of amplification, system automatically determines the expression formula of each line segment, obtains the sign sequence in each road area；Background modeling and renewal are carried out using gauss hybrid models；Present frame is compared with background model, foreground image is obtained；Foreground image is pre-processed, wherein noise is eliminated and then obtains cleaner prospect, binaryzation then is carried out to prospect；The center of gravity and area of each target in calculating prospect, if area is more than defined threshold value, target discrimination is vehicle；Obtain the driving trace of target vehicle；According to the sign sequence variation of the driving trace of vehicle and different road areas, and combine whether the actual conditions of Current traffic signal lamp are broken rules and regulations using judgment rule judgement Current vehicle.
Description
Technical field
Present invention relates particularly to a kind of vehicle peccancy detection method.
Background technology
In intelligent transportation system, Video Supervision Technique is widely applied.At present, the focus of people's research is concentrated on
In terms of detection, identification, tracking, traffic statistics, traffic dispersion and the peccancy detection of vehicle.Break in traffic rules and regulations is that occur traffic accident
Root, common form violating the regulations is made a dash across the red light, solid line lane change, reverse driving etc..The premise for detecting vehicle peccancy is exactly
Detect vehicle and track its driving trace.
People make use of many schemes to realize traffic data collection, event detection, candid photograph violating the regulations and vehicles peccancy number plate
Identification.In vehicle peccancy context of detection, people mainly judge whether vehicle is disobeyed using the relation of vehicle driving trace and lane line
Chapter, the research of this respect has：There is document to propose moving vehicles detection and tracking algorithm for complicated urban road crossing monitors environment,
In terms of judging red light violation, mainly by capturing before stop line, go up, rear 3 process pictures, then progress manual sorting's figure
Piece judges to break rules and regulations；There is solid line violating the regulations lane change of the document only to vehicle to carry out detection research, its main method is by tracking
Track of vehicle and current location, with reference to its with it is initial belonging to track whether unanimously determine whether act of violating regulations, analyze
6 kinds of lane change situations violating the regulations, but lane change violating the regulations is not finely divided；There is document by setting up the Hidden Markov of crossroad
Model is classified to violation event, judges the order of severity of traffic accident；There is document to propose a kind of running red light for vehicle detection
With recognizer, i.e., in the detection window near stop line, using the position relationship between vehicle and stop line, in conjunction with letter
The virtual condition of signal lamp, to judge whether vehicle has red light violation behavior, if violating the regulations, is captured, it is clear that this article side
Method has larger limitation, for example, can not provide the position relationship between vehicle and different road areas, not yet considers various letters
The unified approach of peccancy detection under signal lamp state.
The studies above is not all analyzed different road areas, particular without by the position between different zones
Relation, track of vehicle and specific signal lamp are combined, it is impossible to road area where when providing vehicle peccancy and violated
The information such as specific traffic rules.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of vehicle peccancy detection method.
A kind of vehicle peccancy detection method, comprises the following steps：
S1：Each road video flowing is obtained, video amplifier display window all the way is clicked on；
S2：According to real road graticule manual drawing straightway and specified different road areas in the video window of amplification,
System automatically determines the expression formula of each line segment, obtains the sign sequence in each road area；
S3：Background modeling and renewal are carried out using gauss hybrid models；
S4：Present frame is compared with background model, foreground image is obtained；
S5：Foreground image is pre-processed, including the operation such as medium filtering, expansion and corrosion, eliminate and wherein noise and then obtain
Clean prospect must be compared, binaryzation then is carried out to prospect；
S6：The center of gravity and area of each target in calculating prospect, if area is more than defined threshold value, target discrimination is vehicle；
S7：Obtain the driving trace of target vehicle；
S8：According to the sign sequence variation of the driving trace of vehicle and different road areas, and combine Current traffic signal lamp
Actual conditions using judgment rule judge Current vehicle whether break rules and regulations；
S9：Repeat step S3 to step S8, until video terminates.
The beneficial effects of the invention are as follows：
Position relationship between different zones of the present invention according to described by vehicle driving trace and Implicit Curves race, can be quick
The traffic rules that whether vehicle is violating the regulations and violated are judged exactly, drastically increase detection efficiency, and then improve separated
The accuracy that chapter judges.
Embodiment
The present invention is further elaborated for specific examples below, but not as a limitation of the invention.
A kind of vehicle peccancy detection method, comprises the following steps：
S1：Each road video flowing is obtained, video amplifier display window all the way is clicked on；
S2：According to real road graticule manual drawing straightway and specified different road areas in the video window of amplification,
System automatically determines the expression formula of each line segment, obtains the sign sequence in each road area；
S3：Background modeling and renewal are carried out using gauss hybrid models；
S4：Present frame is compared with background model, foreground image is obtained；
S5：Foreground image is pre-processed, including the operation such as medium filtering, expansion and corrosion, eliminate and wherein noise and then obtain
Clean prospect must be compared, binaryzation then is carried out to prospect；
S6：The center of gravity and area of each target in calculating prospect, if area is more than defined threshold value, target discrimination is vehicle；
S7：Obtain the driving trace of target vehicle；
S8：According to the sign sequence variation of the driving trace of vehicle and different road areas, and combine Current traffic signal lamp
Actual conditions using judgment rule judge Current vehicle whether break rules and regulations；
S9：Repeat step S3 to step S8, until video terminates.
Claims (1)
1. a kind of vehicle peccancy detection method, it is characterised in that comprise the following steps：
S1：Each road video flowing is obtained, video amplifier display window all the way is clicked on；
S2：According to real road graticule manual drawing straightway and specified different road areas in the video window of amplification,
System automatically determines the expression formula of each line segment, obtains the sign sequence in each road area；
S3：Background modeling and renewal are carried out using gauss hybrid models；
S4：Present frame is compared with background model, foreground image is obtained；
S5：Foreground image is pre-processed, including the operation such as medium filtering, expansion and corrosion, eliminate and wherein noise and then obtain
Clean prospect must be compared, binaryzation then is carried out to prospect；
S6：The center of gravity and area of each target in calculating prospect, if area is more than defined threshold value, target discrimination is vehicle；
S7：Obtain the driving trace of target vehicle；
S8：According to the sign sequence variation of the driving trace of vehicle and different road areas, and combine Current traffic signal lamp
Actual conditions using judgment rule judge Current vehicle whether break rules and regulations；
S9：Repeat step S3 to step S8, until video terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710328121.2A CN107038870A (en) | 2017-05-11 | 2017-05-11 | A kind of vehicle peccancy detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710328121.2A CN107038870A (en) | 2017-05-11 | 2017-05-11 | A kind of vehicle peccancy detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107038870A true CN107038870A (en) | 2017-08-11 |
Family
ID=59537522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710328121.2A Withdrawn CN107038870A (en) | 2017-05-11 | 2017-05-11 | A kind of vehicle peccancy detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107038870A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033929A (en) * | 2018-02-05 | 2018-12-18 | 杨明 | A method of investigating and prosecuting minor's dangerous driving behavior |
| CN113269042A (en) * | 2021-04-25 | 2021-08-17 | 安徽银徽科技有限公司 | Intelligent traffic management method and system based on running vehicle violation identification |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1912950A (en) * | 2006-08-25 | 2007-02-14 | 浙江工业大学 | Device for monitoring vehicle breaking regulation based on all-position visual sensor |
| CN101183427A (en) * | 2007-12-05 | 2008-05-21 | 浙江工业大学 | Computer vision based peccancy parking detector |
| KR101182173B1 (en) * | 2012-02-07 | 2012-09-12 | 김진호 | Method and system for recognizing vehicle plate |
| KR20160120453A (en) * | 2015-04-08 | 2016-10-18 | 주식회사 나르테크놀로지 | A vehicle-mounted user authentication system through robust finger blood vessel pattern recognition in surrounding environmental conditions and the method thereof |
-
2017
- 2017-05-11 CN CN201710328121.2A patent/CN107038870A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1912950A (en) * | 2006-08-25 | 2007-02-14 | 浙江工业大学 | Device for monitoring vehicle breaking regulation based on all-position visual sensor |
| CN101183427A (en) * | 2007-12-05 | 2008-05-21 | 浙江工业大学 | Computer vision based peccancy parking detector |
| KR101182173B1 (en) * | 2012-02-07 | 2012-09-12 | 김진호 | Method and system for recognizing vehicle plate |
| KR20160120453A (en) * | 2015-04-08 | 2016-10-18 | 주식회사 나르테크놀로지 | A vehicle-mounted user authentication system through robust finger blood vessel pattern recognition in surrounding environmental conditions and the method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 马丽文 等: ""一种利用隐式曲线族的车辆违章检测算法"", 《西安电子科技大学学报（自然科学版）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033929A (en) * | 2018-02-05 | 2018-12-18 | 杨明 | A method of investigating and prosecuting minor's dangerous driving behavior |
| CN109033929B (en) * | 2018-02-05 | 2019-05-17 | 陈小青 | A method of investigating and prosecuting minor's dangerous driving behavior |
| CN113269042A (en) * | 2021-04-25 | 2021-08-17 | 安徽银徽科技有限公司 | Intelligent traffic management method and system based on running vehicle violation identification |
| CN113269042B (en) * | 2021-04-25 | 2024-03-29 | 安徽银徽科技有限公司 | Intelligent traffic management method and system based on driving vehicle violation identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104008645B (en) | One is applicable to the prediction of urban road lane line and method for early warning | |
| CN102521983B (en) | Vehicle violation detection system based on high definition video technology and method thereof | |
| CN111815959B (en) | Vehicle violation detection method and device and computer readable storage medium | |
| CN109191830B (en) | Road congestion detection method based on video image processing | |
| CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
| CN103258429B (en) | Video detecting method aims at vehicles which enter into jammed intersection by force | |
| CN110930723B (en) | Illegal parking detection implementation method | |
| CN105931467B (en) | A kind of method and device tracking target | |
| CN104992145A (en) | Moment sampling lane tracking detection method | |
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| CN111126171A (en) | Vehicle reverse running detection method and system | |
| Li et al. | Road traffic anomaly detection based on fuzzy theory | |
| CN111597905B (en) | Highway tunnel parking detection method based on video technology | |
| CN110287905A (en) | A kind of traffic congestion region real-time detection method based on deep learning | |
| CN103366571A (en) | Intelligent method for detecting traffic accident at night | |
| CN101984478A (en) | Abnormal S-type driving warning method based on binocular vision lane marking detection | |
| CN102568206A (en) | Video monitoring-based method for detecting cars parking against regulations | |
| CN110688922A (en) | Deep learning-based traffic jam detection system and detection method | |
| CN104809470B (en) | A kind of vehicle based on SVM drives in the wrong direction detection device and detection method | |
| CN105654073A (en) | Automatic speed control method based on visual detection | |
| WO2022213542A1 (en) | Method and system for clearing information-controlled intersection on basis of lidar and trajectory prediction | |
| CN103164958B (en) | Method and system for vehicle monitoring | |
| CN109523787A (en) | A kind of fatigue driving analysis method based on vehicle pass-through track | |
| CN202422420U (en) | Illegal parking detection system based on video monitoring | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170811 |