CN108230667A - A kind of vehicle peccancy behavioral value method - Google Patents

A kind of vehicle peccancy behavioral value method Download PDF

Info

Publication number
CN108230667A
CN108230667A CN201611154230.9A CN201611154230A CN108230667A CN 108230667 A CN108230667 A CN 108230667A CN 201611154230 A CN201611154230 A CN 201611154230A CN 108230667 A CN108230667 A CN 108230667A
Authority
CN
China
Prior art keywords
vehicle
frame
peccancy
difference
image
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Withdrawn
Application number
CN201611154230.9A
Other languages
Chinese (zh)
Inventor
不公告发明人
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.)
Guigang Ruicheng Technology Co Ltd
Original Assignee
Guigang Ruicheng Technology Co Ltd
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 Guigang Ruicheng Technology Co Ltd filed Critical Guigang Ruicheng Technology Co Ltd
Priority to CN201611154230.9A priority Critical patent/CN108230667A/en
Publication of CN108230667A publication Critical patent/CN108230667A/en
Withdrawn legal-status Critical Current

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
    • 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
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • 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

Abstract

The invention discloses a kind of vehicle peccancy behavioral value methods, include the following steps：S1：Traffic Surveillance Video acquires, and video is pre-processed；S2：Using Surendra backgrounds difference is improved vehicle target detection is carried out with the algorithm that three-frame difference is combined；S3：Vehicle target tracking is carried out with reference to camShi ft algorithms and Kalman filter；S4：It extracts vehicle centroid and draws vehicle movement track；S5：Vehicle peccancy behavior is differentiated according to vehicle movement track.Vehicle peccancy behavioral value method proposed by the present invention is by carrying out monitor video data processing in real time and analysis, realize the automatic identification of vehicles peccancy behavior, under the premise of result accuracy is ensured, computation complexity is reduced, realizes the real-time detection to vehicle peccancy behavior.

Description

A kind of vehicle peccancy behavioral value method
Technical field
The present invention relates to a kind of vehicle peccancy behavioral value methods.
Background technology
With the rapid economic development in our country, national car ownership rises every year, automobile brings pole for people's lives Convenience, but traffic accident caused by vehicle peccancy violation is multiple, and huge pressure is brought to national traffic management information system Power.To ensure the normal operation of highway communication, the Chinese government employs intelligent transportation system, to realize a wide range of, more scenes Traffic monitoring and management, promote traffic system comprehensive transport ability.Simultaneously against the fast development of information technology decades, magnanimity The storage of video data has obtained widely universal and application with processing.
Current related field has been carried out widely studying, it is proposed that the detection method of many breaks in traffic rules and regulations, but these Method has the problems such as calculating complexity, required memory capacity is excessive, can occupy excessive hardware cost and expense.
Invention content
The technical problem to be solved in the present invention is to provide a kind of vehicle peccancy behavioral value methods.
A kind of vehicle peccancy behavioral value method, includes the following steps：
S1：Traffic Surveillance Video acquires, and video is pre-processed；
S2：Using Surendra backgrounds difference is improved vehicle target detection is carried out with the algorithm that three-frame difference is combined；
S3：Vehicle target tracking is carried out with reference to camShift algorithms and Kalman filter；
S4：It extracts vehicle centroid and draws vehicle movement track；
S5：Vehicle peccancy behavior is differentiated according to vehicle movement track.
Further, the specific algorithm for improving Surendra background difference algorithms is as follows：
1) video first frame image I is taken0As initial background B0；
2) the maximum gradation value g of current frame image is obtainedmaxWith minimum gradation value gmin, then enable T=gmax+gmin；
3) gray value of image is divided according to T, is divided into two groups of the gray value more than T and the gray value less than T, point Two groups of average gray value μ is not obtained1And μ2；
4) update threshold value T, T=(μ1+μ2)/2；
5) step 3) and 4) is repeated, until the value of T does not change；
6) iterations initialize, and take m=1, maximum iteration M；Calculate present frame and the inter-frame difference of former frame Image, and binaryzation,
In formula, ItThe single-frame images of t moment for input；It-1The single-frame images at the t-1 moment for input；
7) according to the image D after binaryzationtUpdate background,
In formula, Bt(x, y) is t moment background image；α be renewal rate coefficient, value 0.005；
8) each iteration of iterations m terminates iteration, at this time B from increasing 1 as iterations m=MtAfter (x, y) is update Background image.
Further, it is as follows to improve the vehicle detecting algorithm that Surendra backgrounds difference is combined with three-frame difference：
1) to the Traffic Surveillance Video frame image got, improvement Surendra background difference algorithm reconstructed background figures are used Input present frame is made difference processing with background image, obtains background Differential Detection region by picture；
2) with step 1) parallel processing, to the video frame currently inputted, with reference to corresponding former frame and a later frame, three are utilized Frame difference method makees two adjacent frames difference processing, obtains Three image difference detection zone；
3) result of step 1) and step 2) is subjected to inclusive-OR operation processing, obtains comprehensive vehicle testing result, and carry out Morphologic filtering and unicom domain analysis, to remove the noise jamming that non-vehicle object tape comes；
4) region of vehicle in the video frame is demarcated according to the result that step 3) obtains, target is partitioned into external rectangle frame Vehicle.
Further, the calculating of the vehicle movement track is as follows：
If center-of-mass coordinate point of the t moment vehicle in video is denoted as (xt,yt), then the traveling of vehicle can be obtained after L frames Track：
TrajL={ (xt,yt),(xt+1,y+1t),(xt+2,yt+2),...,(xt+L,yt+L)}。
Further, the method for discrimination of vehicle peccancy behavior is as follows：
S5-1：Direction of vehicle movement is adjudicated to be judged with driving in the wrong direction；
If t1Vehicle centroid coordinate is in moment video frame imagest2Vehicle centroid is sat in moment video frame images It is designated asThen from t1To t2Moment, direction of vehicle movement Rule of judgment are：
1)Car speed has the component moved to the right, is denoted as DR；
2)Car speed has the component moved to the left, is denoted as DL；
3)The component of the oriented upper direction of car speed, is denoted as DU；
4)The component of the oriented moved beneath of car speed, is denoted as DD；
Wherein, εx=0.05 × W, εy=0.05 × H, W are vehicle boundary rectangle width of frame, and H is vehicle boundary rectangle frame width Degree；
(D can be used in the direction of vehicle movement of normally travelR,DU), (DR,DD), (DL,DU) and (DL,DD) represent；
S5-2：Vehicle peccancy lane change behavior judges；
1) runway detection is carried out using Hough transform, setting forbids lane change straight line as Forb [N], fitting a straight line side Journey is Ax+By+C=0；
2) the distance d of the corresponding lane line of point all on vehicle tracking track Traj [M] is calculated, calculation formula is such as Under：
D [i]=Traj [i] x-Forb [i] x, i=t, t=1, t+2 ..., t+L；
3) done with lane line distance into two center of mass point be denoted asWithIt enablesR>0 two center of mass point of expression are located at track straight line homonymy；R=0 tables Show at least one center of mass point on straight line；R<0 two center of mass point of expression are located at straight line both sides；
4) dispersion degree of distance, i.e. vehicle and the mean value E and variance S of lane line distance are calculated, i.e.,
5) judgement standard：
When vehicle and the dispersion S of lane line distance are more than threshold value TC, and two barycenter closest with lane line CL is set to 1 by point minute train diatom both sides, and lane change behavior has occurred in expression, otherwise is represented for 0 and lane change behavior does not occur；
S5-3：Head end operation behavior judges；
1) it discusses to two-way vehicle, in left and right sides Through Lane, using track algorithm into the y values of line trace vehicle centroid Persistently increase in vehicle travel process, y values persistently reduce after head end operation；
2) vehicle target y values continued in the increased period, and the slope of vehicle driving trace fitting a straight line section is in right side vehicle In road slope section, similarly, in the period that vehicle target y values persistently reduce, the slope of vehicle driving trace fitting a straight line section In left-hand lane slope section；
3) vehicle y values from reduction switch to it is increased during, vehicle lane change judgement standard CL is set to 1, that is, lane change has occurred Behavior.
The beneficial effects of the invention are as follows：
Vehicle peccancy behavioral value method proposed by the present invention is handled and is analyzed by being carried out to monitor video data in real time, It realizes the automatic identification of vehicles peccancy behavior, under the premise of result accuracy is ensured, reduces computation complexity, realize to vehicle The real-time detection of act of violating regulations.
Specific embodiment
The present invention is further elaborated for specific examples below, but not as a limitation of the invention.
A kind of vehicle peccancy behavioral value method, includes the following steps：
S1：Traffic Surveillance Video acquires, and video is pre-processed；
S2：Using Surendra backgrounds difference is improved vehicle target detection is carried out with the algorithm that three-frame difference is combined；
S3：Vehicle target tracking is carried out with reference to camShift algorithms and Kalman filter；
S4：It extracts vehicle centroid and draws vehicle movement track；
S5：Vehicle peccancy behavior is differentiated according to vehicle movement track.
The specific algorithm for improving Surendra background difference algorithms is as follows：
1) video first frame image I is taken0As initial background B0；
2) the maximum gradation value g of current frame image is obtainedmaxWith minimum gradation value gmin, then enable T=gmax+gmin；
3) gray value of image is divided according to T, is divided into two groups of the gray value more than T and the gray value less than T, point Two groups of average gray value μ is not obtained1And μ2；
4) update threshold value T, T=(μ1+μ2)/2；
5) step 3) and 4) is repeated, until the value of T does not change；
6) iterations initialize, and take m=1, maximum iteration M；Calculate present frame and the inter-frame difference of former frame Image, and binaryzation,
In formula, ItThe single-frame images of t moment for input；It-1The single-frame images at the t-1 moment for input；
7) according to the image D after binaryzationtUpdate background,
In formula, Bt(x, y) is t moment background image；α be renewal rate coefficient, value 0.005；
8) each iteration of iterations m terminates iteration, at this time B from increasing 1 as iterations m=MtAfter (x, y) is update Background image.
Improvement Surendra backgrounds difference is as follows with the vehicle detecting algorithm that three-frame difference is combined：
1) to the Traffic Surveillance Video frame image got, improvement Surendra background difference algorithm reconstructed background figures are used Input present frame is made difference processing with background image, obtains background Differential Detection region by picture；
2) with step 1) parallel processing, to the video frame currently inputted, with reference to corresponding former frame and a later frame, three are utilized Frame difference method makees two adjacent frames difference processing, obtains Three image difference detection zone；
3) result of step 1) and step 2) is subjected to inclusive-OR operation processing, obtains comprehensive vehicle testing result, and carry out Morphologic filtering and unicom domain analysis, to remove the noise jamming that non-vehicle object tape comes；
4) region of vehicle in the video frame is demarcated according to the result that step 3) obtains, target is partitioned into external rectangle frame Vehicle.
The calculating of the vehicle movement track is as follows：
If center-of-mass coordinate point of the t moment vehicle in video is denoted as (xt,yt), then the traveling of vehicle can be obtained after L frames Track：
TrajL={ (xt,yt),(xt+1,y+1t),(xt+2,yt+2),...,(xt+L,yt+L)}。
The method of discrimination of vehicle peccancy behavior is as follows：
S5-1：Direction of vehicle movement is adjudicated to be judged with driving in the wrong direction；
If t1Vehicle centroid coordinate is in moment video frame imagest2Vehicle centroid is sat in moment video frame images It is designated asThen from t1To t2Moment, direction of vehicle movement Rule of judgment are：
1)Car speed has the component moved to the right, is denoted as DR；
2)Car speed has the component moved to the left, is denoted as DL；
3)The component of the oriented upper direction of car speed, is denoted as DU；
4)The component of the oriented moved beneath of car speed, is denoted as DD；
Wherein, εx=0.05 × W, εy=0.05 × H, W are vehicle boundary rectangle width of frame, and H is vehicle boundary rectangle frame width Degree；
(D can be used in the direction of vehicle movement of normally travelR,DU), (DR,DD), (DL,DU) and (DL,DD) represent；
S5-2：Vehicle peccancy lane change behavior judges；
1) runway detection is carried out using Hough transform, setting forbids lane change straight line as Forb [N], fitting a straight line side Journey is Ax+By+C=0；
2) the distance d of the corresponding lane line of point all on vehicle tracking track Traj [M] is calculated, calculation formula is such as Under：
D [i]=Traj [i] x-Forb [i] x, i=t, t=1, t+2 ..., t+L；
3) done with lane line distance into two center of mass point be denoted asWithIt enablesR>0 two center of mass point of expression are located at track straight line homonymy；R=0 is represented At least one center of mass point is on straight line；R<0 two center of mass point of expression are located at straight line both sides；
4) dispersion degree of distance, i.e. vehicle and the mean value E and variance S of lane line distance are calculated, i.e.,
5) judgement standard：
When vehicle and the dispersion S of lane line distance are more than threshold value TC, and two barycenter closest with lane line CL is set to 1 by point minute train diatom both sides, and lane change behavior has occurred in expression, otherwise is represented for 0 and lane change behavior does not occur；
S5-3：Head end operation behavior judges；
1) it discusses to two-way vehicle, in left and right sides Through Lane, using track algorithm into the y values of line trace vehicle centroid Persistently increase in vehicle travel process, y values persistently reduce after head end operation；
2) vehicle target y values continued in the increased period, and the slope of vehicle driving trace fitting a straight line section is in right side vehicle In road slope section, similarly, in the period that vehicle target y values persistently reduce, the slope of vehicle driving trace fitting a straight line section In left-hand lane slope section；
3) vehicle y values from reduction switch to it is increased during, vehicle lane change judgement standard CL is set to 1, that is, lane change has occurred Behavior.

Claims (5)

  1. A kind of 1. vehicle peccancy behavioral value method, which is characterized in that include the following steps：
    S1：Traffic Surveillance Video acquires, and video is pre-processed；
    S2：Using Surendra backgrounds difference is improved vehicle target detection is carried out with the algorithm that three-frame difference is combined；
    S3：Vehicle target tracking is carried out with reference to camShift algorithms and Kalman filter；
    S4：It extracts vehicle centroid and draws vehicle movement track；
    S5：Vehicle peccancy behavior is differentiated according to vehicle movement track.
  2. 2. vehicle peccancy behavioral value method according to claim 1, which is characterized in that the improvement Surendra backgrounds The specific algorithm of difference algorithm is as follows：
    1) video first frame image I is taken0As initial background B0；
    2) the maximum gradation value g of current frame image is obtainedmaxWith minimum gradation value gmin, then enable T=gmax+gmin；
    3) gray value of image is divided according to T, is divided into two groups of the gray value more than T and the gray value less than T, asks respectively Go out two groups of average gray value μ1And μ2；
    4) update threshold value T, T=(μ1+μ2)/2；
    5) step 3) and 4) is repeated, until the value of T does not change；
    6) iterations initialize, and take m=1, maximum iteration M；Present frame and the inter-frame difference image of former frame are calculated, And binaryzation,
    In formula, ItThe single-frame images of t moment for input；It-1The single-frame images at the t-1 moment for input；
    7) according to the image D after binaryzationtUpdate background,
    In formula, Bt(x, y) is t moment background image；α be renewal rate coefficient, value 0.005；
    8) each iteration of iterations m terminates iteration, at this time B from increasing 1 as iterations m=Mt(x, y) is the updated back of the body Scape image.
  3. 3. vehicle peccancy behavioral value method according to claim 1, which is characterized in that improve Surendra background difference It is as follows with the vehicle detecting algorithm that three-frame difference is combined：
    1) to the Traffic Surveillance Video frame image got, using improving Surendra background difference algorithm reconstructed background images, Input present frame is made into difference processing with background image, obtains background Differential Detection region；
    2) it is poor using three frames with reference to corresponding former frame and a later frame to the video frame currently inputted with step 1) parallel processing Point-score makees two adjacent frames difference processing, obtains Three image difference detection zone；
    3) result of step 1) and step 2) is subjected to inclusive-OR operation processing, obtains comprehensive vehicle testing result, and carry out form Filtering and unicom domain analysis are learned, to remove the noise jamming that non-vehicle object tape comes；
    4) region of vehicle in the video frame is demarcated according to the result that step 3) obtains, target carriage is partitioned into external rectangle frame .
  4. 4. vehicle peccancy behavioral value method according to claim 1, which is characterized in that the meter of the vehicle movement track It calculates as follows：
    If center-of-mass coordinate point of the t moment vehicle in video is denoted as (xt,yt), then the traveling rail of vehicle can be obtained after L frames Mark：
    TrajL={ (xt,yt),(xt+1,y+1t),(xt+2,yt+2),...,(xt+L,yt+L)}。
  5. 5. vehicle peccancy behavioral value method according to claim 1, which is characterized in that the differentiation side of vehicle peccancy behavior Method is as follows：
    S5-1：Direction of vehicle movement is adjudicated to be judged with driving in the wrong direction；
    If t1Vehicle centroid coordinate is in moment video frame imagest2Vehicle centroid coordinate is in moment video frame imagesThen from t1To t2Moment, direction of vehicle movement Rule of judgment are：
    1)Car speed has the component moved to the right, is denoted as DR；
    2)Car speed has the component moved to the left, is denoted as DL；
    3)The component of the oriented upper direction of car speed, is denoted as DU；
    4)The component of the oriented moved beneath of car speed, is denoted as DD；
    Wherein, εx=0.05 × W, εy=0.05 × H, W are vehicle boundary rectangle width of frame, and H is vehicle boundary rectangle width of frame；
    (D can be used in the direction of vehicle movement of normally travelR,DU), (DR,DD), (DL,DU) and (DL,DD) represent；
    S5-2：Vehicle peccancy lane change behavior judges；
    1) runway detection is carried out using Hough transform, lane change straight line is forbidden in setting, and fitting a straight line equation is for Forb [N] Ax+By+C=0；
    2) the distance d of the corresponding lane line of point all on vehicle tracking track Traj [M] is calculated, calculation formula is as follows：
    D [i]=Traj [i] x-Forb [i] x, i=t, t=1, t+2 ..., t+L；
    3) done with lane line distance into two center of mass point be denoted asWithIt enablesR>0 two center of mass point of expression are located at track straight line homonymy；R=0 is represented At least one center of mass point is on straight line；R<0 two center of mass point of expression are located at straight line both sides；
    4) dispersion degree of distance, i.e. vehicle and the mean value E and variance S of lane line distance are calculated, i.e.,
    5) judgement standard：
    When vehicle and the dispersion S of lane line distance are more than threshold value TC, and two center of mass point closest with lane line point row CL is set to 1 by lane line both sides, and lane change behavior has occurred in expression, otherwise is represented for 0 and lane change behavior does not occur；
    S5-3：Head end operation behavior judges；
    1) discuss to two-way vehicle, in left and right sides Through Lane, using track algorithm into line trace vehicle centroid y values in vehicle Persistently increase in driving process, y values persistently reduce after head end operation；
    2) vehicle target y values continued in the increased period, and the slope of vehicle driving trace fitting a straight line section is oblique in right-hand lane In rate section, similarly, in the period that vehicle target y values persistently reduce, the slope of vehicle driving trace fitting a straight line section is on a left side In the slope section of side track；
    3) vehicle y values from reduction switch to it is increased during, vehicle lane change judgement standard CL is set to 1, that is, lane change behavior has occurred.
CN201611154230.9A 2016-12-14 2016-12-14 A kind of vehicle peccancy behavioral value method Withdrawn CN108230667A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611154230.9A CN108230667A (en) 2016-12-14 2016-12-14 A kind of vehicle peccancy behavioral value method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611154230.9A CN108230667A (en) 2016-12-14 2016-12-14 A kind of vehicle peccancy behavioral value method

Publications (1)

Publication Number Publication Date
CN108230667A true CN108230667A (en) 2018-06-29

Family

ID=62650156

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611154230.9A Withdrawn CN108230667A (en) 2016-12-14 2016-12-14 A kind of vehicle peccancy behavioral value method

Country Status (1)

Country Link
CN (1) CN108230667A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109215393A (en) * 2018-11-20 2019-01-15 中国葛洲坝集团公路运营有限公司 A kind of method and system for the monitoring of target area anomalous event
CN109299674A (en) * 2018-09-05 2019-02-01 重庆大学 A kind of lane change detection method violating the regulations of the tunnel based on car light
CN109615862A (en) * 2018-12-29 2019-04-12 南京市城市与交通规划设计研究院股份有限公司 Road vehicle movement of traffic state parameter dynamic acquisition method and device
CN109887303A (en) * 2019-04-18 2019-06-14 齐鲁工业大学 Random change lane behavior early warning system and method
CN111833598A (en) * 2020-05-14 2020-10-27 山东科技大学 Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway
CN113570877A (en) * 2021-06-22 2021-10-29 淮阴工学院 Non-motor vehicle retrograde detection device and detection method
CN114419106A (en) * 2022-03-30 2022-04-29 深圳市海清视讯科技有限公司 Vehicle violation detection method, device and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093194A (en) * 2013-01-07 2013-05-08 信帧电子技术（北京）有限公司 Breach of regulation vehicle detection method and device based on videos
CN103714319A (en) * 2013-12-18 2014-04-09 国家电网公司 Video intrusion detection method used for power line external force damage-prevention system
CN103824452A (en) * 2013-11-22 2014-05-28 银江股份有限公司 Lightweight peccancy parking detection device based on full view vision
CN104616501A (en) * 2015-02-06 2015-05-13 河海大学常州校区 Intelligent vision based vehicle law-violation parking detection system and method
CN105185118A (en) * 2015-10-13 2015-12-23 武汉烽火众智数字技术有限责任公司 Vehicle peccancy detection device and method based on video detection

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093194A (en) * 2013-01-07 2013-05-08 信帧电子技术（北京）有限公司 Breach of regulation vehicle detection method and device based on videos
CN103824452A (en) * 2013-11-22 2014-05-28 银江股份有限公司 Lightweight peccancy parking detection device based on full view vision
CN103714319A (en) * 2013-12-18 2014-04-09 国家电网公司 Video intrusion detection method used for power line external force damage-prevention system
CN104616501A (en) * 2015-02-06 2015-05-13 河海大学常州校区 Intelligent vision based vehicle law-violation parking detection system and method
CN105185118A (en) * 2015-10-13 2015-12-23 武汉烽火众智数字技术有限责任公司 Vehicle peccancy detection device and method based on video detection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
宋耀: "交通监控视频中的车辆异常行为检测", 《电视技术》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109299674A (en) * 2018-09-05 2019-02-01 重庆大学 A kind of lane change detection method violating the regulations of the tunnel based on car light
CN109299674B (en) * 2018-09-05 2022-03-18 重庆大学 Tunnel illegal lane change detection method based on car lamp
CN109215393A (en) * 2018-11-20 2019-01-15 中国葛洲坝集团公路运营有限公司 A kind of method and system for the monitoring of target area anomalous event
CN109615862A (en) * 2018-12-29 2019-04-12 南京市城市与交通规划设计研究院股份有限公司 Road vehicle movement of traffic state parameter dynamic acquisition method and device
CN109887303A (en) * 2019-04-18 2019-06-14 齐鲁工业大学 Random change lane behavior early warning system and method
CN111833598A (en) * 2020-05-14 2020-10-27 山东科技大学 Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway
CN113570877A (en) * 2021-06-22 2021-10-29 淮阴工学院 Non-motor vehicle retrograde detection device and detection method
CN114419106A (en) * 2022-03-30 2022-04-29 深圳市海清视讯科技有限公司 Vehicle violation detection method, device and storage medium
CN114419106B (en) * 2022-03-30 2022-07-22 深圳市海清视讯科技有限公司 Vehicle violation detection method, device and storage medium

Similar Documents

Publication Publication Date Title
CN108230667A (en) A kind of vehicle peccancy behavioral value method
CN109829403B (en) Vehicle anti-collision early warning method and system based on deep learning
CN104008645B (en) One is applicable to the prediction of urban road lane line and method for early warning
CN105632186B (en) Detection vehicle is jumped a queue the method and apparatus of behavior
CN108596129A (en) A kind of vehicle based on intelligent video analysis technology gets over line detecting method
CN104021378B (en) Traffic lights real-time identification method based on space time correlation Yu priori
CN106541968B (en) The recognition methods of the subway carriage real-time prompt system of view-based access control model analysis
CN106778593A (en) A kind of track level localization method based on the fusion of many surface marks
CN106652445A (en) Road traffic accident judging method and device
WO2013136878A1 (en) Object detection device
CN103927548B (en) Novel vehicle collision avoiding brake behavior detection method
CN104157160B (en) Vehicle travel control method, device and vehicle
CN104537841A (en) Unlicensed vehicle violation detection method and detection system thereof
CN111597905B (en) Highway tunnel parking detection method based on video technology
CN105678287B (en) A kind of method for detecting lane lines based on ridge measurement
CN103164958B (en) Method and system for vehicle monitoring
Wang et al. Advanced driver-assistance system (ADAS) for intelligent transportation based on the recognition of traffic cones
CN103794050A (en) Real-time transport vehicle detecting and tracking method
CN103021179A (en) Real-time monitoring video based safety belt detection method
CN107705577A (en) A kind of real-time detection method and system based on lane line demarcation vehicle peccancy lane change
CN106951820B (en) Passenger flow statistical method based on annular template and ellipse fitting
CN106530825A (en) Method for detecting traffic conflict between motor-assisted bicycle and automobile based on ST-MRF model
Huang Real-time multi-vehicle detection and sub-feature based tracking for traffic surveillance systems
WO2023020004A1 (en) Vehicle distance detection method and system, and device and medium
CN104867332B (en) Based on the detection method every driving vehicle in the front lane line of frame difference method

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: 20180629