CN104809887B - A kind of retrograde detection method of vehicle on expressway and autoalarm - Google Patents

A kind of retrograde detection method of vehicle on expressway and autoalarm Download PDF

Info

Publication number
CN104809887B
CN104809887B CN201510198257.7A CN201510198257A CN104809887B CN 104809887 B CN104809887 B CN 104809887B CN 201510198257 A CN201510198257 A CN 201510198257A CN 104809887 B CN104809887 B CN 104809887B
Authority
CN
China
Prior art keywords
vehicle
retrograde
frame
wrong direction
detection
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.)
Active
Application number
CN201510198257.7A
Other languages
Chinese (zh)
Other versions
CN104809887A (en
Inventor
石旭刚
张水发
刘嘉
杜雅慧
欧阳忠清
汤泽胜
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.)
OB TELECOM ELECTRONICS CO Ltd
Original Assignee
OB TELECOM ELECTRONICS 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 OB TELECOM ELECTRONICS CO Ltd filed Critical OB TELECOM ELECTRONICS CO Ltd
Priority to CN201510198257.7A priority Critical patent/CN104809887B/en
Publication of CN104809887A publication Critical patent/CN104809887A/en
Application granted granted Critical
Publication of CN104809887B publication Critical patent/CN104809887B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/056Detecting movement of traffic to be counted or controlled with provision for distinguishing direction of travel

Abstract

The invention discloses a kind of retrograde detection method of vehicle on expressway and autoalarm to include the retrograde detection module of image capture module, vehicle, alarm flashing lamp, data transmission device, computer;Image capture module, alarm flashing lamp, data transmission device are connected with the retrograde detection module of vehicle, computer is connected with data transmission device, in order to improve the accuracy rate for detection of driving in the wrong direction, not only previous frame is detected, also in nearest N frames, randomly select M frames and carry out comprehensive descision, exist only more than X frames or X frames and drive in the wrong direction, be just judged as driving in the wrong direction, send retrograde alarm, more vehicle match are carried out with reference to the histogram feature and Fourier spectrum feature of vehicle, improve the accuracy rate of matching.

Description

A kind of retrograde detection method of vehicle on expressway and autoalarm
Technical field
The present invention relates to the vehicle abnormality behavioral analysis technology of field of intelligent video surveillance, more particularly to a kind of highway The retrograde detection method of upper vehicle and autoalarm.
Background technology
With the development of China's traffic transporting technology, the traffic administration operation way of poorly efficient traffic surveillance and control system and aging The needs of the traffic technique of fast development can not much be met, and then as the bottleneck of restriction China's traffic transporting technology development. Intelligent Video Surveillance Technology is that vehicular traffic is inverse as a kind of simple, convenient, efficient, inexpensive, touchless monitoring technology The behaviors such as row, blocking cause traffic accident to have preferable prevention effect.Intelligent Video Surveillance Technology is modernizing Traffic, transport, security protection, police reconnaissance, prison monitoring, the safeguard protection of valuables, alarm, magnitude of traffic flow monitoring, office field No worker monitor, the field such as remote monitoring of computer room is widely used.
Intelligent Video Surveillance Technology mainly has the advantage that:
1st, integrated cost is low.Only need one-time investment, it becomes possible to allow people to be solved from uninteresting, barren artificial monitoring Take off, nursed without special messenger, it is only necessary to when occurring abnormal alarm in monitoring, responded.In cost of labor increasingly Today of height enterprise, undoubtedly save a large number of input and daily expenses.
2nd, testing result is objective, reliable.Under the mode manually monitored, monitored picture is stared at for a long time, and supervisor is easy Fatigue, it is numb to picture, and intelligent monitoring can exclude the interference of this respect, once detecting has unusual condition in picture, you can Alarm is sent in real time, to be convenient for people to timely respond to.
3rd, it is easy to use.As long as the place for having network can just monitor, reception alarm signal, support remotely and local real-time Signal receives, and supports the live signal of multiple spot, various ways to receive.
4th, monitoring video is stored on big capacity hard disk by intelligent monitoring technology, can easily be called, and is stored and is transported, Can be as the evidence of traffic violations.
The content of the invention
For above-mentioned technical problem, the present invention proposes that a kind of retrograde detection method of vehicle on expressway fills with automatic alarm Put.
In order to solve the above-mentioned technical problem, technical scheme is as follows:
A kind of vehicle on expressway drives in the wrong direction autoalarm, including image capture module, vehicle drive in the wrong direction detection module, Alarm flashing lamp, data transmission device, computer;
Described image acquisition module, alarm flashing lamp, data transmission device are connected with the retrograde detection module of vehicle, the meter Calculation machine is connected with data transmission device.
Further, the frame of video that the retrograde detection module of the vehicle gathers to image capture module detects;It is described Alarm flashing lamp is used to receive the signal that the retrograde detection module of the vehicle is sent, and reminds vehicular traffic;The data transfer dress Put the video requency frame data for transmitting the retrograde detection module of the vehicle;
The computer is used to show, store the video requency frame data transmitted by the data transmission device.
Further, in addition to warning device, the warning device are controlled for sending alarm signal by computer.
A kind of vehicle on expressway drives in the wrong direction detection method, comprises the following steps:
4.1) the retrograde detection module of vehicle establishes rule of driving in the wrong direction:It is determined that need detecting the polygonal region of vehicle, vehicle just The direction often travelled and the maximum angle for allowing vehicle to allow deviation normally travel direction;
4.2) moving vehicle is detected:The background constructing mixed Gaussian background mould of the frame of video collected to image capture module Type;By current frame image and background image subtraction, when difference is more than certain value, it is believed that be motion pixel, motion pixel is returned Class obtains moving vehicle;
4.3) track of vehicle and morphological analysis:
A) vehicle of present frame is traveled through, obtains profile, center of gravity, histogram and the Fourier spectrum feature of vehicle;
B) position being likely to occur according to vehicle in the position of frame, calculating vehicle in previous frame, finds a frame of video In all vehicles existing for these positions;
If vehicle c) can not be found, and the location of present frame vehicle is the position that vehicle enters detection zone, Then think that the normal vehicle operation is appeared in detection scene, assign globally unique label, add in normal tracking queue, continue The detection of next vehicle, go to step a);
If vehicle d) can not be found, and present frame vehicle present position is the position that vehicle leaves detection zone, then Think that the vehicle may drive in the wrong direction into scene, assign globally unique label, addition may drive in the wrong direction in vehicle platoon, go to step a);
If vehicle e) can not be found, and not at the edge of polygonal region, then it is assumed that vehicle be blocked or and its He merges vehicle, puts it into queue undetermined, does not change its label, waits next frame to compare, goes to step a);
If f) finding one or more cars, the similarity of histogram similarity and Fourier spectrum feature is calculated, The similarity threshold of histogram similarity and Fourier spectrum feature is set, if there is no histogram similarity and Fourier's frequency Spectrum signature similarity is more than the vehicle of threshold value, then it is assumed that does not match, by the logical process for not finding vehicle, goes to step a);
G) if one or more cars it is eligible, then select most like vehicle, be added into tracking queue, And imparting and label consistent before, their relative position is calculated, is driven in the wrong direction if present frame vehicle is in relative to previous frame Position, it is believed that the car there may be retrograde.
Further, also comprise the following steps after step g):The metamorphosis of the retrograde detection module analysis vehicle of vehicle, If the lasting tracking frame number of the vehicle is less than N frames, then it is assumed that historical track information is also not enough to confirm, goes to step a), such as Fruit persistently tracks frame number and is more than or equal to N frames, randomly selects M frames and is judged, more than X frames or X frames (X≤M≤N) locates as long as having In retrograde position, then it is assumed that Current vehicle, which exists, to drive in the wrong direction, and the retrograde detection module of vehicle sends signal to the alarm flashing lamp, carries Awake vehicular traffic.
The beneficial effects of the present invention are:The present invention is not only carried out to improve the accuracy rate for detection of driving in the wrong direction to previous frame Detection, also in nearest N frames, randomly select M frames and carry out comprehensive descision, exist only more than X frames or X frames and drive in the wrong direction, just judge It is retrograde, sends retrograde alarm.The present invention combines the histogram feature of vehicle and Fourier spectrum feature carries out more vehicle match, Improve the accuracy rate of matching.The present invention combine vehicle it is retrograde during the change in location that occurs and caused by the camera depth of field Metamorphosis judges to drive in the wrong direction, and can preferably eliminate the accuracy rate for due to influence caused by noise, improving detection.The present invention Local alarm and remote alarm are combined, when driving in the wrong direction, flashing lamp alarm is sent, reminds car to slow down, prevent from touching Hit, while alarm is sent to long-range assistant policeman, to timely respond to, and retrograde picture is stored, as punishing justification.
Brief description of the drawings
Fig. 1 is overview flow chart of the present invention;
Fig. 2 is track of vehicle of the present invention and morphological analysis flow chart;
Fig. 3 is the retrograde detection autoalarm structure chart of vehicle of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described further.
It is a kind of retrograde autoalarm of vehicle on expressway as shown in Figure 3, vehicle on expressway drives in the wrong direction automatic Warning device includes:The retrograde detection module of image capture module, vehicle, alarm flashing lamp, data transmission device, computer and report Alert loudspeaker.Image capture module, alarm flashing lamp, data transmission device are connected with the retrograde detection module of vehicle, the calculating Machine is connected with data transmission device, and alarm speaker is connected with computer.Above-mentioned image capture module and vehicle, which drive in the wrong direction, detects mould Block can be integrated in camera internal.This alarm flashing lamp connects the camera after integrated.When detecting that vehicle drives in the wrong direction, send Signal gives alarm flashing lamp, sends retrograde alarm, for reminding vehicular traffic, front has vehicle and driven in the wrong direction;Camera passes through data Transmitting device, the video requency frame data of retrograde picture is transferred to computer, and region of driving in the wrong direction is marked with red block, in picture upper right Angle provides retrograde alarm signal.Computer receives the retrograde picture of vehicle in the video requency frame data of the data transmission device transmission Face, and show, store the retrograde picture of vehicle;And alarm signal is sent by alarm speaker, prompt assistant policeman to be driven in the wrong direction, Take appropriate measures.
Embodiment one:
As depicted in figs. 1 and 2, the retrograde detection method of a kind of vehicle on expressway, it is formed and function declaration is as follows:
(1) the retrograde detection module of vehicle establishes the retrograde rule of vehicle:
Determine vehicle detection quadrilateral area, determine in quadrangle detection zone the direction of normal vehicle operation and It is determined that vehicle is allowed to allow the maximum angle for deviateing normally travel direction.
(2) moving vehicle is detected:
The frame of video collected according to image capture module is background constructing mixture Gaussian background model;
By current frame image and background image subtraction, when difference is more than certain value, it is believed that be motion pixel;By motor image Element, which is sorted out, obtains moving vehicle.
(3) track of vehicle and morphological analysis:
A) vehicle of present frame is traveled through, obtains profile, center of gravity, histogram and the Fourier spectrum feature of vehicle;Because car Speed be it is limited, while camera collection frequency be 25 frames/s, so the distance that vehicle moves between adjacent two frame Within the specific limits;
B) position being likely to occur according to vehicle in the position of present frame, calculating vehicle in previous frame, finds previous frame In all vehicles existing for these positions;
If vehicle c) can not be found, and the location of present frame vehicle is the position that vehicle enters detection zone, Then think that the normal vehicle operation is appeared in detection scene, the car and its corresponding feature are added in tracking queue, and is assigned Globally unique label is given, continues the detection of next vehicle, goes to a);
If vehicle d) can not be found, and present frame vehicle present position is the position that vehicle leaves detection zone, then Think that the vehicle may drive in the wrong direction into scene, the car and its corresponding feature are added in the vehicle platoon that may drive in the wrong direction, and is assigned Globally unique label, goes to a);
If vehicle e) can not be found, and not at the edge in region, then it is assumed that vehicle be blocked or with other vehicles Merge, put it into queue undetermined, do not change its label, wait next frame to compare, go to a);
If f) finding one or more cars, using Pasteur's distance come the histogram between the vehicle that calculates and find The similarity of similarity and Fourier spectrum feature, set the similarity threshold of histogram similarity and Fourier spectrum feature as 0.2,0.2 vehicle is less than if there is no the Pasteur of histogram similarity and Fourier spectrum characteristic similarity distance, then is recognized Not match, by the logical process for not finding vehicle, go to a);G) if one or more cars it is eligible, then Most like vehicle is selected, is added into tracking queue, and imparting and label consistent before, calculate their relative position Put, if present frame vehicle is in retrograde position relative to previous frame, it is believed that the car there may be it is retrograde, meanwhile, analyze car Metamorphosis because the change of the depth of field in scene be present, the change of vehicle form, which can also be used as to strengthen driving in the wrong direction, sentence Disconnected foundation, compare the size of vehicle, if it is to be sailed near toward long journey to drive in the wrong direction, then it is assumed that during vehicle drives in the wrong direction, there is gradual change Small trend, if it is from remote toward nearly traveling to drive in the wrong direction, then it is assumed that during vehicle drives in the wrong direction, there is the trend become larger;In order to carry The accuracy rate of high detection, reduce wrong report and judge, it is necessary to obtain more trace informations and strengthen driving in the wrong direction, for example, if the car continues Tracking frame number is less than 10 frames, then it is assumed that historical track information is also not enough to confirm, goes to a), if persistently track frame number more than etc. In 10 frames, randomly select 5 frames and judged, more than 3 frames or 3 frames be in retrograde position as long as having, then it is assumed that Current vehicle is deposited Driving in the wrong direction, the retrograde detection module of vehicle sends signal to the alarm flashing lamp, reminds vehicular traffic;And video requency frame data is led to Cross data transmission device and transmit to computer and be used to store and show, when running into retrograde situation, and sent by alarm speaker Alarm signal, prompt assistant policeman to be driven in the wrong direction, take appropriate measures.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art Member, without departing from the inventive concept of the premise, can also make some improvements and modifications, these improvements and modifications also should be regarded as In the scope of the present invention.

Claims (4)

  1. The detection method 1. a kind of vehicle on expressway drives in the wrong direction, it is characterised in that drive in the wrong direction and detect including image capture module, vehicle Module, alarm flashing lamp, data transmission device, computer;
    Described image acquisition module, alarm flashing lamp, data transmission device are connected with the retrograde detection module of vehicle, and described image is adopted Collect module by data transmission device, the video requency frame data of retrograde picture is transferred to computer, and marked and driven in the wrong direction with red block Region, retrograde alarm signal is provided in the picture upper right corner, and the computer is connected with data transmission device;The alarm flashing lamp For reminding vehicular traffic, there is vehicle and drive in the wrong direction in front;
    Specific detecting step is as follows:
    4.1) the retrograde detection module of vehicle establishes rule of driving in the wrong direction:It is determined that need to detect the normal row of polygonal region, vehicle of vehicle The direction sailed and the maximum angle for allowing vehicle to deviate normally travel direction;
    4.2) moving vehicle is detected:The background constructing mixture Gaussian background model of the frame of video collected to image capture module; By current frame image and background image subtraction, when difference is more than certain value, it is believed that be motion pixel, motion pixel is sorted out To moving vehicle;
    4.3) track of vehicle and morphological analysis:
    A) vehicle of present frame is traveled through, obtains profile, center of gravity, histogram and the Fourier spectrum feature of vehicle;
    B) position being likely to occur according to vehicle in the position of frame, calculating vehicle in previous frame, finds this in a frame of video All vehicles existing for a little positions;
    If vehicle c) can not be found, and the location of present frame vehicle is the position that vehicle enters detection zone, then recognizes Appeared in for the normal vehicle operation in detection scene, assign globally unique label, add in normal tracking queue, continued next The detection of vehicle, go to step a);
    If vehicle d) can not be found, and present frame vehicle present position is the position that vehicle leaves detection zone, then it is assumed that The vehicle may drive in the wrong direction into detection scene, assign globally unique label, addition may drive in the wrong direction in vehicle platoon, go to step a);
    If vehicle e) can not be found, and not at the edge of polygonal region, then it is assumed that vehicle be blocked or with other cars Merge, put it into queue undetermined, do not change its label, wait next frame to compare, go to step a);
    If f) finding one or more cars, the similarity of histogram similarity and Fourier spectrum feature, setting are calculated One given threshold of the similarity of histogram similarity and Fourier spectrum feature, if there is no histogram similarity and Fu In leaf spectrum signature similarity be more than the vehicle of given threshold, then it is assumed that do not match, by the logical process for not finding vehicle, Go to step a);
    G) if one or more cars it is eligible, then select most like vehicle, be added into tracking queue, and assign Give with label consistent before, their relative position is calculated, if present frame vehicle is in retrograde position relative to previous frame Put, it is believed that the car there may be retrograde.
  2. The detection method 2. vehicle on expressway according to claim 1 drives in the wrong direction, it is characterised in that the vehicle, which drives in the wrong direction, to be examined The frame of video that module gathers image capture module is surveyed to detect;
    The alarm flashing lamp is used to receive the signal that the retrograde detection module of the vehicle is sent, and reminds vehicular traffic;
    The data transmission device is used for the video requency frame data for transmitting the retrograde detection module of the vehicle;
    The computer is used to show, store the video requency frame data transmitted by the data transmission device.
  3. The detection method 3. vehicle on expressway according to claim 1 drives in the wrong direction, it is characterised in that also include alarm dress Put, the warning device is controlled for sending alarm signal by computer.
  4. The detection method 4. vehicle on expressway according to claim 1 drives in the wrong direction, it is characterised in that also wrapped after step g) Include following steps:The metamorphosis of the retrograde detection module analysis vehicle of vehicle, if the lasting tracking frame number of the vehicle is less than N Frame, then it is assumed that historical track information is also not enough to confirm, goes to step a), if persistently tracking frame number is more than or equal to N frames, at random Choose M frames to be judged, retrograde position more than X frames or X frames is in as long as having, then it is assumed that Current vehicle, which exists, to drive in the wrong direction, vehicle Retrograde detection module sends signal to the alarm flashing lamp, reminds vehicular traffic.
CN201510198257.7A 2015-04-23 2015-04-23 A kind of retrograde detection method of vehicle on expressway and autoalarm Active CN104809887B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510198257.7A CN104809887B (en) 2015-04-23 2015-04-23 A kind of retrograde detection method of vehicle on expressway and autoalarm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510198257.7A CN104809887B (en) 2015-04-23 2015-04-23 A kind of retrograde detection method of vehicle on expressway and autoalarm

Publications (2)

Publication Number Publication Date
CN104809887A CN104809887A (en) 2015-07-29
CN104809887B true CN104809887B (en) 2018-03-16

Family

ID=53694683

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510198257.7A Active CN104809887B (en) 2015-04-23 2015-04-23 A kind of retrograde detection method of vehicle on expressway and autoalarm

Country Status (1)

Country Link
CN (1) CN104809887B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105957312A (en) * 2016-06-06 2016-09-21 重庆微标科技股份有限公司 Prompting method and system for abnormal clearance of vehicle
CN109661667A (en) * 2016-10-14 2019-04-19 富士通株式会社 The retrograde detection device of vehicle and method, electronic equipment
CN106297314A (en) * 2016-11-03 2017-01-04 北京文安智能技术股份有限公司 A kind of drive in the wrong direction or the detection method of line ball vehicle behavior, device and a kind of ball machine
CN107886055A (en) * 2017-10-27 2018-04-06 中国科学院声学研究所 A kind of retrograde detection method judged for direction of vehicle movement
CN109637155B (en) * 2018-11-12 2021-07-06 钦州学院 Vehicle detection device of urban traffic intelligent control system
CN110032947B (en) * 2019-03-22 2021-11-19 深兰科技(上海)有限公司 Method and device for monitoring occurrence of event
CN109948582B (en) * 2019-03-28 2021-03-02 湖南大学 Intelligent vehicle reverse running detection method based on tracking trajectory analysis
CN110232807A (en) * 2019-04-30 2019-09-13 广东侍卫长北斗科技股份公司 The automatic monitoring of one kind is received a crime report and emergency rescue service system
CN110310493B (en) * 2019-07-02 2022-01-07 亳州职业技术学院 Traffic retrograde constraint system based on Internet of things
CN112288695B (en) * 2020-10-20 2021-06-15 新昌县鸿吉电子科技有限公司 Factory production area target identification system
CN112738961B (en) * 2021-01-06 2023-04-18 苏州鱼得水电气科技有限公司 Intelligent road lighting control system based on big data
CN114882393B (en) * 2022-03-29 2023-04-07 华南理工大学 Road reverse running and traffic accident event detection method based on target detection

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101111875A (en) * 2005-02-04 2008-01-23 R·梅 Warning system for use on motorways to indicate presence of a vehicle travelling in the wrong direction
CN102081844A (en) * 2011-01-25 2011-06-01 华中科技大学 Traffic video behavior analyzing and alarming server
CN201886629U (en) * 2010-11-17 2011-06-29 赵素杰 All-weather seamless night-vision monitoring laser device special for highways

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5396429A (en) * 1992-06-30 1995-03-07 Hanchett; Byron L. Traffic condition information system
JP2002222486A (en) * 2001-01-29 2002-08-09 Toshiba Corp Road monitoring system
JP2004362433A (en) * 2003-06-06 2004-12-24 Hitachi Ltd Approaching vehicle alarm system and its display method
CN103345618A (en) * 2013-06-21 2013-10-09 银江股份有限公司 Traffic violation detection method based on video technology
CN203630959U (en) * 2013-11-16 2014-06-04 中国计量学院 Real-time road monitoring system against driving in wrong direction
CN104464305A (en) * 2014-12-11 2015-03-25 天津艾思科尔科技有限公司 Intelligent vehicle converse driving detecting device and method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101111875A (en) * 2005-02-04 2008-01-23 R·梅 Warning system for use on motorways to indicate presence of a vehicle travelling in the wrong direction
CN201886629U (en) * 2010-11-17 2011-06-29 赵素杰 All-weather seamless night-vision monitoring laser device special for highways
CN102081844A (en) * 2011-01-25 2011-06-01 华中科技大学 Traffic video behavior analyzing and alarming server

Also Published As

Publication number Publication date
CN104809887A (en) 2015-07-29

Similar Documents

Publication Publication Date Title
CN104809887B (en) A kind of retrograde detection method of vehicle on expressway and autoalarm
CN102945603B (en) Method for detecting traffic event and electronic police device
CN103914688B (en) A kind of urban road differentiating obstacle
CN102521983B (en) Vehicle violation detection system based on high definition video technology and method thereof
US8885929B2 (en) Abnormal behavior detection system and method using automatic classification of multiple features
CN101313345B (en) System and method for detecting driving against road traffic regulation
CN110136447A (en) Lane change of driving a vehicle detects and method for distinguishing is known in illegal lane change
CN109326124A (en) A kind of urban environment based on machine vision parks cars Activity recognition system
CA2925843C (en) System for traffic behaviour surveillance
CN105744232A (en) Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology
CN104021677B (en) A kind of vehicle board turning detection method and device
CN107886055A (en) A kind of retrograde detection method judged for direction of vehicle movement
CN105513349A (en) Double-perspective learning-based mountainous area highway vehicle event detection method
CN104282154A (en) Vehicle overload monitoring system and method
CN104240505A (en) Method for analyzing road traffic video image information
CN113936465B (en) Traffic event detection method and device
CN103886753B (en) A kind of signal lamp control crossroad exception parking reason quickly confirms system and method
CN110796862B (en) Highway traffic condition detection system and method based on artificial intelligence
CN104809470A (en) Vehicle converse running detection device and method based on SVM
CN105574502A (en) Automatic detection method for violation behaviors of self-service card sender
CN206961331U (en) A kind of high threat vehicle monitoring early warning system
CN105279968A (en) Discrimination system and method for the illegal emergency lane occupancy behavior of highway motor vehicle
WO2018209470A1 (en) License plate identification method and system
CN108010312A (en) Suitable for the vehicle safety access management system for station of stopping
Wang et al. Vision-based highway traffic accident detection

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant