CN110490150A - A kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval - Google Patents

A kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval Download PDF

Info

Publication number
CN110490150A
CN110490150A CN201910779521.4A CN201910779521A CN110490150A CN 110490150 A CN110490150 A CN 110490150A CN 201910779521 A CN201910779521 A CN 201910779521A CN 110490150 A CN110490150 A CN 110490150A
Authority
CN
China
Prior art keywords
vehicle
violation
regulations
module
detection module
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.)
Granted
Application number
CN201910779521.4A
Other languages
Chinese (zh)
Other versions
CN110490150B (en
Inventor
高飞
周明明
卢书芳
程振波
张元鸣
肖刚
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.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
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 Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN201910779521.4A priority Critical patent/CN110490150B/en
Publication of CN110490150A publication Critical patent/CN110490150A/en
Application granted granted Critical
Publication of CN110490150B publication Critical patent/CN110490150B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • 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
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval.The auditing system is made of vehicle detection module, vehicle characteristics extraction module, vehicle contrast module and vehicle violation detection module, and vehicle detection module is for detecting all vehicles in picture violating the regulations；Vehicle characteristics extraction module is extracted for vehicle depth characteristic；Vehicle contrast module calculates vehicle characteristics matching degree for comparing vehicle characteristics；Vehicle violation detection module is used to position in violation vehicle with the same vehicle of target violation vehicle, determines violation vehicle further according to specific position.The audit that the present invention is obtained by using above-mentioned technology can correctly be judged when video analysis software judges vehicle violation erroneous detection, avoid the erroneous judgement of vehicle violation, keep vehicle violation automation more perfect；Can also automatic identification vehicle whether violation event occurs, release traffic control human resources, improve resource utilization.

Description

A kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval
Technical field
The present invention relates to field of intelligent transportation technology, specially a kind of picture violating the regulations based on vehicle retrieval side of audit automatically Method and system.
Background technique
In recent years, popularizing with China's vehicle, city vehicle quantity increases year by year, and break in traffic rules and regulations event also increases year by year Add.The investigation of vehicle violation event is conducive to the foundation of road traffic specification, can safeguard road traffic order, prevention and reduction Traffic accident protects personal safety, protects the property safety of the people.So needing to investigate and prosecute break in traffic rules and regulations event.
With social progress and development, the investigation mode of break in traffic rules and regulations event is also changed, and is thought from initial Processing, automatic processing till now.With the increase of break in traffic rules and regulations event, the manpower of traffic management department is significantly increased Resource consumption.In order to discharge because of the increased human resources consumption of break in traffic rules and regulations event, there is automatic auditing system of breaking rules and regulations.
Different vehicle violation picture examination systems currently is proposed there are many scholar, but captured by traffic control camera Video after video analysis software, captured its violation vehicle picture thought, but since video analysis software is deposited In certain erroneous detection, certain puzzlement is brought to examination violating the regulations.
Summary of the invention
To overcome the deficiencies in the prior art, the purpose of the present invention is to provide the pictures violating the regulations based on vehicle retrieval Automatic auditing method and system.
A kind of automatic auditing system of picture violating the regulations based on vehicle retrieval, it is characterised in that by vehicle detection mould Block, vehicle characteristics extraction module, vehicle contrast module and vehicle violation detection module are constituted, the vehicle detection module, vehicle Contrast module is connect with vehicle characteristics extraction module, vehicle violation detection module respectively, and vehicle detection module is for detecting to disobey All vehicles in chapter picture；The vehicle that vehicle characteristics extraction module is used to detected vehicle detection module carries out vehicle depth Feature extraction；Vehicle is special in the vehicle characteristics and picture violating the regulations of the target violation vehicle that vehicle contrast module is used to judge system Sign extraction module extracts the vehicle depth characteristic of vehicle and is compared, and calculates vehicle characteristics matching degree, and by calculated result It is sent to vehicle violation detection module；Vehicle violation detection module receive vehicle contrast module as a result, and according to vehicle detection The coordinate for the corresponding vehicle that module is extracted, for being positioned in violation vehicle with the same vehicle of target violation vehicle, further according to Specific position determines violation vehicle.
The vehicle checking method of the automatic auditing system of picture violating the regulations based on the vehicle retrieval, it is characterised in that including such as Lower step:
1) picture violating the regulations is divided into four regions with center picture point pixel, respectively first, second, third and the 4th area Domain, the target violation vehicle that system detection goes out are present in the fourth region, enable four regions of the vehicle detection module from picture violating the regulations In extract all vehicle characteristics vector set in same pictureAnd detect that all vehicles and vehicle are special The mapping set of the sign extraction module vehicle characteristics vector that extracts all vehicles isIts Middle cjIndicate that jth vehicle, n indicate vehicle fleet size,Indicate the set of the feature vector of jth vehicle, Indicate k-th of vehicle characteristics vector in the vehicle characteristics set of jth vehicle；
2) the feature vector F of the fourth region target violation vehicle is extracted by vehicle characteristics extraction modulem={ feati| i= 1,2 ..., 4096 }, i indicates i-th of vehicle characteristics vector, and sends the eigenvector information of target violation vehicle to vehicle Contrast module；
3) vehicle contrast module is by the vehicle characteristics vector for the target violation vehicle extracted according to formula (1) and step 1) In all vehicle characteristics vector set in the same picture that extractsIn each vehicle characteristics vectorSimilarity s, obtain similarity setIf the phase of two cars Like degree s > K0, K0For vehicle confidence threshold value, then by this information of vehicles (cn,carlistn) similar vehicle set, c is addednIt indicates Vehicle is specifically numbered, carlistnThe specific frame of vehicle position is indicated, thus to obtain the similar of all target vehicles violating the regulations Vehicle；
Wherein Q, P respectively represent the feature vector of two cars, Q={ qi| i=1,2 ..., 4096 }, P={ pi| i=1, 2 ..., 4096 }, qiIndicate the ith feature value in feature vector Q, PiIndicate the ith feature value in feature vector P, K table Show vehicle characteristics dimension, s indicates Q, the similarity function of P two cars；
4) according to the similar vehicle set s of the target vehicle violating the regulations obtained in step 3), it is in place to obtain similar vehicle institute The specific frame set obtains the center point coordinate of the specific frame of vehicle according to formula (2), determines the position where similar vehicle, obtain Similar vehicle center point coordinate (Xc,Yc)；
Wherein, (Xc,Yc) it is similar vehicle center point coordinate, (X, Y) indicates the left apex coordinate of the specific frame of similar vehicle, W table Show that the width of specific frame, H indicate the height of specific frame；
Vehicle violation detection module judges the specific region where vehicle according to similar vehicle center point coordinate, obtains each Region similar vehicle set S1={ (cx,carlistx) | x=1,2 ..., n }, cxThe specific number for indicating similar vehicle, enables D =max (S1), obtain D where similar vehicle specific frame be exactly current region target violation vehicle, judge first area, Whether all there is target violation vehicle in second area and third region, if all existing, then target violation vehicle determines violating the regulations, It is on the contrary then be erroneous detection result.
By using above-mentioned technology, compared with prior art, beneficial effects of the present invention are as follows:
1) this system can correctly be judged when video analysis software judges vehicle violation erroneous detection, avoid vehicle Erroneous judgement violating the regulations keeps vehicle violation automation more perfect；
2) whether this system can occur violation event with automatic identification vehicle, release traffic control human resources, improve money Source utilization rate.
Detailed description of the invention
Fig. 1 is the step flow chart of the method for the present invention；
Fig. 2 is the detection example grayscale image of the embodiment of the present invention, and wherein the vehicle of the fourth region is the mesh that system identification is arrived Mark violation vehicle；
Fig. 3 is review process grayscale image of the present invention, found in four regions of detection example figure with target vehicle Same vehicle.
Specific embodiment
With reference to the accompanying drawings of the specification and embodiment, the present invention is further detailed.It should be appreciated that this place is retouched The specific embodiment stated is used only for explaining the present invention, is not intended to limit the present invention.
As shown in Figure 1, a kind of automatic auditing system of picture violating the regulations based on vehicle retrieval of the invention, by vehicle detection mould Block 1, vehicle characteristics extraction module 2, vehicle contrast module 3 and vehicle violation detection module 4 are constituted, the vehicle detection module 1, Vehicle contrast module 3, vehicle violation detection module 4 and vehicle detection module 1 and vehicle contrast module 3 are separately connected, vehicle inspection It surveys module 1 to be responsible for carrying out vehicle detection to picture violating the regulations, the resolution ratio for picture of breaking rules and regulations is 7296*5792, by institute in picture violating the regulations There is vehicle all to detected；It is deep that the vehicle that vehicle characteristics extraction module 2 is used to detected vehicle detection module 1 carries out vehicle Spend feature extraction；Vehicle contrast module 3 calculates vehicle characteristics matching degree, the vehicle of the target violation vehicle for judging system Feature is compared with the vehicle depth characteristic that vehicle characteristics extraction module 2 in picture violating the regulations extracts vehicle, and ties calculating Fruit is sent to vehicle violation detection module 4；Vehicle violation detection module 4 receive vehicle contrast module 3 as a result, and according to vehicle The coordinate for the corresponding vehicle that detection module 1 extracts, for being positioned with the same vehicle of target violation vehicle, further according to specific positioning Whether it is erroneous judgement that judgement is violating the regulations；
The vehicle positioning of the vehicle detection module 1 is using real-time target detection network YOLOv2 realization, the net Network includes 24 convolutional layers and 2 full articulamentums, and the frame for extracting vehicle is upper left corner extreme coordinates (X, Y) and long W, wide H, enabling the vehicle frame extracted is C={ carlisti| i=1,2 ..., n }, wherein carlistiFor the upper left corner of i-th frame Extreme coordinates and length and width, n indicate the quantity of detected vehicle；
The vehicle depth characteristic extraction and application depth convolutional neural networks of the vehicle characteristics extraction module 2 are realized, are extracted The vehicle characteristics arrived are the depth vehicle characteristics of 4096 dimensions, and enabling the vehicle characteristics vector extracted is F={ feati| i=1, 2 ... 4096 }, wherein featiIt indicates the feature of i-th dimension in vehicle characteristics vector, is float；
The vehicle contrast module 3 is the similarity calculated between vehicle according to formula (1)
Wherein Q, P respectively represent the feature vector of two cars, Q={ qi| i=1,2 ..., 4096 }, P={ pi| i=1, 2 ..., 4096 }, qiIndicate the ith feature value in feature vector Q, PiIndicate the ith feature value in feature vector P, K table Show vehicle characteristics dimension, s indicates Q, the similarity function of P two cars；
The vehicle violation detection module 4 is the comparing result calculated according to vehicle contrast module 3, if the phase between vehicle Like degree s > K0, K0For similarity threshold, then by this information of vehicles (cn,carlistn) be added similar vehicle set it is obtained disobey Picture is divided into four with center picture point pixel due to the particularity for picture of breaking rules and regulations by the similar vehicle set S of chapter target vehicle Region (first area, second area, third region and the fourth region), target violation vehicle is present in the fourth region, according to public affairs Formula (2) obtains the center point coordinate of the specific frame of vehicle, determines the position where similar vehicle,
Wherein, (Xc,Yc) it is similar vehicle center point coordinate, (X, Y) is the similar vehicle that vehicle detection module 1 detects Angle extreme coordinates on specific frame, W indicate that the width of specific frame, H indicate the height of specific frame, are judged according to similar vehicle center point coordinate Specific region where vehicle obtains each region similar vehicle set S1={ (cx,carlistx) | x=1,2 ..., n }, cx The specific number for indicating similar vehicle, enables D=max (S1), the specific frame for obtaining the similar vehicle where D is exactly current region Target violation vehicle judges whether all there is target violation vehicle in first area, second area and third region, if all depositing On the contrary then target violation vehicle determines violating the regulations, then be erroneous detection result.
As shown, the vehicle checking method of the automatic auditing system of picture violating the regulations based on vehicle retrieval of the present invention, including Following steps:
1) due to break rules and regulations picture particularity, with center picture point pixel by Fig. 2 by picture violating the regulations with center picture point picture Element is divided into four regions, and respectively first, second, third and the fourth region, the target violation vehicle that system detection goes out are present in The fourth region enables vehicle detection module (1) extract all vehicle characteristics in same picture from four regions of picture violating the regulations Vector setAnd detect that all vehicles and vehicle characteristics extraction module 2 extract the vehicle of all vehicles The mapping set of feature vector isWherein cjIndicate the number of jth vehicle, n is indicated Vehicle fleet size,Indicate the set of the feature vector of jth vehicle, Indicate jth K-th of vehicle characteristics vector in the vehicle characteristics set of vehicle；
2) the feature vector F of the fourth region target violation vehicle is extracted by vehicle characteristics extraction module 2m={ feati|i =1,2 ..., 4096, i indicates i-th of vehicle characteristics vector, and sends the eigenvector information of target violation vehicle to vehicle Contrast module 3；
3) vehicle contrast module 3 is by the vehicle characteristics vector for the target violation vehicle extracted according to formula (1) and step 1) all vehicle characteristics vector set in the same picture extracted inIn each vehicle characteristics vectorSimilarity, obtain similarity setIf the phase of two cars Like degree s > K0, K0For vehicle confidence threshold value, then by this information of vehicles (cn,carlistn) similar vehicle set, c is addednIt indicates Vehicle is specifically numbered, carlistnThe specific frame of vehicle position is indicated, thus to obtain the similar of all target vehicles violating the regulations Vehicle；
4) according to the similar vehicle set S of the target vehicle violating the regulations obtained in step 3), it is in place to obtain similar vehicle institute The specific frame set obtains the center point coordinate of the specific frame of vehicle according to formula (2), determines the position where similar vehicle,
Wherein, (Xc,Yc) it is similar vehicle center point coordinate, (X, Y) indicates the left apex coordinate of the specific frame of similar vehicle, W table Show that the width of specific frame, H indicate the height of specific frame；
Vehicle violation detection module 4 judges the specific region where vehicle according to similar vehicle center point coordinate, obtains every A region similar vehicle set S1={ (cx,carlistx) | x=1,2 ..., n }, cxIt indicates the specific number of similar vehicle, enables D=max (S1), the specific frame of the similar vehicle where D is obtained, is exactly the target violation vehicle of current region, if a region Middle there are the similar vehicles of more target violation vehicles, then select the maximum similar vehicle of similarity according to similar size, sentence Break as the target violation vehicle of current region, the lesser vehicle of similarity is excluded into violation vehicle judgement, judges three regions Whether all there is target violation vehicle in if all to exist, then target violation vehicle determines violating the regulations, as shown in Figure 3；It is on the contrary then be Erroneous detection result.

Claims (2)

1. a kind of automatic auditing system of picture violating the regulations based on vehicle retrieval, it is characterised in that by vehicle detection module (1), vehicle Characteristic extracting module (2), vehicle contrast module (3) and vehicle violation detection module (4) are constituted, the vehicle detection module (1), Vehicle contrast module (3) is connect with vehicle characteristics extraction module (2), vehicle violation detection module (4) respectively, vehicle detection module (1) for detecting all vehicles in picture violating the regulations；Vehicle characteristics extraction module (2) is used to detect vehicle detection module (1) Vehicle out carries out the extraction of vehicle depth characteristic；The target violation vehicle that vehicle contrast module (3) is used to judge system Vehicle characteristics are compared with the vehicle depth characteristic that vehicle characteristics extraction module (2) extracts vehicle in picture violating the regulations, calculate Vehicle characteristics matching degree out, and calculated result is sent to vehicle violation detection module (4)；Vehicle violation detection module (4) is received To vehicle contrast module (3) as a result, and the coordinate of corresponding vehicle that is extracted according to vehicle detection module (1), for violating the regulations It is positioned in vehicle with the same vehicle of target violation vehicle, determines violation vehicle further according to specific position.
2. a kind of vehicle checking method of the automatic auditing system of picture violating the regulations based on vehicle retrieval described in claim 1, special Sign is to include the following steps:
1) picture violating the regulations is divided into four regions with center picture point pixel, respectively first, second, third and the fourth region, The target violation vehicle that system detection goes out is present in the fourth region, enables four regions of the vehicle detection module (1) from picture violating the regulations In extract all vehicle characteristics vector set in same pictureAnd detect that all vehicles and vehicle are special The mapping set of sign extraction module (2) vehicle characteristics vector for extracting all vehicles isWherein cjIndicate that jth vehicle, n indicate vehicle fleet size,Indicate the spy of jth vehicle The set of vector is levied, Indicate k-th of vehicle in the vehicle characteristics set of jth vehicle Feature vector；
2) the feature vector F of the fourth region target violation vehicle is extracted by vehicle characteristics extraction module (2)m={ feati| i= 1,2 ..., 4096 }, i indicates i-th of vehicle characteristics vector, and sends the eigenvector information of target violation vehicle to vehicle Contrast module (3)；
3) vehicle contrast module (3) is by the vehicle characteristics vector for the target violation vehicle extracted according to formula (1) and step 1) In all vehicle characteristics vector set in the same picture that extractsIn each vehicle characteristics vectorSimilarity s, obtain similarity setIf the phase of two cars Like degree s > K0, K0For vehicle confidence threshold value, then by this information of vehicles (cn,carlistn) similar vehicle set, c is addednIt indicates Vehicle is specifically numbered, carlistnThe specific frame of vehicle position is indicated, thus to obtain the similar of all target vehicles violating the regulations Vehicle；
Wherein Q, P respectively represent the feature vector of two cars, Q={ qi| i=1,2 ..., 4096 }, P={ pi| i=1,2 ..., 4096 }, qiIndicate the ith feature value in feature vector Q, PiIndicate the ith feature value in feature vector P, K indicates vehicle Characteristic dimension, s indicate Q, the similarity function of P two cars；
4) according to the similar vehicle set s of the target vehicle violating the regulations obtained in step 3), similar vehicle position is obtained Specific frame obtains the center point coordinate of the specific frame of vehicle according to formula (2), determines the position where similar vehicle, obtain similar Vehicle center point coordinate (Xc,Yc)；
Wherein, (Xc,Yc) it is similar vehicle center point coordinate, (X, Y) indicates that the left apex coordinate of the specific frame of similar vehicle, W indicate tool The width of body frame, H indicate the height of specific frame；
Vehicle violation detection module (4) judges the specific region where vehicle according to similar vehicle center point coordinate, obtains each Region similar vehicle set S1={ (cx,carlistx) | x=1,2 ..., n }, cxThe specific number for indicating similar vehicle, enables D =max (S1), obtain D where similar vehicle specific frame be exactly current region target violation vehicle, judge first area, Whether all there is target violation vehicle in second area and third region, if all existing, then target violation vehicle determines violating the regulations, It is on the contrary then be erroneous detection result.
CN201910779521.4A 2019-08-22 2019-08-22 Automatic illegal picture auditing system and method based on vehicle retrieval Active CN110490150B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910779521.4A CN110490150B (en) 2019-08-22 2019-08-22 Automatic illegal picture auditing system and method based on vehicle retrieval

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910779521.4A CN110490150B (en) 2019-08-22 2019-08-22 Automatic illegal picture auditing system and method based on vehicle retrieval

Publications (2)

Publication Number Publication Date
CN110490150A true CN110490150A (en) 2019-11-22
CN110490150B CN110490150B (en) 2022-02-11

Family

ID=68552807

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910779521.4A Active CN110490150B (en) 2019-08-22 2019-08-22 Automatic illegal picture auditing system and method based on vehicle retrieval

Country Status (1)

Country Link
CN (1) CN110490150B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111429726A (en) * 2020-04-13 2020-07-17 城云科技（中国）有限公司 Monitoring video illegal parking vehicle detection and management method and corresponding system
CN111444901A (en) * 2020-06-17 2020-07-24 爱保科技有限公司 Processing method and device for distinguishing multiple vehicles from pictures in vehicle insurance case and electronic equipment
CN111767917A (en) * 2019-12-24 2020-10-13 杭州海康威视数字技术股份有限公司 Violation evidence picture detection method and device and electronic equipment
CN111768630A (en) * 2019-12-24 2020-10-13 上海高德威智能交通系统有限公司 Violation waste image detection method and device and electronic equipment
CN112101268A (en) * 2020-09-23 2020-12-18 浙江浩腾电子科技股份有限公司 Vehicle line pressing detection method based on geometric projection

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130279742A1 (en) * 2012-04-18 2013-10-24 Ivs, Inc. Automatic record detection device and method for stop arm violation event
US20150332097A1 (en) * 2014-05-15 2015-11-19 Xerox Corporation Short-time stopping detection from red light camera videos
CN109949578A (en) * 2018-12-31 2019-06-28 上海眼控科技股份有限公司 A kind of illegal automatic auditing method of vehicle crimping based on deep learning
CN109948417A (en) * 2018-12-31 2019-06-28 上海眼控科技股份有限公司 A kind of vehicle based on deep learning drives in the wrong direction illegal automatic auditing method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130279742A1 (en) * 2012-04-18 2013-10-24 Ivs, Inc. Automatic record detection device and method for stop arm violation event
US20150332097A1 (en) * 2014-05-15 2015-11-19 Xerox Corporation Short-time stopping detection from red light camera videos
CN109949578A (en) * 2018-12-31 2019-06-28 上海眼控科技股份有限公司 A kind of illegal automatic auditing method of vehicle crimping based on deep learning
CN109948417A (en) * 2018-12-31 2019-06-28 上海眼控科技股份有限公司 A kind of vehicle based on deep learning drives in the wrong direction illegal automatic auditing method

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111767917A (en) * 2019-12-24 2020-10-13 杭州海康威视数字技术股份有限公司 Violation evidence picture detection method and device and electronic equipment
CN111768630A (en) * 2019-12-24 2020-10-13 上海高德威智能交通系统有限公司 Violation waste image detection method and device and electronic equipment
CN111429726A (en) * 2020-04-13 2020-07-17 城云科技（中国）有限公司 Monitoring video illegal parking vehicle detection and management method and corresponding system
CN111429726B (en) * 2020-04-13 2021-11-26 城云科技（中国）有限公司 Monitoring video illegal parking vehicle detection and management method and corresponding system
CN111444901A (en) * 2020-06-17 2020-07-24 爱保科技有限公司 Processing method and device for distinguishing multiple vehicles from pictures in vehicle insurance case and electronic equipment
CN112101268A (en) * 2020-09-23 2020-12-18 浙江浩腾电子科技股份有限公司 Vehicle line pressing detection method based on geometric projection
CN112101268B (en) * 2020-09-23 2022-07-29 浙江浩腾电子科技股份有限公司 Vehicle line pressing detection method based on geometric projection

Also Published As

Publication number Publication date
CN110490150B (en) 2022-02-11

Similar Documents

Publication Publication Date Title
CN110490150A (en) A kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval
US11455805B2 (en) Method and apparatus for detecting parking space usage condition, electronic device, and storage medium
CN106373426B (en) Parking stall based on computer vision and violation road occupation for parking monitoring method
CN103500322B (en) Automatic lane line identification method based on low latitude Aerial Images
CN109977782B (en) Cross-store operation behavior detection method based on target position information reasoning
CN104303193B (en) Target classification based on cluster
CN104978567B (en) Vehicle checking method based on scene classification
CN102915433B (en) Character combination-based license plate positioning and identifying method
CN102867417B (en) Taxi anti-forgery system and taxi anti-forgery method
CN107886507B (en) A kind of salient region detecting method based on image background and spatial position
CN112883820B (en) Road target 3D detection method and system based on laser radar point cloud
CN104166841A (en) Rapid detection identification method for specified pedestrian or vehicle in video monitoring network
Li et al. Research on vehicle license plate location based on neural networks
CN104616502A (en) License plate identification and positioning system based on combined type vehicle-road video network
CN112183472A (en) Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet
CN103164958B (en) Method and system for vehicle monitoring
CN103679214B (en) Vehicle checking method based on online Class area estimation and multiple features Decision fusion
CN111898491A (en) Method and device for identifying reverse driving of vehicle and electronic equipment
CN104143077B (en) Pedestrian target search method and system based on image
CN104463232A (en) Density crowd counting method based on HOG characteristic and color histogram characteristic
CN109522831A (en) A kind of vehicle real-time detection method based on micro- convolutional neural networks
CN110147748A (en) A kind of mobile robot obstacle recognition method based on road-edge detection
CN113158954B (en) Automatic detection method for zebra crossing region based on AI technology in traffic offsite
CN110188607A (en) A kind of the traffic video object detection method and device of multithreads computing
CN115440071B (en) Automatic driving illegal parking detection 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
GR01 Patent grant
GR01 Patent grant