CN101739829B - Video-based vehicle overspeed monitoring method and system - Google Patents
Video-based vehicle overspeed monitoring method and system Download PDFInfo
- Publication number
- CN101739829B CN101739829B CN200910242053.3A CN200910242053A CN101739829B CN 101739829 B CN101739829 B CN 101739829B CN 200910242053 A CN200910242053 A CN 200910242053A CN 101739829 B CN101739829 B CN 101739829B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- video
- pixel
- overspeed
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 230000000007 visual effect Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 9
- 230000033001 locomotion Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 230000002349 favourable effect Effects 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007688 edging Methods 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 2
- 230000006698 induction Effects 0.000 abstract description 2
- 230000006855 networking Effects 0.000 abstract description 2
- 230000033228 biological regulation Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000005484 gravity Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 206010038743 Restlessness Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a video-based vehicle overspeed monitoring method and a video-based vehicle overspeed monitoring system. The method comprises the following steps: firstly, performing standardization and enhancement on originally acquired images through image pretreatment; then, acquiring the vehicle speed of a dynamic target through dynamic target segmentation, the dynamic target tracking and the vehicle speed measurement, and judging whether the dynamic target is overspeed through the vehicle speed; and finally, finishing the identification of the plate number of the dynamic target and transmitting the data to a monitoring center through the plate number positioning and character recognition. The video-based vehicle overspeed monitoring system realizes full-automatic monitoring and networking, and has convenient erection, low cost and higher practical value. The video-based vehicle overspeed monitoring system has strong universality, strong openness, and strong extensibility. In addition, the video-based vehicle overspeed monitoring system is unnecessarily embedded with a wayside induction coil, adopts video to detect the overspeed state in a non-contact way, integrates the vehicle speed measurement and the plate number identification at the front end of the system, and has low requirement on the communication bandwidth.
Description
Technical field
The present invention relates to intelligent mapping techniques field, be specifically related to a kind of method for monitoring overspeed of vehicle and system based on video.
Background technology
Along with the fast development of national economy, the vehicle travelling on highway is more and more, and speed is also more and more faster, and the case relevant with vehicular traffic is also continuous ascendant trend, and the cases such as escaping behavior after traffic accident happen occasionally.How to use the means of science to help public security department effectively to control overspeed violation phenomenon on highway, arrest escape vehicle, become public security traffic department problem anxious to be resolved.
The mature system that at present, can complete monitoring overspeed function has: based on microwave radar and the overspeed monitoring system based on laser.They through out-of-date, utilize the frequency change of transmitted wave to carry out the information of monitoring vehicle at vehicle, and still, this system can not provide the comprehensively transport information such as the type, license plate number of hypervelocity automobile, the processing and arrest escape vehicle of cannot break rules and regulations in time.
Summary of the invention
For problems of the prior art, the object of this invention is to provide a kind of method for monitoring overspeed and system based on video.The method and system can be utilized video image processing technology, by video frequency speed-measuring and license plate recognition technology, automobile on highway track is carried out to contactless monitoring, obtain the running state information such as the over-speed vehicles speed of a motor vehicle, the number-plate number, photo violating the regulations, can be applicable to highway administration, escape vehicle and the occasion such as arrest.
For achieving the above object, the technical solution used in the present invention is: a kind of method for monitoring overspeed of vehicle based on video, comprises the following steps:
(1) utilize the video image on camera Real-time Collection highway, and by image digitazation;
(2) image after above-mentioned digitizing is carried out to pre-service, described pre-service comprises the geometric correction of imagery, figure image intensifying and image filtering;
(3) according to whether having vehicle in pretreated spectral discrimination visual field, and determine movement locus and the travel speed that has vehicle;
(4) to occurring in step (3) that the car plate of vehicle identifies;
(5) according to the travel speed of vehicle, judge that whether vehicle exceeds the speed limit, and is if it is sent to Surveillance center by the video image of the travel speed of the license plate number of this vehicle, vehicle, vehicle and reports to the police.
Further, the method is further comprising the steps of: (6) judge that according to license plate number whether vehicle is hit-and-run vehicle or other vehicles that need monitoring, is if it is sent to Surveillance center by the video image of the license plate number of this vehicle, vehicle and reports to the police.
For realizing said method, the invention provides a kind of overspeed monitoring system for vehicle based on video, comprise with lower device:
Video image acquisition and digitalizer: for passing through the video image on camera Real-time Collection highway, and by image digitazation;
Image preprocess apparatus: carry out pre-service for the image to after digitizing, described pre-service comprises the geometric correction of imagery, figure image intensifying and image filtering;
Vehicle detection apparatus: for judging whether pretreated image visual field exists vehicle, and determine movement locus and the travel speed that has vehicle;
License plate recognition device: for the car plate of the vehicle detecting is identified;
Warning device: for judging that whether the travel speed of vehicle exceeds the speed limit, and if it is reaches Surveillance center by the video image of the travel speed of the license plate number of this vehicle, vehicle, vehicle.
Further, described warning device is also for judging whether the vehicle detecting is hit-and-run vehicle or other vehicles that need monitoring, if it is the video image of the license plate number of this vehicle, vehicle is reached to Surveillance center.
Effect of the present invention is: adopt method and system of the present invention, realized Full-automatic monitoring and the networking of overspeed monitoring system, set up conveniently, cost is not high, there is higher practical value, can obtain in time the running state information such as the speed of a motor vehicle, the number-plate number and photo violating the regulations.The automatic car plate recognition speed of the present invention is fast, accuracy rate is high, in real time violating the regulations process provide may, and this system highly versatile, open strong, extendability is strong; In addition, this system, without burying ground induction coil underground, adopts video non-contact detecting overspeed condition, and vehicle speed measurement and car plate identification are integrated in to system front end, and communication bandwidth requires little.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of method for monitoring overspeed of vehicle based on video in the embodiment of the present invention;
Fig. 2 is the system chart of a kind of overspeed monitoring system for vehicle based on video in the embodiment of the present invention;
Fig. 3 is the process flow diagram of car plate recognition processing module in the embodiment of the present invention;
Fig. 4 is the schematic diagram of the character recognition decision tree of character recognition module in the embodiment of the present invention.
Embodiment
Below in conjunction with Figure of description and embodiment, the present invention is described further.
The invention provides a kind of method for monitoring overspeed of vehicle based on video, as shown in Figure 1, it comprises the following steps:
Step S11: image acquisition and digitizing;
Utilize the video image on camera Real-time Collection highway, and by the video image digitizing collecting.
Step S12: image pre-service;
Image after above-mentioned digitizing is carried out to pre-service, and described pre-service comprises the geometric correction of imagery, figure image intensifying and image filtering.In the present embodiment, what image unification adopted is 256 rank gray level images, by the method for gray level expansion, strengthens image.By gradation of image scope linear expansion, to 0--255, image car plate sharpness after treatment obviously improves.What image filtering adopted is nonlinear median filtering algorithm, and this filtering is verified has very strong noise suppression effect.Consider the efficiency of algorithm, do not carry out the medium filtering of two-dimentional 8 neighborhoods, wherein only in every a line, carry out one-dimensional filtering, i.e. I (x)=median (I (x-1), I (x), I (x+1));
Step S13: vehicle detection;
According to whether having vehicle in pretreated spectral discrimination visual field, and determine movement locus and the travel speed that has vehicle;
While carrying out over-speed vehicles detection from video image, can adopt based on frame differential method the method based on background difference and the method based on optical flow field.In the present embodiment, have the feature of strong correlation according to handled video image, adopted inter-frame difference object detection method, concrete grammar is:
1) dynamical object segmentation;
Gray level image is changed into black and white binary image, target rough edge profile is carried out to mathematical morphology filter to remove ground unrest, extract and detect objective contour and other parameters, obtain entering the object size parameter of visual field, wherein, by formula below, realize during the conversion of image:
Wherein, I
t-1(x, y) is t-1 visual pixel (x, y) gray scale constantly; I
t(x, y) is t visual pixel (x, y) gray scale constantly; T, for setting thresholding, gets 8-16 in the present invention.
2) dynamic target tracking and travel speed are measured;
Based on step 1) in the motion target area that obtains, carry out dynamic target tracking and movement velocity and estimate.In the present embodiment, adopt the method for traditional Feature Points Matching to carry out tracking of maneuvering target, to utilize the disparity computation speed of a motor vehicle of unique point.Its main points are: in the moving target window of a two field picture, select one group of unique point with invariance, do to mate, thereby try to achieve parallax with the similar unique point in next frame image.The method of Feature Points Matching that Here it is.
Adopt Moravac operator as feature point extraction operator.It is based on a desirable unique point, and in all directions of its surrounding, gray scale has very large variance.
The step of described feature point extraction comprises:
A. calculate the favorable values M of pixel:
In formula, i=n-2 ..., n+2; J=m-2 ..., m+2; M, n is the row, column sequence of window center pixel, g
i, jfor (i, j) locates the gray-scale value of image;
B. determine alternative features point, if the favorable values M of pixel is greater than empirical value, this pixel is alternative features point; Otherwise this pixel is not unique point;
C. by the method that suppresses local non-maximum M value, determine unique point;
Check whether the M value of each alternative features point is the maximal value in a certain size 5 * 5 window, if there are several alternative features points in window, get the maximum pixel of M value as unique point, all the other all remove.For guaranteeing the accuracy of coupling, adopt the maximum and poor absolute value sum minimum of covariance as dual criterion, determine the choice of match point, to strengthen the reliability of matching result.Find after match point, utilize both parallaxes and the visual field in advance demarcated in the minor increment of image minimum resolution representative and the interval time of image acquisition, just can calculate target velocity, according to this value prediction target reposition and judge whether hypervelocity.
Step S14: car plate identification;
Car plate identification comprises car plate location and character recognition, and car plate location mainly comprises the location in vehicle license region and cutting apart of character;
1) location in vehicle license region, the steps include:
A. utilize the horizontal edge of colour edging sobel operator extraction image;
B. utilize global threshold method to carry out binaryzation to gradient image;
C. the gradient image after binaryzation is carried out to Morphology level expansion;
2) realize cutting apart by vertical projection method of character, due to the inevitable gap location in intercharacter or character of projection in vertical direction of character obtain local minimum near, and this position should meet character writing form, character, size restrictions and some other conditions of licence plate.Utilize vertical projection method to have good effect to the Character segmentation in the automobile image under complex environment, its concrete steps are:
A, first bottom-up image being lined by line scan until run into the pixel of first black and record, more from top to bottom image is lined by line scan until find first black picture element, determine image altitude range roughly;
B, in described altitude range roughly, scan by column from left to right, while running into first black picture element, think the reference position of Character segmentation, continue scanning, until run into have in row, there is no black picture element, think that this Character segmentation finishes, then according to above-mentioned method, scan until the low order end of image always, obtain the more accurate width range of each character;
C, in the known accurate width range of each charactor comparison, according to the method for the first step, respectively from top to bottom and from bottom to top line by line scan to obtain the accurate altitude range of each character.
3) behind car plate location, will identify character.License plate recognition technology is after deliberation more ripe, mainly contains at present based on template matching algorithm with based on artificial neural network algorithm.Based on template matching algorithm, first by the character binaryzation after cutting apart, and its size is scaled to the size of template in character database, then mates with all templates, finally select optimum matching as a result of.Algorithm based on artificial neural network is treated identification character and is carried out feature extraction, then by obtained feature, carrys out neural network training divider.
In the present embodiment, the identification of character is known method for distinguishing by neural network and is realized: according to the feature of the character extracting, send into character recognition decision tree as shown in Figure 4, utilize character recognition decision tree to analyze specifically which character of each character splitting.
The feature of described character specifically comprises:
1) number of edges
Refer to that the edge of a character is communicated with the number of profile, if the number of edges of character 6 is 2;
2) edge gravity center
The character that edge gravity center is 2 mainly for number of edges, calculates respectively the coordinate of top, two edges and bottom, is designated as y
edge1 top, y
edge1 bottom, y
edge2 top, y
edge2 bottom, then the difference at these two edges of asking respectively
So work as D
top/ D
bottom< 0.5, and edge gravity center is at the first half; Work as D
top/ D
bottom> 2, and edge gravity center is in Lower Half;
3) contour feature value
Utilize the single order differential variation tendency definition of profile to form the elementary cell of character outline, be divided into five classes: left tiltedly, right tiltedly, straight line, circular arc, sudden change;
4) duty information
The all directions that utilizes top, bottom, left side, the right side of contour feature calculating character image and 45 degree that are clipped in the middle to the duty amount in totally 12 regions;
5) stroke number
Take to a certain position of character up and down or left and right draw arbitrarily straight line, check its number of times through white portion;
6) projection
Character is carried out vertically and horizontal projection to the projection amount of statistics diverse location;
7) nose
Calculate vertically or the white line length of horizontal direction connected region, then find out wherein long one, can look for also and can look in certain region in entire image;
8) Area Ratio
Calculate the area that character is put in a certain region, be mainly used to distinguish characters such as " 0 " or " D " and " Q ".The black region that need comprise white connected region while quadraturing is filled.
Step S15: judge that according to the travel speed of vehicle whether vehicle exceeds the speed limit, and is if it is sent to Surveillance center by the data such as video image of the travel speed of the license plate number of this vehicle, vehicle, vehicle.
According to license plate number, judge that whether vehicle is hit-and-run vehicle or other vehicles that need monitoring, is if it is sent to Surveillance center by the data such as video image of the license plate number of this vehicle, vehicle.
For realizing said method, the invention provides a kind of overspeed monitoring system based on video, as shown in Figure 2, it comprises with lower module:
Video image acquisition and digitalizer 21: for passing through the video image on camera Real-time Collection highway, and by image digitazation;
Image preprocess apparatus 22: carry out pre-service for the image to after digitizing, described pre-service comprises the geometric correction of imagery, figure image intensifying and image filtering;
Vehicle detection apparatus 23: for judging whether pretreated image visual field exists vehicle, and determine movement locus and the travel speed that has vehicle;
License plate recognition device 24: for the car plate of the vehicle detecting is identified;
Data link 25: for judging that whether the travel speed of vehicle exceeds the speed limit, and if it is reaches Surveillance center by the data such as video image of the travel speed of the license plate number of this vehicle, vehicle, vehicle.
Described warning device 25 is also for judging whether the vehicle detecting is hit-and-run vehicle or other vehicles that need monitoring, if it is the data such as video image of the license plate number of this vehicle, vehicle is reached to Surveillance center.
As shown in Figure 2, vehicle detection apparatus 23 comprises Target Segmentation module 231, target tracking module 232 and speed measurement module 233.License plate recognition device 24 comprises car plate identification module 241 and character recognition module 242.
As shown in Figure 3, for vehicle detection apparatus 23, its workflow is: first utilize colour edging sobel operator (medium filtering S31) to extract the horizontal edge of image, utilize global threshold method to carry out image binaryzation S32 to gradient image, then the gradient image after binaryzation is carried out to the adjustment S33 that Morphology level expansion completes degree of tilt, then by Character segmentation S34, adopt the identification that completes character based on artificial neural network algorithm identification S35, finally complete information output.
An application example on highway: adopt method and system proposed by the invention, first front monitoring front-end gathers the panoramic picture of highway by camera, and utilize panoramic picture to carry out over-speed vehicles detection, as vehicles peccancy detected, start the work of close shot high-definition camera, gather close shot image and utilize the automatic car plate identification of close shot image, its recognition result can minute number-plate number character, number-plate number photo, vehicle driving against traffic regulations photo are saved in respectively overspeed violation vehicle data storehouse, for process afterwards; By wireless or cable data delivery module, from the processing server violating the regulations at trend freeway facility center, transmit the number-plate number of vehicles peccancy, photographic intelligence violating the regulations, to break rules and regulations in real time, process.The invention belongs to a kind of intelligent mapping techniques, can improve the effect of visualization of image, strengthen picture contrast, guarantee that under dark surrounds, camera maintains the frame per second of publishing picture at a high speed.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technology thereof, the present invention is also intended to comprise these changes and modification interior.
Claims (8)
1. the method for monitoring overspeed of vehicle based on video, its step comprises:
(1) utilize the video image on camera Real-time Collection highway, and by image digitazation;
(2) image after above-mentioned digitizing is carried out to pre-service, described pre-service comprises the geometric correction of imagery, figure image intensifying and image filtering;
(3) according to whether having vehicle in pretreated spectral discrimination visual field, and determine movement locus and the travel speed that has vehicle; When carrying out over-speed vehicles detection, adopt based on frame differential method, specifically comprise the following steps:
1) dynamical object segmentation;
The detection of over-speed vehicles realizes by inter-frame difference object detection method, concrete grammar is: gray level image is changed into black and white binary image, target rough edge profile is carried out to mathematical morphology filter, extraction detects objective contour parameter, obtain entering the object size parameter of visual field, wherein, by formula below, realize during the conversion of image:
Wherein, I
t-1(x, y) is t-1 visual pixel (x, y) gray scale constantly; I
t(x, y) is t visual pixel (x, y) gray scale constantly; T is for setting thresholding, and its span is 8-16;
2) dynamic target tracking and travel speed are measured;
In the moving target window of a two field picture, select one group of unique point with invariance, do to mate, thereby try to achieve parallax with the similar unique point in next frame image, the tracking of dynamic object is that the method by Feature Points Matching realizes;
The step of described feature point extraction comprises:
A. calculate the favorable values M of pixel:
In formula, i=n-2 ..., n+2; J=m-2 ..., m+2; M, n is the row, column sequence of window center pixel, g
i,jfor (i, j) locates the gray-scale value of image;
B. determine alternative features point, if the favorable values M of pixel is greater than empirical value, this pixel is alternative features point; Otherwise this pixel is not unique point;
C. by the method that suppresses local non-maximum M value, determine unique point, concrete grammar is: the M value of each alternative features point in check window, get the maximum pixel of M value as unique point;
(4) to occurring in step (3) that the car plate of vehicle identifies;
(5) according to the travel speed of vehicle, judge that whether vehicle exceeds the speed limit, and is if it is sent to Surveillance center by the video image of the travel speed of the license plate number of this vehicle, vehicle, vehicle.
2. a kind of method for monitoring overspeed of vehicle based on video as claimed in claim 1, is characterized in that, the method also comprises:
(6) according to license plate number, judge that whether vehicle is hit-and-run vehicle or other vehicles that need monitoring, is if it is sent to Surveillance center by the video image of the license plate number of this vehicle, vehicle.
3. a kind of method for monitoring overspeed of vehicle based on video as claimed in claim 1, it is characterized in that: in step (2), what described figure image intensifying adopted is the method for gray level expansion, what described image filtering adopted is nonlinear median filtering algorithm, wherein only in every a line, carries out one-dimensional filtering.
4. a kind of method for monitoring overspeed of vehicle based on video as claimed in claim 1, it is characterized in that: the calculating of dynamic object speed is by finding after match point, the minor increment of image minimum resolution representative and calculate the interval time of image acquisition in the visual field that utilizes both parallaxes and demarcated in advance, and judge whether hypervelocity according to result of calculation.
5. a kind of method for monitoring overspeed of vehicle based on video as described in one of claims 1 to 3, is characterized in that, in step (4), described car plate is known method for distinguishing and comprised the following steps:
1) location in vehicle license region, the steps include:
A. utilize the horizontal edge of colour edging sobel operator extraction image;
B. utilize global threshold method to carry out binaryzation to gradient image;
C. the gradient image after binaryzation is carried out to Morphology level expansion;
2) adopt vertical projection method that vehicle license Region Segmentation is become to single character;
3) the single character extracting after cutting apart is identified.
6. a kind of method for monitoring overspeed of vehicle based on video as claimed in claim 5, it is characterized in that, step 3) in, employing is identified character based on artificial neural network algorithm, be specially: the feature of extracting character, according to the character feature extracting, send into character recognition decision tree, utilize the concrete character of character recognition decision tree Analysis deterrmination.
7. the overspeed monitoring system for vehicle based on video, it comprises with lower device:
Video image acquisition and digitalizer: for passing through the video image on camera Real-time Collection highway, and by image digitazation;
Image preprocess apparatus: carry out pre-service for the image to after digitizing, described pre-service comprises the geometric correction of imagery, figure image intensifying and image filtering;
Vehicle detection apparatus: for judging whether pretreated image visual field exists vehicle, and determine movement locus and the travel speed that has vehicle; When carrying out over-speed vehicles detection, adopt based on frame differential method, specifically comprise the following steps:
1) dynamical object segmentation;
The detection of over-speed vehicles realizes by inter-frame difference object detection method, concrete grammar is: gray level image is changed into black and white binary image, target rough edge profile is carried out to mathematical morphology filter, extraction detects objective contour parameter, obtain entering the object size parameter of visual field, wherein, by formula below, realize during the conversion of image:
Wherein, I
t-1(x, y) is t-1 visual pixel (x, y) gray scale constantly; I
t(x, y) is t visual pixel (x, y) gray scale constantly; T is for setting thresholding, and its span is 8-16;
2) dynamic target tracking and travel speed are measured;
In the moving target window of a two field picture, select one group of unique point with invariance, do to mate, thereby try to achieve parallax with the similar unique point in next frame image, the tracking of dynamic object is that the method by Feature Points Matching realizes;
The step of described feature point extraction comprises:
A. calculate the favorable values M of pixel:
In formula, i=n-2 ..., n+2; J=m-2 ..., m+2; M, n is the row, column sequence of window center pixel, g
i,jfor (i, j) locates the gray-scale value of image;
B. determine alternative features point, if the favorable values M of pixel is greater than empirical value, this pixel is alternative features point; Otherwise this pixel is not unique point;
C. by the method that suppresses local non-maximum M value, determine unique point, concrete grammar is: the M value of each alternative features point in check window, get the maximum pixel of M value as unique point;
License plate recognition device: for the car plate of the vehicle detecting is identified;
Warning device: for judging that whether the travel speed of vehicle exceeds the speed limit, and if it is reaches Surveillance center by the video image of the travel speed of the license plate number of this vehicle, vehicle, vehicle.
8. a kind of overspeed monitoring system for vehicle based on video as claimed in claim 7, it is characterized in that: described warning device is also for judging whether the vehicle detecting is other vehicles of hit-and-run vehicle or needs monitoring, if it is the video image of the license plate number of this vehicle, vehicle is reached to Surveillance center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910242053.3A CN101739829B (en) | 2009-12-03 | 2009-12-03 | Video-based vehicle overspeed monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910242053.3A CN101739829B (en) | 2009-12-03 | 2009-12-03 | Video-based vehicle overspeed monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101739829A CN101739829A (en) | 2010-06-16 |
| CN101739829B true CN101739829B (en) | 2014-04-23 |
Family
ID=42463258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910242053.3A Active CN101739829B (en) | 2009-12-03 | 2009-12-03 | Video-based vehicle overspeed monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101739829B (en) |
Families Citing this family (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622575A (en) * | 2011-01-31 | 2012-08-01 | 日电（中国）有限公司 | Baseline band video monitoring system and monitoring method |
| CN102323070B (en) * | 2011-06-10 | 2015-04-08 | 北京华兴致远科技发展有限公司 | Method and system for detecting abnormality of train |
| CN102768731A (en) * | 2012-06-29 | 2012-11-07 | 陕西省交通规划设计研究院 | Method and system for automatic positioning and identifying target based on high definition video images |
| CN102855467A (en) * | 2012-07-30 | 2013-01-02 | 上海未来软件有限公司 | Method for extracting and identifying plate numbers from video streaming |
| CN102982311B (en) * | 2012-09-21 | 2016-03-30 | 公安部第三研究所 | Based on automobile video frequency Feature Extraction System and the method for video structural description |
| CN103714528B (en) * | 2012-09-28 | 2017-08-04 | 株式会社理光 | Object segmentation device and method |
| CN102902965B (en) * | 2012-10-09 | 2016-07-06 | 公安部第三研究所 | Realize the method that the vedio data structural description of multiple target tracking processes |
| CN103106798A (en) * | 2012-12-20 | 2013-05-15 | 黑龙江省电力有限公司信息通信分公司 | Image recognition triggering traffic speed measuring photograph system |
| CN103413325B (en) * | 2013-08-12 | 2016-04-13 | 大连理工大学 | A kind of speed of a motor vehicle authentication method based on vehicle body positioning feature point |
| CN103903448B (en) * | 2014-04-21 | 2015-09-09 | 闽南师范大学 | A kind of traffic intersection based on license plate recognition technology is broken rules and regulations method for detecting |
| CN104050818B (en) * | 2014-06-30 | 2016-03-16 | 武汉烽火众智数字技术有限责任公司 | The moving vehicle speed-measuring method of based target tracking and Feature Points Matching |
| CN104282147A (en) * | 2014-09-27 | 2015-01-14 | 无锡市恒通智能交通设施有限公司 | Intelligent vehicle monitor method |
| CN104918015A (en) * | 2015-06-04 | 2015-09-16 | 广州长视电子有限公司 | High-speed operation object-recognizable video monitoring system for expressways |
| CN104967817A (en) * | 2015-06-18 | 2015-10-07 | 黑龙江八一农垦大学 | Computer image processing system |
| CN106856044A (en) * | 2015-12-08 | 2017-06-16 | 黄波 | It is a kind of based on wireless technology can anti-intrusion traffic surveillance and control system |
| CN105608903A (en) * | 2015-12-15 | 2016-05-25 | 重庆凯泽科技有限公司 | Traffic violation detection method and system |
| CN105354573B (en) * | 2015-12-15 | 2019-03-22 | 重庆凯泽科技股份有限公司 | A kind of container licence plate recognition method and system |
| CN106709927A (en) * | 2016-12-27 | 2017-05-24 | 浙江大学 | Method for extracting target from acoustic image under complex background |
| CN106652414A (en) * | 2016-12-30 | 2017-05-10 | 杭州联络互动信息科技股份有限公司 | Method and device for interaction between smart watch and central control system of automobile |
| CN107909823A (en) * | 2017-04-12 | 2018-04-13 | 深圳市哈工大业信息技术股份有限公司 | A kind of multi-functional license plate recognition device |
| CN108470453B (en) * | 2018-03-16 | 2021-01-01 | 长安大学 | Vehicle straight-going speed calculation method |
| CN108320531A (en) * | 2018-04-04 | 2018-07-24 | 武汉市技领科技有限公司 | A kind of speed measuring equipment and velocity-measuring system |
| CN110769175B (en) | 2018-07-27 | 2022-08-09 | 华为技术有限公司 | Intelligent analysis system, method and device |
| CN109375177B (en) * | 2018-08-30 | 2020-12-08 | 安徽四创电子股份有限公司 | Moving target detection method for airport scene surveillance radar system |
| CN109543598A (en) * | 2018-11-20 | 2019-03-29 | 哈尔滨工程大学 | A kind of highway accident response and warning system and method based on image recognition |
| CN109697857A (en) * | 2019-01-18 | 2019-04-30 | 合肥米佑信息技术有限公司 | Intelligent traffic control system based on image recognition and neural network algorithm |
| CN110147788B (en) * | 2019-05-27 | 2021-09-21 | 东北大学 | Feature enhancement CRNN-based metal plate strip product label character recognition method |
| CN110286248A (en) * | 2019-06-26 | 2019-09-27 | 贵州警察学院 | A kind of vehicle speed measuring method based on video image |
| CN111814602B (en) * | 2020-06-23 | 2022-06-17 | 成都信息工程大学 | Intelligent vehicle environment dynamic target detection method based on vision |
| CN114078331B (en) * | 2020-08-19 | 2023-02-17 | 北京万集科技股份有限公司 | Overspeed detection method, overspeed detection device, visual sensor and storage medium |
| CN112863193B (en) * | 2021-01-06 | 2022-11-01 | 厦门大学 | Monitoring system and method for running vehicles in tunnel |
| CN114066968A (en) * | 2021-11-05 | 2022-02-18 | 郑州高识智能科技有限公司 | Vehicle speed measuring method based on visual image processing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0631683B1 (en) * | 1992-03-20 | 2001-08-01 | Commonwealth Scientific And Industrial Research Organisation | An object monitoring system |
| CN101187671A (en) * | 2007-12-27 | 2008-05-28 | 北京中星微电子有限公司 | Method and device for determining automobile driving speed |
| CN101246551A (en) * | 2008-03-07 | 2008-08-20 | 北京航空航天大学 | Fast license plate locating method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000333158A (en) * | 1999-05-19 | 2000-11-30 | Hitachi Denshi Ltd | Image transmission system |
-
2009
- 2009-12-03 CN CN200910242053.3A patent/CN101739829B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0631683B1 (en) * | 1992-03-20 | 2001-08-01 | Commonwealth Scientific And Industrial Research Organisation | An object monitoring system |
| CN101187671A (en) * | 2007-12-27 | 2008-05-28 | 北京中星微电子有限公司 | Method and device for determining automobile driving speed |
| CN101246551A (en) * | 2008-03-07 | 2008-08-20 | 北京航空航天大学 | Fast license plate locating method |
Non-Patent Citations (3)
| Title |
|---|
| 孙华燕等.高速公路视频超速监控系统的实现.《计算机应用》.2004,(第7期), |
| 宋焕生等.一种新的汽车牌照识别的图像增强算法.《长安大学学报（自然科学版）》.2006,第26卷(第4期), * |
| 高速公路视频超速监控系统的实现;孙华燕等;《计算机应用》;20040731(第7期);正文11-13页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101739829A (en) | 2010-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101739829B (en) | Video-based vehicle overspeed monitoring method and system | |
| 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 | |
| CN102765365B (en) | Pedestrian detection method based on machine vision and pedestrian anti-collision warning system based on machine vision | |
| CN100403332C (en) | Vehicle lane Robust identifying method for lane deviation warning | |
| CN101030256B (en) | Method and apparatus for cutting vehicle image | |
| CN105216797B (en) | Method of overtaking and system | |
| CN109299674B (en) | Tunnel illegal lane change detection method based on car lamp | |
| CN104331910A (en) | Track obstacle detection system based on machine vision | |
| EP2879113A1 (en) | Three-dimensional object detection device, three-dimensional object detection method | |
| CN111198371A (en) | Forward-looking obstacle detection system | |
| CN105047019B (en) | A kind of passenger stock prevent rear car overtake other vehicles after lane change determination methods and device suddenly | |
| CN103324930A (en) | License plate character segmentation method based on grey level histogram binaryzation | |
| CN102314599A (en) | Identification and deviation-detection method for lane | |
| CN104778444A (en) | Method for analyzing apparent characteristic of vehicle image in road scene | |
| CN109948552B (en) | Method for detecting lane line in complex traffic environment | |
| KR101756848B1 (en) | Unlawfulness parking and no standing control system and method thereof | |
| EP2741234B1 (en) | Object localization using vertical symmetry | |
| CN103440785B (en) | One is traffic lane offset warning method fast | |
| KR101406316B1 (en) | Apparatus and method for detecting lane | |
| CN105678287A (en) | Ridge-measure-based lane line detection method | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
| CN111899514A (en) | Artificial intelligence's detection system that blocks up | |
| FAN et al. | Robust lane detection and tracking based on machine vision | |
| US20210114611A1 (en) | System for performing effective identification of vehicle line pressing and giving early prompt |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180408 Address after: 100191 Xueyuan Road, Haidian District, Haidian District, Beijing, No. 607, No. six Patentee after: Beijing Vimicro AI Chip Technology Co Ltd Address before: 100083, Haidian District, Xueyuan Road, Beijing No. 35, Nanjing Ning building, 15 Floor Patentee before: Beijing Vimicro Corporation |
|
| TR01 | Transfer of patent right |