CN106127143A - A kind of highway parking offense detection method - Google Patents
A kind of highway parking offense detection method Download PDFInfo
- Publication number
- CN106127143A CN106127143A CN201610457650.8A CN201610457650A CN106127143A CN 106127143 A CN106127143 A CN 106127143A CN 201610457650 A CN201610457650 A CN 201610457650A CN 106127143 A CN106127143 A CN 106127143A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- time
- image
- highway
- video sequence
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 35
- 239000000284 extract Substances 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims description 24
- 238000006073 displacement reaction Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 9
- 230000007935 neutral effect Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Classifications
-
- 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
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- 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)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of highway parking offense detection method, belong to technical field of image processing.The present invention carries out video sequence extraction first against highway in region and carries out code identification, sets up this fastlink Video sequence information storehouse；Secondly, carry out this section video sequence image and process, extract moving vehicle car plate and also calibrate vehicle centroid, the distance of this region highway initial position of registration of vehicle centroid distance, and set up vehicle real-time position information storehouse and store；Then, it is tracked driving vehicle demarcating, it is judged that this vehicle rate of change away from initial position in video sequence, it is judged that vehicle running state, and calculates vehicle peccancy down time；Finally, according to vehicle at this section of highway parking offense duration, send to disobey and stop warning.The present invention can monitor in real time to specifying section, finds in time parking offense phenomenon, it is to avoid the generation of potential vehicle accident, and early warning is greatly improved disobeys the degree of accuracy stopped, and reduces the consuming of human resources.
Description
Technical field
The present invention relates to a kind of highway parking offense detection method, belong to technical field of image processing.
Background technology
Along with the development of telling of information age, the living standard of people steps up, and motor vehicles become more people trip
Walking-replacing tool.But the many traffic safety problem of the thing followed highlight the most day by day, wherein highway parking offense is exactly
Bigger potential safety hazard.At present, express-road vehicle running supervision still needs to substantial amounts of manpower and materials and puts into, festivals or holidays in addition
Big being also enough to of in-trips vehicles flow draws attention, and especially dense fog etc. are unfavorable for that the weather conditions of trip can strengthen highway
Contingency occurrence probability.Therefore, detection section vehicle traveling becomes problem demanding prompt solution the most accurately.Highway
Disobey and stop detection employing digital image processing techniques, testing result can be drawn with the form that computer directly runs, in any feelings
All can work reliably under condition, and there is higher accurate rate, reach to detect in real time, improve the function of work efficiency.
Summary of the invention
The technical problem to be solved in the present invention is the method proposing the detection of a kind of highway parking offense, on solving
State problem.
The technical scheme is that a kind of method that highway parking offense detects, first, for high speed in region
Highway carries out video sequence extraction and carries out code identification, sets up this fastlink Video sequence information storehouse；Secondly, this road is carried out
Section video sequence image processes, and extracts moving vehicle car plate and calibrates vehicle centroid, and this region of registration of vehicle centroid distance is high
The distance of speed highway initial position, and set up vehicle real-time position information storehouse and store；Then, driving vehicle is tracked
Demarcate, it is judged that this vehicle change away from initial position in video sequence, it is judged that vehicle running state, and calculate vehicle peccancy parking
Time；Finally, according to vehicle at this section of highway parking offense duration, send to disobey and stop warning.
Concretely comprise the following steps:
Step1: set up express highway section Video sequence information storehouse: highway in region is monitored in real time, and
Extract video sequence image, carry out code identification according to the time order and function sequence to being extracted.Set up this express highway section to regard
Frequency sequence information bank carries out image information storage；
Step2: set up vehicle real-time position information storehouse: with the original image in express highway section Video sequence information storehouse
As input, Color License Plate image being carried out background separation, extract the license board information of vehicle, application image processing method is carried out
Plate location recognition, distinguishes different vehicle；
Step2.1: car plate Objective extraction: first, the express-road vehicle running captured in request Video sequence information storehouse
Image information, as input, utilizes the feature of license plate area to judge licence plate, is split by license plate area from view picture vehicle image
Out.
Step2.2: License Plate based on Color Segmentation method: according to the different characteristic of car plate, selects to use based on coloured silk
The location technology of color dividing method carries out plate location recognition.The method includes two modules of Color Segmentation and target location, makes
With multi-Layer Perceptron Neural Network, coloured image is split, be then partitioned into potential license plate area by sciagraphy.
1, Color Segmentation module: use neural network model when carrying out Color Segmentation, here for preferably carrying out coloured silk
Color is split, and the coloured image of common RGB pattern is converted into HSI pattern, i.e. tone (hue), saturation (saturability)
With brightness (luminance), then the saturation of output image is adjusted.
2, target location: in order to reduce amount of calculation, coloured image is taken out dilute after carry out pattern conversion again.Meanwhile, in order to subtract
The impact that image segmentation is produced by few illumination condition, uses and counting method is carried out color saturation adjustment.Then pattern is converted
After coloured image carry out the segmentation of colored neutral net, finally according to prioris such as car plate background color and length-width ratios, use projection
Method is partitioned into rational license plate area.
Step2.3: Car license recognition based on character segmentation method: first, by it has been determined that license plate area be transformed into ash
Degree figure.Utilize medium filtering to carry out pretreatment, then utilize medium filtering to eliminate the stain on licence plate, utilize HOUGH conversion right
Car plate carries out gradient rectification.Then Adaptive Thresholding is used, by image binaryzation.The projection utilizing vertical direction has ripple
The characteristic that peak, trough interval occurs, splits character.Finally, after the character boundary normalization of segmentation, send into BP neural
Network carries out character recognition.In BP neutral net, add factor of momentum, shorten the training time of network.
Step3: extract vehicle and sail out of initial position distance: owing to vehicle has made a distinction labelling, herein according to taking pictures
Employing edge image processes, and extracts the gray level image of vehicle centroid.Application card Kalman Filtering track algorithm follows the trail of vehicle
Blob image, uses the course of dynamic Model Prediction vehicle, and corrects prediction with observation model, reduce forecast error.With
Monitoring express highway section original position is labelling initial point O, measures and follows the trail of vehicle FtThe distance O F away from initial positiont.Dynamic
In state image procossing, F in previous frame imaget-1Position as the input value of Kalman prediction, so repeat prediction and repair
Order measurement result, draw in detection zone video sequence the distance the most in the same time between vehicle centroid and initial position, and carry out record
Storage, in registered vehicle real-time position information storehouse；
Step4: judge vehicle running state:
Step4.1: obtaining in vehicle real-time position information storehouse every frame information, registration of vehicle sails out of initial position distance not
Numerical value in the same time.Then this barycenter displacement difference is represented by:
ΔFt-1,t(x)=| OFt(x)-OFt-1(x) |, t=1,2,3 ...
In formula: OFtX () represents the vehicle x stand-off distance at moment t, OFt-1X () represents vehicle x sailing out of at moment t-1
Distance speed, Δ OFt-1,tX () represents that vehicle x is in the displacement in frame；
Step4.2: sail out of the change of displacement according to vehicle and judge the state that vehicle travels:
1, as vehicle movement Δ OFt-1,t(x) ＞ Δ OFt,t+1(x), t=1, when 2,3..., show that vehicle movement is gradually
Reduce, it is judged that vehicle slows down, have bigger parking possible, need to keep higher attention rate；
2, as vehicle movement Δ OFt-1,t(x)≥ΔOFt,t+1(x), t=1, when 2,3..., it is judged that vehicle is normal traveling,
Non-detection section is disobeyed and is stopped monitored object；
3, displacement OF is sailed out of when vehiclet-1,t(x)→ΔOFt,t+1(x), t=1, when 2,3..., show that vehicle travels speed
Degree levels off to zero, it is judged that vehicle has stopped, and records this frame picture shooting time, disobeys as vehicle and stops initial time, carries out weight
Point monitoring.Continuing to monitor in ensuing video sequence, car speed remains the time of zero, and it is separated to calculate vehicle simultaneously
Between the stopping time.Computation model is as follows:
T=(tn-t0)*Tf, n=1,2,3 ...
In formula: T represents the separated time stopped, TnRepresent the video capture time point that car speed is zero, T0Represent vehicle first
Secondary speed is the frame video capture time point of zero, TfRepresent the frame per second of this detection equipment；
Step5: according to vehicle peccancy parking duration T, it is judged that vehicle is disobeyed between the stopping time and regulation disobeys threshold T between the stopping timem's
Relation, when beyond threshold value, i.e. T ＞ Tm, send to disobey and stop warning.
The invention has the beneficial effects as follows:
1, patent of the present invention is by setting up Video sequence information storehouse, vehicle real-time position information storehouse, and uses digital picture
The technology such as process, it is achieved that the Intelligent Measurement to highway parking offense phenomenon；And for the result of Intelligent Recognition, it is achieved that
Highway is disobeyed the automatic early-warning stopping phenomenon.
2, patent of the present invention is disobeyed for highway and is stopped phenomenon, it is provided that specifies section real-time detection function, improves biography
The inefficient operation pattern of the artificial supervision of system.Testing result is drawn, under any circumstance equal energy with the form that computer directly runs
Work reliably, and there is higher accurate rate, reach to detect in real time, improve the function of work efficiency.
Accompanying drawing explanation
Fig. 1 is the method overview flow chart of highway parking offense of the present invention detection；
Fig. 2 is present invention License Plate based on Color Segmentation method FB(flow block)；
Fig. 3 is present invention Car license recognition based on character segmentation method FB(flow block)；
Fig. 4 is the positioning flow block diagram of Kalman filter of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings and detailed description of the invention, the invention will be further described.
Embodiment 1: as it is shown in figure 1, the method for a kind of highway parking offense detection, first, for high speed in region
Highway carries out video sequence extraction and carries out code identification, sets up this fastlink Video sequence information storehouse；Secondly, this road is carried out
Section video sequence image processes, and extracts moving vehicle car plate and calibrates vehicle centroid, and this region of registration of vehicle centroid distance is high
The distance of speed highway initial position, and set up vehicle real-time position information storehouse and store；Then, driving vehicle is tracked
Demarcate, it is judged that this vehicle change away from initial position in video sequence, it is judged that vehicle running state, and calculate vehicle peccancy parking
Time；Finally, according to vehicle at this section of highway parking offense duration, send to disobey and stop warning.
Concretely comprise the following steps:
Step1: set up express highway section Video sequence information storehouse: highway in region is monitored in real time, and
Extract video sequence image, carry out code identification according to the time order and function sequence to being extracted.Set up this express highway section to regard
Frequency sequence information bank carries out image information storage；
Step2: set up vehicle real-time position information storehouse: with the original image in express highway section Video sequence information storehouse
As input, Color License Plate image being carried out background separation, extract the license board information of vehicle, application image processing method is carried out
Plate location recognition, distinguishes different vehicle；
Step2.1: car plate Objective extraction: first, the express-road vehicle running captured in request Video sequence information storehouse
Image information, as input, utilizes the feature of license plate area to judge licence plate, is split by license plate area from view picture vehicle image
Out.
Step2.2: License Plate based on Color Segmentation method: according to the different characteristic of car plate, selects to use based on coloured silk
The location technology of color dividing method carries out plate location recognition.The method includes two modules of Color Segmentation and target location, makes
With multi-Layer Perceptron Neural Network, coloured image is split, be then partitioned into potential license plate area by sciagraphy.
1, Color Segmentation module: use neural network model when carrying out Color Segmentation, here for preferably carrying out coloured silk
Color is split, and the coloured image of common RGB pattern is converted into HSI pattern, i.e. tone (hue), saturation (saturability)
With brightness (luminance), then the saturation of output image is adjusted.
2, target location: in order to reduce amount of calculation, coloured image is taken out dilute after carry out pattern conversion again.Meanwhile, in order to subtract
The impact that image segmentation is produced by few illumination condition, uses and counting method is carried out color saturation adjustment.Then pattern is converted
After coloured image carry out the segmentation of colored neutral net, finally according to prioris such as car plate background color and length-width ratios, use projection
Method is partitioned into rational license plate area.
Step2.3: Car license recognition based on character segmentation method: first, by it has been determined that license plate area be transformed into ash
Degree figure.Utilize medium filtering to carry out pretreatment, then utilize medium filtering to eliminate the stain on licence plate, utilize HOUGH conversion right
Car plate carries out gradient rectification.Then Adaptive Thresholding is used, by image binaryzation.The projection utilizing vertical direction has ripple
The characteristic that peak, trough interval occurs, splits character.Finally, after the character boundary normalization of segmentation, send into BP neural
Network carries out character recognition.In BP neutral net, add factor of momentum, shorten the training time of network.
Step3: extract vehicle and sail out of initial position distance: owing to vehicle has made a distinction labelling, herein according to taking pictures
Employing edge image processes, and extracts the gray level image of vehicle centroid.Application card Kalman Filtering track algorithm follows the trail of vehicle
Blob image, uses the course of dynamic Model Prediction vehicle, and corrects prediction with observation model, reduce forecast error.With
Monitoring express highway section original position is labelling initial point O, measures and follows the trail of vehicle FtThe distance O F away from initial positiont.Dynamic
In state image procossing, F in previous frame imaget-1Position as the input value of Kalman prediction, so repeat prediction and repair
Order measurement result, draw in detection zone video sequence the distance the most in the same time between vehicle centroid and initial position, and carry out record
Storage, in registered vehicle real-time position information storehouse；
Step4: judge vehicle running state:
Step4.1: obtaining in vehicle real-time position information storehouse every frame information, registration of vehicle sails out of initial position distance not
Numerical value in the same time.Then this barycenter displacement difference is represented by:
ΔFt-1,t(x)=| OFt(x)-OFt-1(x) |, t=1,2,3 ...
In formula: OFtX () represents the vehicle x stand-off distance at moment t, OFt-1X () represents vehicle x sailing out of at moment t-1
Distance speed, Δ OFt-1,tX () represents that vehicle x is in the displacement in frame；
Step4.2: sail out of the change of displacement according to vehicle and judge the state that vehicle travels:
1, as vehicle movement Δ OFt-1,t(x) ＞ Δ OFt,t+1(x), t=1,2,3 ... time, show that vehicle movement is gradually subtracting
Little, it is judged that vehicle slows down, there is bigger parking possible, need to keep higher attention rate；
2, as vehicle movement Δ OFt-1,t(x)≥ΔOFt,t+1(x), t=1,2,3 ... time, it is judged that vehicle is normal traveling,
Non-detection section is disobeyed and is stopped monitored object；
3, displacement OF is sailed out of when vehiclet-1,t(x)→ΔOFt,t+1(x), t=1,2,3 ... time, show Vehicle Speed
Level off to zero, it is judged that vehicle has stopped, and records this frame picture shooting time, disobey as vehicle and stop initial time, carry out emphasis
Monitoring.Continuing to monitor in ensuing video sequence, car speed remains the time of zero simultaneously, and calculates vehicle and disobey and stop
Time.Computation model is as follows:
T=(tn-t0)*Tf, n=1,2,3 ...
In formula: T represents the separated time stopped, TnRepresent the video capture time point that car speed is zero, T0Represent vehicle first
Secondary speed is the frame video capture time point of zero, TfRepresent the frame per second of this detection equipment；
Step5: according to vehicle peccancy parking duration T, it is judged that vehicle is disobeyed between the stopping time and regulation disobeys threshold T between the stopping timem's
Relation, when beyond threshold value, i.e. T ＞ Tm, send to disobey and stop warning.
Embodiment 2: as it is shown in figure 1, the method for a kind of highway parking offense detection, first, for high speed in region
Highway carries out video sequence extraction and carries out code identification, sets up this fastlink Video sequence information storehouse；Secondly, this road is carried out
Section video sequence image processes, and extracts moving vehicle car plate and calibrates vehicle centroid, and this region of registration of vehicle centroid distance is high
The distance of speed highway initial position, and set up vehicle real-time position information storehouse and store；Then, driving vehicle is tracked
Demarcate, it is judged that this vehicle change away from initial position in video sequence, it is judged that vehicle running state, and calculate vehicle peccancy parking
Time；Finally, according to vehicle at this section of highway parking offense duration, send to disobey and stop warning.
Above in association with accompanying drawing, the detailed description of the invention of the present invention is explained in detail, but the present invention is not limited to above-mentioned
Embodiment, in the ken that those of ordinary skill in the art are possessed, it is also possible to before without departing from present inventive concept
Put that various changes can be made.
Claims (2)
1. a highway parking offense detection method, it is characterised in that: first, carry out video for highway in region
Sequential extraction procedures also carries out code identification, sets up this fastlink Video sequence information storehouse；Secondly, this section video sequence figure is carried out
As processing, extract moving vehicle car plate and calibrate vehicle centroid, this region highway initial bit of registration of vehicle centroid distance
The distance put, and set up vehicle real-time position information storehouse and store；Then, it is tracked driving vehicle demarcating, it is judged that regard
This vehicle change away from initial position in frequency sequence, it is judged that vehicle running state, and calculate vehicle peccancy down time；Finally,
According to vehicle at this section of highway parking offense duration, send to disobey and stop warning.
Highway parking offense detection method the most according to claim 1, it is characterised in that concretely comprise the following steps:
Step1: set up express highway section Video sequence information storehouse: highway in region is monitored in real time, and extracts
Video sequence image, carries out code identification according to the time order and function sequence to being extracted, and sets up this express highway section video sequence
Column information storehouse carries out image information storage；
Step2: set up vehicle real-time position information storehouse: using the original image in express highway section Video sequence information storehouse as
Input, carries out background separation by Color License Plate image, extracts the license board information of vehicle, and application image processing method carries out car plate
Fixation and recognition, distinguishes different vehicle；
Step2.1: car plate Objective extraction: first, the express-road vehicle running image captured in request Video sequence information storehouse
Information, as input, utilizes the feature of license plate area to judge licence plate, is split by license plate area from view picture vehicle image；
Step2.2: License Plate based on Color Segmentation method: according to the different characteristic of car plate, selects to use and divides based on colour
The location technology of segmentation method carries out plate location recognition, and the method includes two modules of Color Segmentation and target location, uses many
Coloured image is split by layer perceptron network, is then partitioned into potential license plate area by sciagraphy；
1, Color Segmentation module: use neural network model when carrying out Color Segmentation, here for preferably carrying out colored point
Cut, the coloured image of common RGB pattern is converted into HSI pattern, i.e. tone, saturation and brightness, then to output image
Saturation adjusts；
2, target location: in order to reduce amount of calculation, coloured image is taken out dilute after carry out pattern conversion again；Meanwhile, in order to reduce light
The impact produced image segmentation according to condition, uses and counting method is carried out color saturation adjustment；Then after pattern being converted
Coloured image carries out colored neutral net segmentation, finally according to prioris such as car plate background color and length-width ratios, uses sciagraphy to divide
Cut out rational license plate area；
Step2.3: Car license recognition based on character segmentation method: first, by it has been determined that license plate area be transformed into gray-scale map,
Utilize medium filtering to carry out pretreatment, then utilize medium filtering to eliminate the stain on licence plate, utilize HOUGH conversion that car plate is entered
Line tilt degree is corrected, and then uses Adaptive Thresholding, by image binaryzation, utilizes the projection of vertical direction to have crest, ripple
The characteristic that paddy interval occurs, splits character, finally, after the character boundary normalization of segmentation, sends into BP neutral net
Carry out character recognition, BP neutral net adds factor of momentum, shortens the training time of network；
Step3: extract vehicle and sail out of initial position distance: owing to vehicle has made a distinction labelling according to taking pictures, use herein
Edge image processes, and extracts the gray level image of vehicle centroid, and application card Kalman Filtering track algorithm follows the trail of the blob figure of vehicle
Picture, uses the course of dynamic Model Prediction vehicle, and corrects prediction with observation model, reduce forecast error；To monitor height
Speed highway section original position is labelling initial point O, measures and follows the trail of vehicle FtThe distance O F away from initial positiont, at dynamic image
In process, F in previous frame imaget-1Position as the input value of Kalman prediction, so repeat prediction and revision measured
As a result, draw in detection zone video sequence the distance the most in the same time between vehicle centroid and initial position, and carry out record storage, step on
In caravan real-time position information storehouse；
Step4: judge vehicle running state:
Step4.1: obtaining in vehicle real-time position information storehouse every frame information, registration of vehicle sails out of initial position distance when difference
The numerical value carved, then this barycenter displacement difference is represented by:
ΔFt-1,t(x)=| OFt(x)-OFt-1(x) |, t=1,2,3 ...
In formula: OFtX () represents the vehicle x stand-off distance at moment t, OFt-1X () represents the vehicle x stand-off distance at moment t-1
Speed, Δ OFt-1,tX () represents that vehicle x is in the displacement in frame；
Step4.2: sail out of the change of displacement according to vehicle and judge the state that vehicle travels:
1, as vehicle movement Δ OFt-1,t(x) ＞ Δ OFt,t+1(x), t=1,2,3 ... time, show that vehicle movement is being gradually reduced, sentence
Disconnected vehicle slows down, and has bigger parking possible, needs to keep higher attention rate；
2, as vehicle movement Δ OFt-1,t(x)≥ΔOFt,t+1(x), t=1,2,3 ... time, it is judged that vehicle is normal traveling, non-detection
Section is disobeyed and is stopped monitored object；
3, displacement OF is sailed out of when vehiclet-1,t(x)→ΔOFt,t+1(x), t=1,2,3 ... time, show Vehicle Speed convergence
In zero, it is judged that vehicle has stopped, record this frame picture shooting time, disobey as vehicle and stop initial time, carry out emphasis monitoring,
Continuing to monitor in ensuing video sequence, car speed remains the time of zero simultaneously, and calculates vehicle and disobey between the stopping time,
Computation model is as follows:
T=(tn-t0)*Tf, n=1,2,3 ...
In formula: T represents the separated time stopped, TnRepresent the video capture time point that car speed is zero, T0Represent vehicle speed for the first time
Degree is the frame video capture time point of zero, TfRepresent the frame per second of this detection equipment；
Step5: according to vehicle peccancy parking duration T, it is judged that vehicle is disobeyed between the stopping time and regulation disobeys threshold T between the stopping timemRelation,
When beyond threshold value, i.e. T ＞ Tm, send to disobey and stop warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610457650.8A CN106127143A (en) | 2016-06-23 | 2016-06-23 | A kind of highway parking offense detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610457650.8A CN106127143A (en) | 2016-06-23 | 2016-06-23 | A kind of highway parking offense detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106127143A true CN106127143A (en) | 2016-11-16 |
Family
ID=57268382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610457650.8A Pending CN106127143A (en) | 2016-06-23 | 2016-06-23 | A kind of highway parking offense detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106127143A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107240268A (en) * | 2017-07-28 | 2017-10-10 | 西安因诺航空科技有限公司 | A kind of detection method of high speed Emergency Vehicle Lane vehicles peccancy towards unmanned plane |
| CN107273896A (en) * | 2017-06-15 | 2017-10-20 | 浙江南自智能科技股份有限公司 | A kind of car plate detection recognition methods based on image recognition |
| CN107330373A (en) * | 2017-06-02 | 2017-11-07 | 重庆大学 | A kind of parking offense monitoring system based on video |
| CN108154146A (en) * | 2017-12-25 | 2018-06-12 | 陈飞 | A kind of car tracing method based on image identification |
| CN108806272A (en) * | 2018-06-22 | 2018-11-13 | 安徽科力信息产业有限责任公司 | A kind of method and device for reminding more motor vehicle car owner's illegal parking behaviors |
| CN108932853A (en) * | 2018-06-22 | 2018-12-04 | 安徽科力信息产业有限责任公司 | A kind of method and device recording more motor vehicle illegal parking behaviors |
| CN108932851A (en) * | 2018-06-22 | 2018-12-04 | 安徽科力信息产业有限责任公司 | A kind of method and device recording the behavior of motor vehicle illegal parking |
| CN109003455A (en) * | 2018-06-22 | 2018-12-14 | 安徽科力信息产业有限责任公司 | A kind of method and device for reminding the behavior of car owner's illegal parking |
| CN109063612A (en) * | 2018-07-19 | 2018-12-21 | 中智城信息技术有限公司 | City intelligent red line management method and machine readable storage medium |
| CN109086686A (en) * | 2018-07-12 | 2018-12-25 | 西安电子科技大学 | Blind source separation method under time varying channel based on self-adapted momentum factor |
| CN109147341A (en) * | 2018-09-14 | 2019-01-04 | 杭州数梦工场科技有限公司 | Violation vehicle detection method and device |
| CN109255957A (en) * | 2018-11-20 | 2019-01-22 | 湖北文理学院 | The method and system of vehicle driving monitoring in a kind of tunnel |
| CN109493606A (en) * | 2017-09-11 | 2019-03-19 | 中国移动通信集团浙江有限公司 | The recognition methods and system of parking are disobeyed on a kind of highway |
| CN109901168A (en) * | 2019-03-21 | 2019-06-18 | 西安交通大学 | There are detection system and methods for a kind of vehicle based on guardrail and radar |
| CN111007226A (en) * | 2019-12-31 | 2020-04-14 | 南京熙岳智能科技有限公司 | Water quality on-line monitoring system based on machine vision |
| CN111178806A (en) * | 2019-12-30 | 2020-05-19 | 北京四维智联科技有限公司 | Method, device and equipment for searching vehicle stopping point |
| CN111241879A (en) * | 2018-11-29 | 2020-06-05 | 杭州海康威视数字技术股份有限公司 | Vehicle detection method and device, electronic equipment and readable storage medium |
| CN111523385A (en) * | 2020-03-20 | 2020-08-11 | 北京航空航天大学合肥创新研究院 | Stationary vehicle detection method and system based on frame difference method |
| CN112883904A (en) * | 2021-03-15 | 2021-06-01 | 珠海安联锐视科技股份有限公司 | Method for detecting vehicle illegal parking lane occupation |
| CN115131718A (en) * | 2022-08-30 | 2022-09-30 | 南通浩盛汽车科技有限公司 | Crossing detection system that parks violating regulations based on regional speed distribution |
| CN115410370A (en) * | 2022-08-31 | 2022-11-29 | 南京慧尔视智能科技有限公司 | Abnormal parking detection method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778786A (en) * | 2013-12-17 | 2014-05-07 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method based on significant vehicle part model |
| CN105513371A (en) * | 2016-01-15 | 2016-04-20 | 昆明理工大学 | Expressway illegal parking detection method based on kernel density estimation |
-
2016
- 2016-06-23 CN CN201610457650.8A patent/CN106127143A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778786A (en) * | 2013-12-17 | 2014-05-07 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method based on significant vehicle part model |
| CN105513371A (en) * | 2016-01-15 | 2016-04-20 | 昆明理工大学 | Expressway illegal parking detection method based on kernel density estimation |
Non-Patent Citations (2)
| Title |
|---|
| 刘振: "基于卡尔曼滤波与模板匹配的目标跟踪研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 双维: "基于神经网络的车牌识别技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330373A (en) * | 2017-06-02 | 2017-11-07 | 重庆大学 | A kind of parking offense monitoring system based on video |
| CN107273896A (en) * | 2017-06-15 | 2017-10-20 | 浙江南自智能科技股份有限公司 | A kind of car plate detection recognition methods based on image recognition |
| CN107240268A (en) * | 2017-07-28 | 2017-10-10 | 西安因诺航空科技有限公司 | A kind of detection method of high speed Emergency Vehicle Lane vehicles peccancy towards unmanned plane |
| CN109493606A (en) * | 2017-09-11 | 2019-03-19 | 中国移动通信集团浙江有限公司 | The recognition methods and system of parking are disobeyed on a kind of highway |
| CN108154146A (en) * | 2017-12-25 | 2018-06-12 | 陈飞 | A kind of car tracing method based on image identification |
| CN108932851A (en) * | 2018-06-22 | 2018-12-04 | 安徽科力信息产业有限责任公司 | A kind of method and device recording the behavior of motor vehicle illegal parking |
| CN108932853A (en) * | 2018-06-22 | 2018-12-04 | 安徽科力信息产业有限责任公司 | A kind of method and device recording more motor vehicle illegal parking behaviors |
| CN109003455A (en) * | 2018-06-22 | 2018-12-14 | 安徽科力信息产业有限责任公司 | A kind of method and device for reminding the behavior of car owner's illegal parking |
| CN108932851B (en) * | 2018-06-22 | 2021-03-30 | 安徽科力信息产业有限责任公司 | Method and device for recording illegal parking behaviors of motor vehicle |
| CN108806272A (en) * | 2018-06-22 | 2018-11-13 | 安徽科力信息产业有限责任公司 | A kind of method and device for reminding more motor vehicle car owner's illegal parking behaviors |
| CN108932853B (en) * | 2018-06-22 | 2021-03-30 | 安徽科力信息产业有限责任公司 | Method and device for recording illegal parking behaviors of multiple motor vehicles |
| CN109086686A (en) * | 2018-07-12 | 2018-12-25 | 西安电子科技大学 | Blind source separation method under time varying channel based on self-adapted momentum factor |
| CN109086686B (en) * | 2018-07-12 | 2022-09-30 | 西安电子科技大学 | Blind source separation method under time-varying channel based on self-adaptive momentum factor |
| CN109063612A (en) * | 2018-07-19 | 2018-12-21 | 中智城信息技术有限公司 | City intelligent red line management method and machine readable storage medium |
| CN109147341B (en) * | 2018-09-14 | 2019-11-22 | 杭州数梦工场科技有限公司 | Violation vehicle detection method and device |
| CN109147341A (en) * | 2018-09-14 | 2019-01-04 | 杭州数梦工场科技有限公司 | Violation vehicle detection method and device |
| CN109255957A (en) * | 2018-11-20 | 2019-01-22 | 湖北文理学院 | The method and system of vehicle driving monitoring in a kind of tunnel |
| CN111241879A (en) * | 2018-11-29 | 2020-06-05 | 杭州海康威视数字技术股份有限公司 | Vehicle detection method and device, electronic equipment and readable storage medium |
| CN111241879B (en) * | 2018-11-29 | 2023-09-26 | 杭州海康威视数字技术股份有限公司 | Vehicle detection method, device, electronic equipment and readable storage medium |
| CN109901168A (en) * | 2019-03-21 | 2019-06-18 | 西安交通大学 | There are detection system and methods for a kind of vehicle based on guardrail and radar |
| CN111178806A (en) * | 2019-12-30 | 2020-05-19 | 北京四维智联科技有限公司 | Method, device and equipment for searching vehicle stopping point |
| CN111178806B (en) * | 2019-12-30 | 2023-08-15 | 北京四维智联科技有限公司 | Method, device and equipment for searching vehicle stay points |
| CN111007226A (en) * | 2019-12-31 | 2020-04-14 | 南京熙岳智能科技有限公司 | Water quality on-line monitoring system based on machine vision |
| CN111523385B (en) * | 2020-03-20 | 2022-11-04 | 北京航空航天大学合肥创新研究院 | Stationary vehicle detection method and system based on frame difference method |
| CN111523385A (en) * | 2020-03-20 | 2020-08-11 | 北京航空航天大学合肥创新研究院 | Stationary vehicle detection method and system based on frame difference method |
| CN112883904A (en) * | 2021-03-15 | 2021-06-01 | 珠海安联锐视科技股份有限公司 | Method for detecting vehicle illegal parking lane occupation |
| CN115131718A (en) * | 2022-08-30 | 2022-09-30 | 南通浩盛汽车科技有限公司 | Crossing detection system that parks violating regulations based on regional speed distribution |
| CN115131718B (en) * | 2022-08-30 | 2022-11-11 | 南通浩盛汽车科技有限公司 | Crossing parking violating regulations detection system based on regional speed distribution |
| CN115410370A (en) * | 2022-08-31 | 2022-11-29 | 南京慧尔视智能科技有限公司 | Abnormal parking detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127143A (en) | A kind of highway parking offense detection method | |
| CN107766821B (en) | Method and system for detecting and tracking full-time vehicle in video based on Kalman filtering and deep learning | |
| CN105892471B (en) | Automatic driving method and apparatus | |
| CN105678316B (en) | Active drive manner based on multi-information fusion | |
| CN104021378B (en) | Traffic lights real-time identification method based on space time correlation Yu priori | |
| CN103522970B (en) | Based on vehicle driving safety method of inspection and the system of machine vision | |
| CN103150559B (en) | Head recognition and tracking method based on Kinect three-dimensional depth image | |
| CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
| CN104077756B (en) | Direction filtering method based on lane line confidence | |
| US20120327188A1 (en) | Vehicle-Mounted Environment Recognition Apparatus and Vehicle-Mounted Environment Recognition System | |
| CN109598187A (en) | Obstacle recognition method, differentiating obstacle and railcar servomechanism | |
| CN106679633B (en) | A kind of vehicle-mounted distance-finding system base and method | |
| CN104318258A (en) | Time domain fuzzy and kalman filter-based lane detection method | |
| CN103324913A (en) | Pedestrian event detection method based on shape features and trajectory analysis | |
| Suhweil et al. | Smart controlling for traffic light time | |
| CN105913041A (en) | Pre-marked signal lights based identification method | |
| CN109190523A (en) | A kind of automobile detecting following method for early warning of view-based access control model | |
| CN107066968A (en) | The vehicle-mounted pedestrian detection method of convergence strategy based on target recognition and tracking | |
| CN102862574A (en) | Method for realizing active safety of vehicle on the basis of smart phone | |
| CN103400157A (en) | Road pedestrian and non-motor vehicle detection method based on video analysis | |
| CN105931467A (en) | Target tracking method and device | |
| CN114898296A (en) | Bus lane occupation detection method based on millimeter wave radar and vision fusion | |
| CN111753797A (en) | Vehicle speed measuring method based on video analysis | |
| JP2020064583A (en) | Vehicle detection method, nighttime vehicle detection method based on dynamic light intensity, and system for the same | |
| CN112861748B (en) | Traffic light detection system and method in automatic driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
| RJ01 | Rejection of invention patent application after publication |