CN104504908A - Monitoring method and system for illegal parking - Google Patents
Monitoring method and system for illegal parking Download PDFInfo
- Publication number
- CN104504908A CN104504908A CN201510019175.1A CN201510019175A CN104504908A CN 104504908 A CN104504908 A CN 104504908A CN 201510019175 A CN201510019175 A CN 201510019175A CN 104504908 A CN104504908 A CN 104504908A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- parking offense
- parking
- vehicle target
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a monitoring method and system for illegal parking. The monitoring method for the illegal parking comprises the following steps: obtaining a vehicle objective; judging whether the vehicle objective is recorded as the illegal parking evidence within the first preset time; while the illegal parking evidence is not recorded within the first preset time, calculating the continuous rest time of the vehicle objective; and while the continuous rest time exceeds the second preset time, judging that the vehicle objective is the vehicle of illegal parking. The same vehicle can be avoided to be captured repeatedly, the accuracy rate for judging the vehicle of illegal parking is improved, and the vehicle for short time parking is avoided to be judged as the vehicle of illegal parking, so the parking behavior of the illegal parking is accurately discovered and investigated in time. The technical problem that the parking behavior of the illegal parking is difficult to be accurately discovered and investigated in time in the prior art is solved.
Description
Technical field
The present invention relates to vehicle detection control technology field, be specifically related to a kind of parking offense method for supervising and system.
Background technology
Along with the lasting raising of socioeconomic development and living standards of the people, Urban vehicles poputation rapidly increases.The parking demand of quick growth and the supply of parking space incompatible, parking supply and demand contradiction.Meanwhile, because the traffic safety consciousness of vehicle driver is thin, motor vehicle illegal parking has become city persistent ailment.The situation such as traffic congestion, rear-end collision caused because of illegal parking is every year millions of, drastically influence the overall traffic environment in city, and can cause the loss of people's person property.
Traditional parking offense monitoring mainly fixes a point to implement artificial supervision by traffic police, and efficiency is low, cannot realize real-time monitoring, the manpower and financial resources of significant wastage relevant departments.Wherein, the intelligent transportation that traffic control department tradition uses one to be commonly called as " electronic eyes " is broken rules and regulations supervisory system.Electronic eyes mainly contains two kinds of modes to monitoring violating the regulations, and one adopts wagon detector (such as inductive coil, ultrasound wave hardware) monitoring mode to realize, this mode or lay particular emphasis on speed monitoring, or just realization is made a dash across the red light monitoring, function singleness; Another kind carries out real-time recording to act of violating regulations, and the later stage needs special viewing video recording to extract picture violating the regulations, time-consuming effort.
At present, along with the development of video detection technology, Video Supervision Technique and computer vision technique, ripe day by day in the detection to Moving Objects, tracking, abnormal behaviour identification etc., possess practicality in many scenes.In traffic monitoring, act of violating regulations detection technique obtains significant progress, can realize accurately detecting to violation phenomenons such as the yellow lines that exceeds the speed limit, drives in the wrong direction, makes a dash across the red light, presses, but parking offense monitoring technique but develops more delayed relatively.
How accurately and rapidly detection record to be carried out to the behavior of motor vehicle illegal parking, parking behavior the carrying out evidence obtaining promptly and accurately of violating regulations is investigated and prosecuted, avoids manual detection cost of labor high, fatiguability simultaneously, the drawbacks such as easy carelessness are the technical matterss being badly in need of solving.
Summary of the invention
For this reason, the technical problem to be solved in the present invention is that prior art is difficult to parking behavior the carrying out evidence obtaining promptly and accurately realized violating regulations and investigates and prosecutes, thus proposes a kind of parking offense method for supervising and system solves this problem.
For solving the problems of the technologies described above, the present invention by the following technical solutions:
A kind of parking offense method for supervising, comprises the following steps: obtain vehicle target; Judge whether described vehicle target was recorded parking offense evidence in the first Preset Time; When not being recorded parking offense evidence in the first Preset Time, calculated the continuous rest time of described vehicle target; When described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.
Preferably, the step of described acquisition vehicle target comprises: obtain monitoring scene image; The moving target filtered in described monitoring scene image obtains background image; Vehicle target is detected from described background image.
Preferably, describedly from described background image, detect that the step of vehicle target comprises: the process of expansion limit is carried out to described background image; Convergent-divergent formation image pyramid is carried out to the image after expanding limit; Characteristic image is obtained to the image zooming-out texture gradient feature of often opening of described image pyramid; Utilize vehicle characteristics training pattern to carry out moving window scanning to described characteristic image and obtain vehicle target.
Preferably, described vehicle characteristics training pattern is obtained by following steps: the vehicle image obtaining different angles under different natural lighting condition; Texture gradient feature is extracted to described vehicle image; Cluster is carried out to described texture gradient feature; The different classes of described texture gradient feature that cluster goes out is trained respectively, obtains the vehicle characteristics training pattern of each classification.
Preferably, described judge that described vehicle target is as parking offense vehicle after, also comprise: the close-up image obtaining parking offense vehicle; Identify the car plate of described parking offense vehicle; Record described close-up image, car plate as parking offense evidence.
Preferably, the step of the car plate of described identification described parking offense vehicle comprises: carry out license diction and plate to described close-up image and obtain license plate image; Extract the texture gradient feature of described license plate image; Level and the vertical bank angle of car plate is obtained according to described texture gradient feature; According to described level and vertical bank angle, affined transformation is carried out to described license plate image; According to the characters on license plate of the license plate image identification parking offense vehicle after affined transformation.
As identical inventive concept, the present invention also provides a kind of parking offense supervisory system, comprising: acquisition module, for obtaining vehicle target; Judge module, for judging whether described vehicle target was recorded parking offense evidence in the first Preset Time; Computing module, for when not being recorded parking offense evidence in the first Preset Time, calculated the continuous rest time of described vehicle target; Determination module, for when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.
Preferably, described acquisition module comprises: obtain elementary area, for obtaining monitoring scene image; Filter element, obtains background image for the moving target filtered in described monitoring scene image; Detecting unit, for detecting vehicle target from described background image.
Preferably, described detecting unit comprises: expand limit subelement, for carrying out the process of expansion limit to described background image; Convergent-divergent subelement, forms image pyramid for carrying out convergent-divergent to the image behind expansion limit; Extract feature subelement, for obtaining characteristic image to the image zooming-out texture gradient feature of often opening of described image pyramid; Sliding window scanning subelement, carries out moving window scanning for utilizing vehicle characteristics training pattern to described characteristic image and obtains vehicle target.
Preferably, described parking offense supervisory system also comprises: obtain close-up image module, for obtaining the close-up image of parking offense vehicle; Identify car plate module, for identifying the car plate of described parking offense vehicle; Taking of evidence module, for recording described close-up image, car plate as parking offense evidence.
Preferably, described identification car plate module comprises: license diction and plate unit, obtains license plate image for carrying out license diction and plate to described close-up image; Extract license plate image feature unit, for extracting the texture gradient feature of described license plate image; Obtain angle module, for obtaining level and the vertical bank angle of car plate according to described texture gradient feature; Affined transformation module, for carrying out affined transformation according to described level and vertical bank angle to described license plate image; Identification character module, for the characters on license plate according to the license plate image identification parking offense vehicle after affined transformation.
The beneficial effect of parking offense method for supervising of the present invention and system comprises:
A kind of parking offense method for supervising of the present invention and system, because wherein said parking offense method for supervising comprises the following steps: obtain vehicle target; Judge whether described vehicle target was recorded parking offense evidence in the first Preset Time; When not being recorded parking offense evidence in the first Preset Time, calculated the continuous rest time of described vehicle target; When described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.By judging whether described vehicle target was recorded parking offense evidence in the first Preset Time, can avoid repeating to capture to same vehicle, improve the accuracy rate judging parking offense vehicle, and by calculate described vehicle target continuous rest time and when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle, avoid to be judged to be parking offense vehicle by resident vehicle in short-term, and then parking behavior the carrying out evidence obtaining promptly and accurately realized violating regulations is investigated and prosecuted.
Accompanying drawing explanation
In order to make content of the present invention be more likely to be clearly understood, below according to a particular embodiment of the invention and by reference to the accompanying drawings, the present invention is further detailed explanation, wherein
Fig. 1 is the schematic flow sheet of a kind of parking offense method for supervising of the embodiment of the present invention 1;
Fig. 2 is the schematic flow sheet detecting the step of vehicle target from described background image of a kind of method for snap control of the embodiment of the present invention 1;
Fig. 3 is the schematic flow sheet of the vehicle characteristics training pattern obtaining step of a kind of method for snap control of the embodiment of the present invention 1;
Fig. 4 is the schematic flow sheet of a kind of parking offense method for supervising of the embodiment of the present invention 2;
Fig. 5 is the schematic flow sheet of the step of the car plate of the described parking offense vehicle of identification of a kind of parking offense method for supervising of the embodiment of the present invention 2;
Fig. 6 is the structural representation of a kind of parking offense supervisory system of the embodiment of the present invention 3;
Fig. 7 is a kind of structural representation capturing the detecting unit of control system of the embodiment of the present invention 3;
Fig. 8 is the structural representation of a kind of parking offense supervisory system of the embodiment of the present invention 4;
Fig. 9 is the structural representation of the identification car plate module of a kind of parking offense supervisory system of the embodiment of the present invention 4.
Embodiment
Embodiment 1
Fig. 1 shows a kind of parking offense method for supervising of the embodiment of the present invention 1, can comprise the following steps:
Step S11, obtains vehicle target.
Step S12, judges whether described vehicle target was recorded parking offense evidence in the first Preset Time.The vehicle target of acquisition and the vehicle target of recorded parking offense evidence can be carried out feature (comprising vehicle location, size, color and texture etc.) to mate, if the match is successful, then obtain the license board information (comprising car plate color, characters on license plate etc.) of described vehicle target further, and mate with the license board information of the vehicle target of recorded parking offense evidence, and then avoid repeating record parking offense evidence to same car at the first Preset Time.Described first Preset Time can be that CCTV camera comes back to the time of the state of the monitoring scene image obtaining described vehicle target from camera lens close-up condition or other rotational angle states, also can be the time returned again after described vehicle target leaves monitoring scene, described in leave monitoring scene after time of returning again can supervise regulation by the parking offense of monitoring scene and determine.
Step S13, when not being recorded parking offense evidence in the first Preset Time, calculated the continuous rest time of described vehicle target.A timer can be distributed for described vehicle target, accumulative timing is carried out to the rest time of described vehicle target, thus obtain described continuous rest time.
Step S14, when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.Usual described continuous rest time can not think that described vehicle target belongs to illegal parking when being less than a certain scope, therefore be provided with the second Preset Time in the present embodiment to compare with described continuous rest time, namely, when exceeding described second Preset Time described continuous rest time, judge that described vehicle target is as parking offense vehicle.
By judging whether described vehicle target was recorded parking offense evidence in the first Preset Time, can avoid repeating to capture to same vehicle, improve the accuracy rate judging parking offense vehicle, and by calculate described vehicle target continuous rest time and when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle, avoid to be judged to be parking offense vehicle by resident vehicle in short-term, and then parking behavior the carrying out evidence obtaining promptly and accurately realized violating regulations is investigated and prosecuted.
Hereafter the embodiment of technique scheme is introduced:
As preferred embodiment, the step S11 obtaining vehicle target can comprise the following steps:
Step S111, obtains monitoring scene image.Monitoring scene image that such as can be real-time with the camera acquisition with The Cloud Terrace PTZ (PTZ is writing a Chinese character in simplified form of Pan/Ti l t/Zoom, represents The Cloud Terrace all-around mobile and camera lens zoom, Zoom control) function.
Step S112, the moving target filtered in described monitoring scene image obtains background image.Such as, first by described monitoring scene image conversion to gray level image, then average background modeling is carried out to the gray level image obtained, filters out the targets such as moving vehicle, obtain background image.
Step S113, detects vehicle target from described background image.
Obtain monitoring scene image, the moving target filtered in described monitoring scene image obtains background image, finally from described background image, detect vehicle target, vehicle target can be obtained according to monitoring scene image rapidly like this, improve further and the promptness investigated and prosecuted of collecting evidence is carried out to the parking behavior violating regulations.
Further, as shown in Figure 2, from described background image, detect that the step S113 of vehicle target can comprise the following steps:
Step S1131, carries out the process of expansion limit to described background image.Such as, 0.2 times can be expanded respectively to the left and right width of described background image.
Step S1132, carries out convergent-divergent formation image pyramid to the image after expanding limit.Equal proportion zoom factor (such as 1.02) can be utilized to carry out image scaling.
Step S1133, obtains characteristic image to the image zooming-out texture gradient feature of often opening of described image pyramid.The texture gradient feature extracting image belongs to common practise, does not hereby repeat.
Step S1134, utilizes vehicle characteristics training pattern to carry out moving window scanning to described characteristic image and obtains vehicle target.Such as, vehicle characteristics training pattern (model size can be 40*40, and Number of Models is 4 to 8) can be utilized in the enterprising line slip window scanning of described characteristic image.The position of the scanning window of each vehicle target that last basis scans and size carry out merging treatment (common practise does not hereby repeat), obtain final vehicle target.
By carrying out the process of expansion limit to described background image, the vehicle at described background image edge can be detected, image pyramid is formed by carrying out convergent-divergent to the image behind expansion limit, the vehicle target of the upper different size size of original image can be detected, avoid shade, camera shake, pedestrian/vehicle/other objects block bring flase drop impact, improve the accuracy rate obtaining vehicle target, improve further and the accuracy investigated and prosecuted of collecting evidence is carried out to the parking behavior violating regulations.
Further, as shown in Figure 3, described vehicle characteristics training pattern can be obtained by following steps:
Step S31, obtains the vehicle image of different angles under different natural lighting condition.So-called different natural lighting condition can be the outdoor illumination condition of daytime (under comprising different weather condition) different time sections, or the light conditions etc. around night monitoring scene.So-called different angles, can consider from the different parked state of vehicle monitoring scene, and the vehicle shooting image that also can obtain different visual angles from CCTV camera is considered.
Step S32, extracts texture gradient feature to described vehicle image.
Step S33, carries out cluster to described texture gradient feature.Kmeans clustering algorithm can be utilized to carry out cluster to the vehicle texture gradient feature extracted.Vehicle characteristics training pattern can be divided into 4 to 8 classes according to these features.
Step S34, trains respectively the different classes of described texture gradient feature that cluster goes out, obtains the vehicle characteristics training pattern of each classification.The method of machine learning can be utilized to train, such as SVM (Support Vector Machine, i.e. support vector machine) algorithm, or adaboost algorithm.
The vehicle image of different angles under different natural lighting condition is obtained by step S31, by step S32, texture gradient feature is extracted to described vehicle image, by step S33, cluster is carried out to described texture gradient feature, by step S34, the different classes of described texture gradient feature that cluster goes out is trained respectively, obtain the vehicle characteristics training pattern of each classification, can realize, to the parking behavior monitoring, from various visual angles of violation regulations, improving the accuracy of the parking behavior violating regulations being carried out to evidence obtaining investigation further on a large scale.
Embodiment 2
Fig. 4 shows a kind of parking offense method for supervising of the embodiment of the present invention 2, be with the difference of the described parking offense method for supervising in embodiment 1, when described continuous rest time more than the second Preset Time time, can also comprise the following steps after judging the step S14 of described vehicle target as parking offense vehicle:
Step S15, obtains the close-up image of parking offense vehicle.Such as, the video camera with The Cloud Terrace PTZ function can be utilized, video camera be turned to can photograph the feature position of parking offense vehicle, gather close-up image.
Step S16, identifies the car plate of described parking offense vehicle.
Step S17, records described close-up image, car plate as parking offense evidence.In addition, the video record of parking offense vehicle can also be obtained, to its record and as parking offense evidence.Finally, can store described parking offense evidence, and statistics and inquiry service are provided, also described parking offense evidence can be reported interested regulatory authorities in time by remote transmission mode.
The close-up image of parking offense vehicle is obtained by step S15, the car plate of described parking offense vehicle is identified by step S16, described close-up image, car plate is recorded as parking offense evidence by step S17, the controversial of punishment on contravention of regulation can be avoided, thus ensure accuracy and the promptness of the parking behavior violating regulations being carried out to evidence obtaining investigation.
As preferred embodiment, as shown in Figure 5, identify that the step S16 of the car plate of described parking offense vehicle can comprise the following steps:
Step S161, carries out license diction and plate to described close-up image and obtains license plate image.License diction and plate acquisition license plate image is carried out to image and belongs to common practise, hereby do not repeat.
Step S162, extracts the texture gradient feature of described license plate image.
Step S163, obtains level and the vertical bank angle of car plate according to described texture gradient feature.The level and vertical bank angle that obtain car plate can be calculated according to Hough transformation algorithm.
Step S164, carries out affined transformation according to described level and vertical bank angle to described license plate image.
Step S165, according to the characters on license plate of the license plate image identification parking offense vehicle after affined transformation.Belong to common practise according to license plate image identification characters on license plate, hereby do not repeat.
The texture gradient feature of described license plate image is extracted by step S162, level and the vertical bank angle of car plate is obtained by step S163, by step S164, affined transformation is carried out to described license plate image, and then the correction that can realize license plate image, improve the accuracy rate of the characters on license plate identifying parking offense vehicle, improve further and the accuracy investigated and prosecuted of collecting evidence is carried out to the parking behavior violating regulations.
Embodiment 3
Fig. 6 shows a kind of parking offense supervisory system of the embodiment of the present invention 3, comprises acquisition module 61, judge module 62, computing module 63 and determination module 64.
Acquisition module 61 is corresponding with the step S11 in embodiment 1, for obtaining vehicle target.
Judge module 62 is corresponding with the step S12 in embodiment 1, for judging whether described vehicle target was recorded parking offense evidence in the first Preset Time.
Computing module 63 is corresponding with the step S13 in embodiment 1, for when not being recorded parking offense evidence in the first Preset Time, calculates the continuous rest time of described vehicle target.
Determination module 64 is corresponding with the step S14 in embodiment 1, for when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.
By judging whether described vehicle target was recorded parking offense evidence in the first Preset Time, can avoid repeating to capture to same vehicle, improve the accuracy rate judging parking offense vehicle, and by calculate described vehicle target continuous rest time and when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle, avoid to be judged to be parking offense vehicle by resident vehicle in short-term, and then parking behavior the carrying out evidence obtaining promptly and accurately realized violating regulations is investigated and prosecuted.
Hereafter the embodiment of technique scheme is introduced:
As preferred embodiment, acquisition module 61 comprises acquisition elementary area 611, filter element 612 and detecting unit 613.
Obtain elementary area 611 corresponding with the step S111 in embodiment 1, for obtaining monitoring scene image;
Filter element 612 is corresponding with the step S112 in embodiment 1, obtains background image for the moving target filtered in described monitoring scene image;
Detecting unit 613 is corresponding with the step S113 in embodiment 1, for detecting vehicle target from described background image.
Obtain monitoring scene image, the moving target filtered in described monitoring scene image obtains background image, finally from described background image, detect vehicle target, vehicle target can be obtained according to monitoring scene image rapidly like this, improve further and the promptness investigated and prosecuted of collecting evidence is carried out to the parking behavior violating regulations.
Further, as shown in Figure 7, detecting unit 613 comprises expansion limit subelement 6131, convergent-divergent subelement 6132, extracts feature subelement 6133 and sliding window scanning subelement 6134.
Expand limit subelement 6131 corresponding with the step S1131 in embodiment 1, for carrying out the process of expansion limit to described background image;
Convergent-divergent subelement 6132 is corresponding with the step S1132 in embodiment 1, forms image pyramid for carrying out convergent-divergent to the image behind expansion limit;
Extract feature subelement 6133 corresponding with the step S1133 in embodiment 1, for obtaining characteristic image to the image zooming-out texture gradient feature of often opening of described image pyramid;
Sliding window scanning subelement 6134 is corresponding with the step S1134 in embodiment 1, carries out moving window scanning obtain vehicle target for utilizing vehicle characteristics training pattern to described characteristic image.Described vehicle characteristics training pattern can be obtained by the step S31-step S34 in embodiment 1.
By carrying out the process of expansion limit to described background image, the vehicle at described background image edge can be detected, image pyramid is formed by carrying out convergent-divergent to the image behind expansion limit, the vehicle target of the upper different size size of original image can be detected, avoid shade, camera shake, pedestrian/vehicle/other objects block bring flase drop impact, improve the accuracy rate obtaining vehicle target, improve further and the accuracy investigated and prosecuted of collecting evidence is carried out to the parking behavior violating regulations.
Embodiment 4
Fig. 8 shows a kind of parking offense supervisory system of the embodiment of the present invention 4, is, also comprises with the difference of the described parking offense method for supervising in embodiment 3:
Obtain close-up image module 65 corresponding with the step S15 in embodiment 1, for obtaining the close-up image of parking offense vehicle;
Identify that car plate module 66 is corresponding with the step S16 in embodiment 1, for identifying the car plate of described parking offense vehicle;
Taking of evidence module 67 is corresponding with the step S17 in embodiment 1, for recording described close-up image, car plate as parking offense evidence.
Obtain the close-up image of parking offense vehicle, identify the car plate of described parking offense vehicle, record described close-up image, car plate as parking offense evidence, the controversial of punishment on contravention of regulation can be avoided, thus ensure accuracy and the promptness of the parking behavior violating regulations being carried out to evidence obtaining investigation.
As preferred embodiment, as shown in Figure 9, identify that car plate module 66 comprises:
License diction and plate unit 661 is corresponding with the step S161 in embodiment 1, obtains license plate image for carrying out license diction and plate to described close-up image;
Extract license plate image feature unit 662 corresponding with the step S162 in embodiment 1, for extracting the texture gradient feature of described license plate image;
Obtain angle module 663 corresponding with the step S163 in embodiment 1, for obtaining level and the vertical bank angle of car plate according to described texture gradient feature;
Affined transformation module 664 is corresponding with the step S164 in embodiment 1, for carrying out affined transformation according to described level and vertical bank angle to described license plate image;
Identification character module 665 is corresponding with the step S165 in embodiment 1, for the characters on license plate according to the license plate image identification parking offense vehicle after affined transformation.
Extract the texture gradient feature of described license plate image, obtain level and the vertical bank angle of car plate, affined transformation is carried out to described license plate image, and then the correction that can realize license plate image, improve the accuracy rate of the characters on license plate identifying parking offense vehicle, improve further and the accuracy investigated and prosecuted of collecting evidence is carried out to the parking behavior violating regulations.
Obviously, above-described embodiment is only for clearly example being described, and the restriction not to embodiment.For those of ordinary skill in the field, can also make other changes in different forms on the basis of the above description.Here exhaustive without the need to also giving all embodiments.And thus the apparent change of extending out or variation be still among the protection domain of the invention.
Claims (11)
1. a parking offense method for supervising, is characterized in that, comprises the following steps:
Obtain vehicle target;
Judge whether described vehicle target was recorded parking offense evidence in the first Preset Time;
When not being recorded parking offense evidence in the first Preset Time, calculated the continuous rest time of described vehicle target;
When described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.
2. parking offense method for supervising according to claim 1, is characterized in that, the step of described acquisition vehicle target comprises:
Obtain monitoring scene image;
The moving target filtered in described monitoring scene image obtains background image;
Vehicle target is detected from described background image.
3. parking offense method for supervising according to claim 2, is characterized in that, describedly from described background image, detects that the step of vehicle target comprises:
The process of expansion limit is carried out to described background image;
Convergent-divergent formation image pyramid is carried out to the image after expanding limit;
Characteristic image is obtained to the image zooming-out texture gradient feature of often opening of described image pyramid;
Utilize vehicle characteristics training pattern to carry out moving window scanning to described characteristic image and obtain vehicle target.
4. parking offense method for supervising according to claim 3, is characterized in that, described vehicle characteristics training pattern is obtained by following steps:
Obtain the vehicle image of different angles under different natural lighting condition;
Texture gradient feature is extracted to described vehicle image;
Cluster is carried out to described texture gradient feature;
The different classes of described texture gradient feature that cluster goes out is trained respectively, obtains the vehicle characteristics training pattern of each classification.
5. the parking offense method for supervising according to any one of claim 1-4, is characterized in that, described judge that described vehicle target is as parking offense vehicle after, also comprise:
Obtain the close-up image of parking offense vehicle;
Identify the car plate of described parking offense vehicle;
Record described close-up image, car plate as parking offense evidence.
6. parking offense method for supervising according to claim 5, is characterized in that, the step of the car plate of the described parking offense vehicle of described identification comprises:
License diction and plate is carried out to described close-up image and obtains license plate image;
Extract the texture gradient feature of described license plate image;
Level and the vertical bank angle of car plate is obtained according to described texture gradient feature;
According to described level and vertical bank angle, affined transformation is carried out to described license plate image;
According to the characters on license plate of the license plate image identification parking offense vehicle after affined transformation.
7. a parking offense supervisory system, is characterized in that, comprising:
Acquisition module, for obtaining vehicle target;
Judge module, for judging whether described vehicle target was recorded parking offense evidence in the first Preset Time;
Computing module, for when not being recorded parking offense evidence in the first Preset Time, calculated the continuous rest time of described vehicle target;
Determination module, for when described continuous rest time more than the second Preset Time time, judge that described vehicle target is as parking offense vehicle.
8. parking offense supervisory system according to claim 7, is characterized in that, described acquisition module comprises:
Obtain elementary area, for obtaining monitoring scene image;
Filter element, obtains background image for the moving target filtered in described monitoring scene image;
Detecting unit, for detecting vehicle target from described background image.
9. parking offense supervisory system according to claim 8, is characterized in that, described detecting unit comprises:
Expand limit subelement, for carrying out the process of expansion limit to described background image;
Convergent-divergent subelement, forms image pyramid for carrying out convergent-divergent to the image behind expansion limit;
Extract feature subelement, for obtaining characteristic image to the image zooming-out texture gradient feature of often opening of described image pyramid;
Sliding window scanning subelement, carries out moving window scanning for utilizing vehicle characteristics training pattern to described characteristic image and obtains vehicle target.
10. the parking offense supervisory system according to any one of claim 7-9, is characterized in that, also comprise:
Obtain close-up image module, for obtaining the close-up image of parking offense vehicle;
Identify car plate module, for identifying the car plate of described parking offense vehicle;
Taking of evidence module, for recording described close-up image, car plate as parking offense evidence.
11. parking offense supervisory systems according to claim 10, is characterized in that, described identification car plate module comprises:
License diction and plate unit, obtains license plate image for carrying out license diction and plate to described close-up image;
Extract license plate image feature unit, for extracting the texture gradient feature of described license plate image;
Obtain angle module, for obtaining level and the vertical bank angle of car plate according to described texture gradient feature;
Affined transformation module, for carrying out affined transformation according to described level and vertical bank angle to described license plate image;
Identification character module, for the characters on license plate according to the license plate image identification parking offense vehicle after affined transformation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510019175.1A CN104504908A (en) | 2015-01-14 | 2015-01-14 | Monitoring method and system for illegal parking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510019175.1A CN104504908A (en) | 2015-01-14 | 2015-01-14 | Monitoring method and system for illegal parking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104504908A true CN104504908A (en) | 2015-04-08 |
Family
ID=52946510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510019175.1A Pending CN104504908A (en) | 2015-01-14 | 2015-01-14 | Monitoring method and system for illegal parking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104504908A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046966A (en) * | 2015-05-08 | 2015-11-11 | 天津大学 | System and method for automatically detecting illegal parking behaviors in drop-off areas |
| CN105303825A (en) * | 2015-09-07 | 2016-02-03 | 北京信路威科技股份有限公司 | Violating inclined side parking evidence obtaining device and method |
| CN105303826A (en) * | 2015-09-07 | 2016-02-03 | 北京信路威科技股份有限公司 | Violating side parking evidence obtaining device and method |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN107748866A (en) * | 2017-10-20 | 2018-03-02 | 河北机电职业技术学院 | illegal parking automatic identifying method and device |
| US9940524B2 (en) | 2015-04-17 | 2018-04-10 | General Electric Company | Identifying and tracking vehicles in motion |
| US10043307B2 (en) | 2015-04-17 | 2018-08-07 | General Electric Company | Monitoring parking rule violations |
| CN108922195A (en) * | 2018-06-07 | 2018-11-30 | 安徽清新互联信息科技有限公司 | Illegal parking automatic evidence collecting system and its control method |
| CN110689054A (en) * | 2019-09-10 | 2020-01-14 | 华中科技大学 | Worker violation monitoring method |
| CN110880243A (en) * | 2019-11-19 | 2020-03-13 | 北京市公安局公安交通管理局东城交通支队 | Road illegal parking management method based on high-order video roadside parking charging equipment |
| US10616465B2 (en) | 2015-09-16 | 2020-04-07 | Microsoft Technology Licensing, Llc | Bandwidth efficient video surveillance system |
| CN111027558A (en) * | 2019-10-23 | 2020-04-17 | 中电科新型智慧城市研究院有限公司 | Method for recognizing type and license plate of violation vehicle |
| CN111160339A (en) * | 2019-12-24 | 2020-05-15 | 浙江大华技术股份有限公司 | License plate correction method, image processing equipment and device with storage function |
| CN112001319A (en) * | 2020-08-25 | 2020-11-27 | 天地伟业技术有限公司 | Method for filtering repeated license plates of illegal ball-stopping machine |
| CN112232441A (en) * | 2020-11-18 | 2021-01-15 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
| US11010623B2 (en) | 2019-05-08 | 2021-05-18 | Mitac Digital Technology Corporation | Method and system for detecting parking violation |
| CN114299503A (en) * | 2021-12-15 | 2022-04-08 | 深圳云天励飞技术股份有限公司 | License plate recognition method and device, electronic equipment and storage medium |
| WO2022247932A1 (en) * | 2021-05-27 | 2022-12-01 | 北京万集科技股份有限公司 | Method and system for recognizing traffic violation participant, and computer-readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100820952B1 (en) * | 2008-01-04 | 2008-04-11 | 한국비전기술(주) | Detecting method at automatic police enforcement system of illegal-stopping and parking vehicle using single camera and system thereof |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| KR101057882B1 (en) * | 2011-02-28 | 2011-08-19 | 심광호 | Wanted-vehicle and illegal parking crackdown system |
| CN102855758A (en) * | 2012-08-27 | 2013-01-02 | 无锡北邮感知技术产业研究院有限公司 | Detection method for vehicle in breach of traffic rules |
| CN103093194A (en) * | 2013-01-07 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Breach of regulation vehicle detection method and device based on videos |
| CN103390164A (en) * | 2012-05-10 | 2013-11-13 | 南京理工大学 | Object detection method based on depth image and implementing device thereof |
| CN103793708A (en) * | 2014-03-05 | 2014-05-14 | 武汉大学 | Multi-scale license plate precise locating method based on affine correction |
| CN103927878A (en) * | 2014-04-10 | 2014-07-16 | 中海网络科技股份有限公司 | Automatic snapshot device and method for illegal parking |
-
2015
- 2015-01-14 CN CN201510019175.1A patent/CN104504908A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100820952B1 (en) * | 2008-01-04 | 2008-04-11 | 한국비전기술(주) | Detecting method at automatic police enforcement system of illegal-stopping and parking vehicle using single camera and system thereof |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| KR101057882B1 (en) * | 2011-02-28 | 2011-08-19 | 심광호 | Wanted-vehicle and illegal parking crackdown system |
| CN103390164A (en) * | 2012-05-10 | 2013-11-13 | 南京理工大学 | Object detection method based on depth image and implementing device thereof |
| CN102855758A (en) * | 2012-08-27 | 2013-01-02 | 无锡北邮感知技术产业研究院有限公司 | Detection method for vehicle in breach of traffic rules |
| CN103093194A (en) * | 2013-01-07 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Breach of regulation vehicle detection method and device based on videos |
| CN103793708A (en) * | 2014-03-05 | 2014-05-14 | 武汉大学 | Multi-scale license plate precise locating method based on affine correction |
| CN103927878A (en) * | 2014-04-10 | 2014-07-16 | 中海网络科技股份有限公司 | Automatic snapshot device and method for illegal parking |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10380430B2 (en) | 2015-04-17 | 2019-08-13 | Current Lighting Solutions, Llc | User interfaces for parking zone creation |
| US11328515B2 (en) | 2015-04-17 | 2022-05-10 | Ubicquia Iq Llc | Determining overlap of a parking space by a vehicle |
| US10872241B2 (en) | 2015-04-17 | 2020-12-22 | Ubicquia Iq Llc | Determining overlap of a parking space by a vehicle |
| US9940524B2 (en) | 2015-04-17 | 2018-04-10 | General Electric Company | Identifying and tracking vehicles in motion |
| US10043307B2 (en) | 2015-04-17 | 2018-08-07 | General Electric Company | Monitoring parking rule violations |
| CN105046966A (en) * | 2015-05-08 | 2015-11-11 | 天津大学 | System and method for automatically detecting illegal parking behaviors in drop-off areas |
| CN105303825A (en) * | 2015-09-07 | 2016-02-03 | 北京信路威科技股份有限公司 | Violating inclined side parking evidence obtaining device and method |
| CN105303826A (en) * | 2015-09-07 | 2016-02-03 | 北京信路威科技股份有限公司 | Violating side parking evidence obtaining device and method |
| US10616465B2 (en) | 2015-09-16 | 2020-04-07 | Microsoft Technology Licensing, Llc | Bandwidth efficient video surveillance system |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN107748866B (en) * | 2017-10-20 | 2020-02-14 | 河北机电职业技术学院 | Illegal parking automatic identification method and device |
| CN107748866A (en) * | 2017-10-20 | 2018-03-02 | 河北机电职业技术学院 | illegal parking automatic identifying method and device |
| CN108922195A (en) * | 2018-06-07 | 2018-11-30 | 安徽清新互联信息科技有限公司 | Illegal parking automatic evidence collecting system and its control method |
| US11010623B2 (en) | 2019-05-08 | 2021-05-18 | Mitac Digital Technology Corporation | Method and system for detecting parking violation |
| CN110689054A (en) * | 2019-09-10 | 2020-01-14 | 华中科技大学 | Worker violation monitoring method |
| CN110689054B (en) * | 2019-09-10 | 2022-04-01 | 华中科技大学 | Worker violation monitoring method |
| CN111027558A (en) * | 2019-10-23 | 2020-04-17 | 中电科新型智慧城市研究院有限公司 | Method for recognizing type and license plate of violation vehicle |
| CN110880243B (en) * | 2019-11-19 | 2021-03-09 | 北京市公安局公安交通管理局东城交通支队 | Road illegal parking management method based on high-order video roadside parking charging equipment |
| CN110880243A (en) * | 2019-11-19 | 2020-03-13 | 北京市公安局公安交通管理局东城交通支队 | Road illegal parking management method based on high-order video roadside parking charging equipment |
| CN111160339B (en) * | 2019-12-24 | 2023-05-16 | 浙江大华技术股份有限公司 | License plate correction method, image processing equipment and device with storage function |
| CN111160339A (en) * | 2019-12-24 | 2020-05-15 | 浙江大华技术股份有限公司 | License plate correction method, image processing equipment and device with storage function |
| CN112001319A (en) * | 2020-08-25 | 2020-11-27 | 天地伟业技术有限公司 | Method for filtering repeated license plates of illegal ball-stopping machine |
| CN112001319B (en) * | 2020-08-25 | 2024-04-23 | 天地伟业技术有限公司 | Repeated license plate filtering method of illegal ball stopping machine |
| CN112232441A (en) * | 2020-11-18 | 2021-01-15 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
| CN112232441B (en) * | 2020-11-18 | 2023-06-06 | 中国联合网络通信集团有限公司 | Illegal parking judgment method, system, computer equipment and storage medium |
| WO2022247932A1 (en) * | 2021-05-27 | 2022-12-01 | 北京万集科技股份有限公司 | Method and system for recognizing traffic violation participant, and computer-readable storage medium |
| CN114299503A (en) * | 2021-12-15 | 2022-04-08 | 深圳云天励飞技术股份有限公司 | License plate recognition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104504908A (en) | Monitoring method and system for illegal parking | |
| CN111368687B (en) | Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation | |
| Qadri et al. | Automatic number plate recognition system for vehicle identification using optical character recognition | |
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| CN202077142U (en) | Vehicle-mounted intelligent video detecting and analyzing system | |
| US20150161796A1 (en) | Method and device for recognizing pedestrian and vehicle supporting the same | |
| CN106652468A (en) | Device and method for detection of violation of front vehicle and early warning of violation of vehicle on road | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN102231236B (en) | Method and device for counting vehicles | |
| CN107609491A (en) | A kind of vehicle peccancy parking detection method based on convolutional neural networks | |
| Jadhav et al. | Smart traffic control system using image processing | |
| CN102509090B (en) | A kind of vehicle feature recognition device based on public safety video image in sky net engineering | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN103226891B (en) | Video-based vehicle collision accident detection method and system | |
| CN103021175A (en) | Pedestrian red light running video detection method and device based on Davinci architecture | |
| CN111161312B (en) | Object trajectory tracking and identifying device and system based on computer vision | |
| CN103106766A (en) | Forest fire identification method and forest fire identification system | |
| CN111209780A (en) | Lane line attribute detection method and device, electronic device and readable storage medium | |
| CN101739809A (en) | Automatic alarm and monitoring system for pedestrian running red light | |
| CN110852177B (en) | Obstacle detection method and system based on monocular camera | |
| CN113676702B (en) | Video stream-based target tracking and monitoring method, system, device and storage medium | |
| CN201307337Y (en) | Automatic alarming and monitoring device for traffic-lights nonobservance of pedestrian | |
| CN104537360A (en) | Method and system for detecting vehicle violation of not giving way | |
| Ketcham et al. | Recognizing the Illegal Parking Patterns of Cars on the Road in Front of the Bus Stop Using the Support Vector Machine | |
| CN105046948A (en) | System and method of monitoring illegal traffic parking in yellow grid line area |
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: 20150408 |
|
| RJ01 | Rejection of invention patent application after publication |