CN103021186B - Vehicle monitoring method and vehicle monitoring system - Google Patents
Vehicle monitoring method and vehicle monitoring system Download PDFInfo
- Publication number
- CN103021186B CN103021186B CN201210584612.0A CN201210584612A CN103021186B CN 103021186 B CN103021186 B CN 103021186B CN 201210584612 A CN201210584612 A CN 201210584612A CN 103021186 B CN103021186 B CN 103021186B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- magnetic test
- test coil
- judge
- reposition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a vehicle monitoring method and a vehicle monitoring system. The method includes: detecting vehicle movement information by the aid of a detecting coil covering in a lane; tracking a vehicle entering a detecting coil area by the aid of a camera, and generating a movement track including vehicle travelling information after tracking is finished; and judging whether the vehicle violates regulations or not according to the movement track and the vehicle travelling information detected by the detecting coil. By the aid of the method, vehicles are monitored in real time, and a guarantee is provided for urban traffic safety.
Description
Technical field
The present invention relates to area of pattern recognition, particularly relate to a kind of method and system of vehicle monitoring.
Background technology
The monitoring of vehicle and be the main research of Intelligent Vehicle Monitoring System to its corelation behaviour analysis in road traffic environment is also one of important research direction of field of intelligent video surveillance.Typically mix in road traffic system in such one of China, pedestrian and vehicle constitute the main body of road traffic.By intelligent video analysis technology, vehicle movement target is accurately detected, robust tracking and Accurate classification, and obtain movement locus, the characteristic information such as movement velocity and direction of target, thus realize such as vehicle Flow Detection and vehicle abnormality behavioral value etc., be the study hotspot of current intelligent transportation field.In conjunction with real road traffic environment, realize the detection and tracking accurately to vehicle, the fast development of promotion intelligent transport technology and comprehensive coverage urban road traffic safety are had important practical significance.
Although current vehicle monitoring system has much all used video as information source, but video information used mainly as post-mordem forensics, and most of vehicle monitoring system is due to hardware reason, its installation need adjust according to actual monitored scene, amendment is comparatively complicated, does not have general applicability.
Summary of the invention
The object of this invention is to provide a kind of method and system of vehicle monitoring, achieve the real-time monitoring of vehicle, for urban traffic safety provides guarantee.
A method for vehicle monitoring, the method comprises:
Vehicle movable information is detected by the magnetic test coil covered in track;
Utilize video camera to follow the tracks of the vehicle entering this magnetic test coil region, after tracking terminates, generate the movement locus comprising vehicle traveling information;
Judge whether vehicle breaks rules and regulations according to the vehicle movement information that described movement locus and magnetic test coil detect.
A system for vehicle monitoring, this system comprises:
Magnetic test coil, detects vehicle movable information for covering in track;
Trace generator module, for utilizing video camera to follow the tracks of the vehicle entering this magnetic test coil region, after tracking terminates, generates the movement locus comprising vehicle traveling information;
For the vehicle movement information detected according to described movement locus and magnetic test coil, judge module violating the regulations, judges whether vehicle breaks rules and regulations.
As seen from the above technical solution provided by the invention, by arranging magnetic test coil, and on the basis of automobile detecting following, completing vehicle flowrate and judgement violating the regulations, improve vehicle monitoring system intelligent, for urban traffic safety provides guarantee.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
The process flow diagram of the method for a kind of vehicle monitoring that Fig. 1 provides for the embodiment of the present invention one;
The process flow diagram of the method for another vehicle monitoring that Fig. 2 provides for the embodiment of the present invention two;
The schematic diagram of the system of a kind of vehicle monitoring that Fig. 3 provides for the embodiment of the present invention three.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on embodiments of the invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to protection scope of the present invention.
Embodiment one
The process flow diagram of the method for a kind of vehicle monitoring that Fig. 1 provides for the embodiment of the present invention one, mainly comprises the steps:
Step 101, detect vehicle movable information by covering magnetic test coil in track.
Magnetic test coil can be divided into two types: common magnetic test coil and line ball magnetic test coil.
Wherein, common magnetic test coil is quadrilateral, is laid on a certain track, can adjust four summits of magnetic test coil according to demand to regulate its size, shape and position.Carry out wagon flow quantitative statistics according to statistics by the vehicle of this magnetic test coil, such as, when vehicle is through this magnetic test coil, add 1 by the vehicle fleet size in this track, magnetic test coil place.In addition, this magnetic test coil can also detect the travel direction of vehicle, such as, judges its travel direction according to same car through the order of this magnetic test coil.
Line ball magnetic test coil, it is arranged on (such as, yellow line) on the graticule between track, and for detecting vehicle, whether line ball travels.
Can effectively monitor vehicle running state by arranging above-mentioned two kinds of coils.
Step 102, utilize video camera to follow the tracks of the vehicle entering this magnetic test coil region, after tracking terminates, generate the movement locus comprising vehicle movement information.
The present embodiment only processes for the video data in magnetic test coil region.Namely start when vehicle enters within the scope of magnetic test coil to follow the tracks of, stop when leaving or leaving magnetic test coil scope following the tracks of.
By the extraction of motion information of vehicle within the scope of magnetic test coil, and generate for carrying out the movement locus judged violating the regulations.
Step 103, the vehicle movement information detected according to described movement locus and magnetic test coil judge whether vehicle breaks rules and regulations.
The Kalman filter smoothing algorithm of based target orientation, size first can be adopted to carry out track filtering analyze described movement locus, obtain the information such as the position of the travel direction of vehicle, the travel speed of vehicle and vehicle;
To combine with the information that magnetic test coil detects according to information such as the positions of the travel direction of vehicle obtained, the travel speed of vehicle and vehicle and carry out breaking rules and regulations to judge:
Drive in the wrong direction and judge: whether the angle in the direction that the travel direction judging described vehicle and common magnetic test coil detect is greater than 90 °, if be positive integer at continuous print N(N, such as 10) be all greater than 90 ° in this angle of two field picture, then judge that this vehicle is retrograde;
Hypervelocity judges: the travel speed and the max-thresholds magnitude relationship that judge described vehicle; If the travelling speed of this vehicle is all greater than max-thresholds in continuous print N two field picture, then judge that this overspeed of vehicle travels;
Parking offense judges: judge the travel speed of described vehicle and the magnitude relationship of minimum threshold; If the travelling speed of this vehicle is all less than minimum threshold in continuous print N two field picture, then judge that this vehicle peccancy stops;
Line ball travels and judges: judge whether the central point of the position tracking box representing this vehicle enters the region of line ball magnetic test coil, if so, then judges that this vehicle line ball travels.
Further, after judgement violating the regulations terminates, the colour picture of this vehicle is preserved.In addition, if judge this vehicle peccancy, then automatic alarm; Such as, glimmered and show red font by this vehicle tracking frame on the display screen, font content is kind violating the regulations, processes to remind staff; And the act of violating regulations kind of this vehicle, time violating the regulations and location information and photochrome are preserved in file as the summary info of this vehicle, post-mordem forensics is inquired about more convenient.
The embodiment of the present invention by arranging magnetic test coil, and on the basis of automobile detecting following, completes vehicle flowrate and judgement violating the regulations, improves vehicle monitoring system intelligent, for urban traffic safety provides guarantee.
Embodiment two
For the ease of understanding the present invention, below in conjunction with accompanying drawing 2, the present invention will be further described, as shown in Figure 2, mainly comprises the steps:
Step 201, arrange cover in track for detecting vehicle movable information magnetic test coil.
Magnetic test coil can be divided into two types: common magnetic test coil and line ball magnetic test coil.
Wherein, common magnetic test coil is quadrilateral, is laid on a certain track, can adjust four summits of magnetic test coil according to demand to regulate its size, shape and position.Carry out wagon flow quantitative statistics according to statistics by the vehicle of this common magnetic test coil, such as, when vehicle is through this magnetic test coil, add 1 by the vehicle fleet size in this track, magnetic test coil place.In addition, this magnetic test coil can also detect the travel direction of vehicle, such as, judges its travel direction according to same car through the order of this common magnetic test coil.
Line ball magnetic test coil, it is arranged on (such as, yellow line) on the graticule between track, and for detecting vehicle, whether line ball travels.
Effectively can monitor vehicle running state by arranging above-mentioned two kinds of coils, and the amount of video information of system process can be made to reduce, improve overall real-time.
Step 202, the vehicle entering magnetic test coil region to be detected.
Because vehicle monitoring scene is road, the moving target in road comprises pedestrian and vehicle, therefore, needs to distinguish moving target, and extracts vehicle target as monitored object.
The present embodiment adopts and detects vehicle target based on Background difference; Needed first to detect before carrying out this algorithm camera acquisition to image whether be RGB(three primary colours) image, if so, then can directly use, otherwise, need rgb format be converted to.The concrete steps of Background difference: carry out background modeling to RGB image, obtain foreground image, then detect one or more moving target in foreground image, and extract the large Small object connected region profile representing moving target; The size of target connected region profile obtained and the threshold value of setting are compared, if be greater than this threshold value, then judges that this moving target is as vehicle.
Step 203, the vehicle in magnetic test coil region to be followed the tracks of, after tracking terminates, generate movement locus.
After vehicle being detected, average drift Mean Shift and particle filter Particle Filter hybrid tracking algorithm is adopted to follow the tracks of the vehicle detected, to ensure that vehicle tracking has certain robustness.Track algorithm is divided into following steps:
(1) by representing that the target connected region profile of vehicle is birdsed of the same feather flock together, vehicle list is obtained;
(2) reposition of each vehicle in the list of Kalman Kalman filter prediction vehicle is utilized; Wherein, this Kalman filter iteration system equation is:
x(k)＝A×x(k-1)+B×u(k)+w(k)
z(k)＝H×x(k)+v(k)
x(k)＝x'(k)+K(k)×(z(k)-H*x'(k))
P'(k)＝A×P(k-1)×A
t+Q
K(k)＝P'(k)×H
t×inv(H×P'(k)×H
t+R)
P(k)＝(1-K(k)×H)×P'(k)；
Wherein, x' is predicted state, x is correcting state, and A is state-transition matrix, and B is gating matrix, H is calculation matrix, Q is noise covariance matrix, and R is measurement noises covariance matrix, and P' is the estimation of error covariance matrix of priori, K is Kalman matrix, and P is posteriori error estimate covariance matrix.
(3) vehicle collision detection is carried out by predicting the outcome of Kalman Kalman filter: if be same position in the predicting the outcome of multiple vehicle, then judge collision happens, then adopt Mean Shift and Particle Filter hybrid algorithm to follow the tracks of the vehicle collided, and the position obtained with tracking is as its reposition; Otherwise, judge that vehicle does not collide, the following two kinds situation can be divided into: if reposition only the predicting the outcome of a corresponding vehicle, then predict the outcome as its reposition using this vehicle; If predicting the outcome of the corresponding vehicle of multiple reposition, then search best reposition: carry out predicting the outcome respectively according to histogram minimum Pasteur Bhattacharyya Furthest Neighbor in Mean Shift algorithm calculating the confidence level obtaining correspondence, what confidence level was maximum predict the outcome, and corresponding position is then optimum position, and with the reposition of described optimum position as this vehicle; In addition, also can verify described optimum position, such as, adopt spatially minimum distance method check whether to mate with described optimum position apart from minimum position.
Use said method to carry out vehicle tracking, after tracking terminates, generate the movement locus comprising vehicle heading, speed and position.
Wherein, when occurring following situation, then judges to follow the tracks of end: such as, when continuous T (T as positive integer, 3 frames), frame vehicle area is all less than setting threshold value, or the edge of vehicle is in beyond image, or the size of the connected region profile of this vehicle is less than threshold value.
Step 204, movement locus to be analyzed.
The Kalman filter smoothing algorithm of based target orientation, size can be adopted to carry out track filtering, again in conjunction with the relevant information of magnetic test coil, evaluating objects track, obtains the information such as the speed of vehicle, travel direction and position, for the judgement of vehicle behavior provides the most direct data.
Step 205, being combined with the testing result of magnetic test coil by the analysis result of movement locus judges whether vehicle breaks rules and regulations.
To combine with the information that magnetic test coil detects according to information such as the positions of the travel direction of vehicle obtained, the travel speed of vehicle and vehicle and carry out breaking rules and regulations to judge:
Drive in the wrong direction and judge: whether the angle in the direction that the travel direction judging described vehicle and common magnetic test coil detect is greater than 90 °, if be positive integer at continuous print N(N, such as 10) be all greater than 90 ° in this angle of two field picture, then judge that this vehicle is retrograde;
Hypervelocity judges: the travel speed and the max-thresholds magnitude relationship that judge described vehicle; If the travelling speed of this vehicle is all greater than max-thresholds in continuous print N two field picture, then judge that this overspeed of vehicle travels;
Parking offense judges: judge the travel speed of described vehicle and the magnitude relationship of minimum threshold; If the travelling speed of this vehicle is all less than minimum threshold in continuous print N two field picture, then judge that this vehicle peccancy stops;
Line ball travels and judges: judge whether the central point of the position tracking box representing this vehicle enters the region of line ball magnetic test coil, if so, then judges that this vehicle line ball travels.
Further, after judgement violating the regulations terminates, the colour picture of this vehicle is preserved.In addition, if judge this vehicle peccancy, then automatic alarm; Such as, glimmered and show red font by this vehicle tracking frame on the display screen, font content is kind violating the regulations, processes to remind staff; And the act of violating regulations kind of this vehicle, time violating the regulations and location information and photochrome are preserved in file as the summary info of this vehicle, post-mordem forensics is inquired about more convenient.
The embodiment of the present invention by arranging magnetic test coil, and on the basis of automobile detecting following, completes vehicle flowrate and judgement violating the regulations, improves vehicle monitoring system intelligent, for urban traffic safety provides guarantee.
Through the above description of the embodiments, those skilled in the art can be well understood to above-described embodiment can by software simulating, and the mode that also can add necessary general hardware platform by software realizes.Based on such understanding, the technical scheme of above-described embodiment can embody with the form of software product, it (can be CD-ROM that this software product can be stored in a non-volatile memory medium, USB flash disk, portable hard drive etc.) in, comprise some instructions and perform method described in each embodiment of the present invention in order to make a computer equipment (can be personal computer, server, or the network equipment etc.).
Embodiment three
The schematic diagram of the system of a kind of vehicle monitoring that Fig. 3 provides for the embodiment of the present invention three, this system mainly comprises:
Magnetic test coil 31, detects vehicle movable information for covering in track;
Information of vehicles acquisition module 32, for utilizing video camera to follow the tracks of the vehicle entering this magnetic test coil region, after tracking terminates, generates the movement locus comprising vehicle traveling information;
For the vehicle movement information detected according to described movement locus and magnetic test coil, judge module 33 violating the regulations, judges whether vehicle breaks rules and regulations.
Described magnetic test coil 31 comprises: common magnetic test coil 311 and line ball magnetic test coil 312;
Described common magnetic test coil 311 is quadrilateral, arranges and covers on track; For being obtained the travel direction of vehicle by the order of this magnetic test coil according to the same vehicle of detection, and carry out wagon flow quantitative statistics according to statistics by the vehicle of this magnetic test coil;
Described line ball coil 312 is arranged on the graticule between track, and for detecting vehicle, whether line ball travels.
Described information of vehicles acquisition module 32 comprises:
Vehicle detection module 321, for detecting vehicle target based on Background difference; Concrete: background modeling is carried out to the image that video camera photographs, obtains foreground image, detect one or more moving target in foreground image, and extract the large Small object connected region profile representing moving target; The size of target connected region profile obtained and the threshold value of setting are compared, if be greater than this threshold value, then judges that this moving target is as vehicle;
Vehicle tracking module 322, follows the tracks of the vehicle target detected for adopting average drift Mean Shift and particle filter Particle Filter hybrid tracking algorithm; Concrete: by representing that the target connected region profile of vehicle is birdsed of the same feather flock together, obtain vehicle list; Utilize the reposition of each vehicle in the list of kalman Kalman filter prediction vehicle;
If be same position in the predicting the outcome of multiple vehicle, then judge collision happens, then adopt Mean Shift and Particle Filter hybrid algorithm to follow the tracks of the vehicle collided, and the position obtained with tracking is as its reposition; If reposition only the predicting the outcome of a corresponding vehicle, then predict the outcome as its reposition using this vehicle; If predicting the outcome of the corresponding vehicle of multiple reposition, then search best reposition: carry out predicting the outcome respectively according to histogram minimum Pasteur Bhattacharyya Furthest Neighbor in Mean Shift algorithm calculating the confidence level obtaining correspondence, what confidence level was maximum predict the outcome, and corresponding position is then optimum position, and with the reposition of described optimum position as this vehicle.
Follow the tracks of and terminate judge module 323, terminate for judging whether to follow the tracks of: if continuous T frame vehicle area is all less than setting threshold value, or the edge of vehicle is in beyond image, or the size of the connected region profile of this vehicle is less than threshold value, then judge to follow the tracks of to terminate, wherein T is positive integer;
Trace generator module 324, for after judgement tracking terminates, generates the movement locus comprising vehicle heading, speed and positional information.
Described judge module violating the regulations 33 comprises:
Gripper path analysis module 331, for analyzing described movement locus, combining the vehicle movement information that analysis result and magnetic test coil detect and judging whether vehicle breaks rules and regulations; Wherein, the Kalman filter smoothing algorithm of employing based target orientation, size carries out track filtering and analyzes described movement locus, obtains the positional information of the travel direction of vehicle, the travel speed of vehicle and vehicle.
Drive in the wrong direction judge module 332, and whether the angle in the direction detected in the travel direction that judges described vehicle with common magnetic test coil is greater than 90 °, if be all greater than 90 ° in this angle of continuous print N two field picture, then judge that this vehicle is retrograde, wherein, N is positive integer;
Hypervelocity judge module 333, for the magnitude relationship of the travel speed and max-thresholds that judge described vehicle; If the travelling speed of this vehicle is all greater than max-thresholds in continuous print N two field picture, then judge that this overspeed of vehicle travels;
Parking offense judge module 334, for the magnitude relationship of the travel speed and minimum threshold that judge described vehicle; If the travelling speed of this vehicle is all less than minimum threshold in continuous print N two field picture, then judge that this vehicle peccancy stops;
Line ball travels judge module 335, for judging whether the central point of the position tracking box representing this vehicle enters the region of line ball magnetic test coil, if so, then judges that this vehicle line ball travels;
Described system also comprises:
Vehicle summary preserves module 34, and for preservation vehicle summary info after judgement violating the regulations terminates, this summary info comprises: the colour picture of vehicle; If this vehicle peccancy, then also comprise type of violation, time violating the regulations and place violating the regulations.
It should be noted that, have a detailed description in the specific implementation of the function that each processing module comprised in said system realizes each embodiment above, therefore here repeat no more.
Those skilled in the art can be well understood to, for convenience and simplicity of description, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by system is divided into different functional modules, to complete all or part of function described above.
In several embodiments that the application provides, should be understood that disclosed system and method can realize by another way.Such as, system embodiment described above is only schematic, such as, the division of described module, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple module can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of system or module or communication connection can be electrical, machinery or other form.
The above; be only the present invention's preferably embodiment, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (8)
1. a method for vehicle monitoring, is characterized in that, the method comprises:
Vehicle movable information is detected by the magnetic test coil covered in track;
Utilize video camera to follow the tracks of the vehicle entering this magnetic test coil region, after tracking terminates, generate the movement locus comprising vehicle traveling information; Concrete: detect vehicle target based on Background difference; Concrete: background modeling is carried out to the image that video camera photographs, obtains foreground image, detect one or more moving target in foreground image, and extract the large Small object connected region profile representing moving target; The size of target connected region profile obtained and the threshold value of setting are compared, if be greater than this threshold value, then judges that this moving target is as vehicle; Average drift Mean Shift and particle filter Particle Filter hybrid tracking algorithm is adopted to follow the tracks of the vehicle detected; Concrete: by representing that the target connected region profile of vehicle is birdsed of the same feather flock together, obtain vehicle list; Utilize the reposition of each vehicle in the list of Kalman Kalman filter prediction vehicle; If be same position in the predicting the outcome of multiple vehicle, then judge collision happens, then adopt mean shift and Particle Filter hybrid algorithm to follow the tracks of the vehicle collided, and the position obtained with tracking is as its reposition; If reposition only the predicting the outcome of a corresponding vehicle, then predict the outcome as its reposition using this vehicle; If predicting the outcome of the corresponding vehicle of multiple reposition, then search best reposition: carry out predicting the outcome respectively according to histogram minimum Pasteur Bhattacharyya Furthest Neighbor in Mean Shift algorithm calculating the confidence level obtaining correspondence, what confidence level was maximum predict the outcome, and corresponding position is then optimum position, and with the reposition of described optimum position as this vehicle; Follow the tracks of and terminate to judge: if continuous T frame vehicle area is all less than setting threshold value, or the edge of vehicle is in beyond image, or the size of the connected region profile of this vehicle is less than threshold value, then judge to follow the tracks of and terminate, wherein T is positive integer; After judgement tracking terminates, generate the movement locus comprising vehicle heading, speed and positional information
Judge whether vehicle breaks rules and regulations according to the vehicle movement information that described movement locus and magnetic test coil detect.
2. method according to claim 1, is characterized in that, described magnetic test coil comprises: common magnetic test coil and line ball magnetic test coil;
Described common magnetic test coil is quadrilateral, is arranged on a certain track; According to detecting the travel direction of same vehicle by the order acquisition vehicle of this magnetic test coil, and carry out wagon flow quantitative statistics according to statistics by the vehicle of this magnetic test coil;
Described line ball coil is arranged on the graticule between track, and for detecting vehicle, whether line ball travels.
3. method according to claim 1 and 2, is characterized in that, the vehicle movement information that the described movement locus according to generation and magnetic test coil detect judges that the step whether vehicle breaks rules and regulations comprises:
The Kalman filter smoothing algorithm of employing based target orientation, size carries out track filtering and analyzes described movement locus, obtains the positional information of the travel direction of vehicle, the travel speed of vehicle and vehicle;
The positional information of the acquisition travel direction of vehicle, the travel speed of vehicle and vehicle is combined with the vehicle movement information that magnetic test coil detects and judges whether vehicle breaks rules and regulations:
Judge whether the angle in the direction that the travel direction of described vehicle and common magnetic test coil detect is greater than 90 °, if be all greater than 90 ° in this angle of continuous print N two field picture, then judge that this vehicle drives in the wrong direction, wherein, N is positive integer;
Judge the travel speed of described vehicle and the magnitude relationship of max-thresholds; If the travelling speed of this vehicle is all greater than max-thresholds in continuous print N two field picture, then judge that this overspeed of vehicle travels;
Judge the travel speed of described vehicle and the magnitude relationship of minimum threshold; If the travelling speed of this vehicle is all less than minimum threshold in continuous print N two field picture, then judge that this vehicle peccancy stops;
Judge whether the central point of the position tracking box representing this vehicle enters the region of line ball magnetic test coil, if so, then judges that this vehicle line ball travels.
4. method according to claim 1 and 2, is characterized in that, the method also comprises:
Preservation vehicle summary info after judgement violating the regulations terminates, this summary info comprises: the colour picture of vehicle; If this vehicle peccancy, then also comprise type of violation, time violating the regulations and place violating the regulations.
5. a system for vehicle monitoring, is characterized in that, this system comprises:
Magnetic test coil, detects vehicle movable information for covering in track;
Information of vehicles acquisition module, for utilizing video camera to follow the tracks of the vehicle entering this magnetic test coil region, after tracking terminates, generates the movement locus comprising vehicle traveling information;
Wherein, described information of vehicles acquisition module comprises: vehicle detection module, for detecting vehicle target based on Background difference; Concrete: background modeling is carried out to the image that video camera photographs, obtains foreground image, detect one or more moving target in foreground image, and extract the large Small object connected region profile representing moving target; The size of target connected region profile obtained and the threshold value of setting are compared, if be greater than this threshold value, then judges that this moving target is as vehicle; Vehicle tracking module, follows the tracks of the vehicle target detected for adopting average drift Mean Shift and particle filter Particle Filter hybrid tracking algorithm; Concrete: by representing that the target connected region profile of vehicle is birdsed of the same feather flock together, obtain vehicle list; Utilize the reposition of each vehicle in the list of Kalman Kalman filter prediction vehicle; If be same position in the predicting the outcome of multiple vehicle, then judge collision happens, then adopt Mean Shift and Particle Filter hybrid algorithm to follow the tracks of the vehicle collided, and the position obtained with tracking is as its reposition; If reposition only the predicting the outcome of a corresponding vehicle, then predict the outcome as its reposition using this vehicle; If predicting the outcome of the corresponding vehicle of multiple reposition, then search best reposition: carry out predicting the outcome respectively according to histogram minimum Pasteur Bhattacharyya Furthest Neighbor in Mean Shift algorithm calculating the confidence level obtaining correspondence, what confidence level was maximum predict the outcome, and corresponding position is then optimum position, and with the reposition of described optimum position as this vehicle; Follow the tracks of and terminate judge module, terminate for judging whether to follow the tracks of: if continuous T frame vehicle area is all less than setting threshold value, or the edge of vehicle is in beyond image, or the size of the connected region profile of this vehicle is less than threshold value, then judge to follow the tracks of to terminate, wherein T is positive integer; Trace generator module, for after judgement tracking terminates, generates the movement locus comprising vehicle heading, speed and positional information;
For the vehicle movement information detected according to described movement locus and magnetic test coil, judge module violating the regulations, judges whether vehicle breaks rules and regulations.
6. system according to claim 5, is characterized in that, described magnetic test coil comprises: common magnetic test coil and line ball magnetic test coil;
Described common magnetic test coil is quadrilateral, is arranged on a certain track; For being obtained the travel direction of vehicle by the order of this magnetic test coil according to the same vehicle of detection, and carry out wagon flow quantitative statistics according to statistics by the vehicle of this magnetic test coil;
Described line ball coil is arranged on the graticule between track, and for detecting vehicle, whether line ball travels.
7. the system according to claim 5 or 6, is characterized in that, described judge module violating the regulations comprises:
Gripper path analysis module, carries out track filtering for adopting the Kalman filter smoothing algorithm of based target orientation, size and analyzes described movement locus, obtains the positional information of the travel direction of vehicle, the travel speed of vehicle and vehicle;
Drive in the wrong direction judge module, and whether the angle in the direction detected in the travel direction that judges described vehicle with common magnetic test coil is greater than 90 °, if be all greater than 90 ° in this angle of continuous print N two field picture, then judge that this vehicle is retrograde, wherein, N is positive integer;
Hypervelocity judge module, for the magnitude relationship of the travel speed and max-thresholds that judge described vehicle; If the travelling speed of this vehicle is all greater than max-thresholds in continuous print N two field picture, then judge that this overspeed of vehicle travels;
Parking offense judge module, for the magnitude relationship of the travel speed and minimum threshold that judge described vehicle; If the travelling speed of this vehicle is all less than minimum threshold in continuous print N two field picture, then judge that this vehicle peccancy stops;
Line ball travels judge module, for judging whether the central point of the position tracking box representing this vehicle enters the region of line ball magnetic test coil, if so, then judges that this vehicle line ball travels.
8. the system according to claim 5 or 6, is characterized in that, described system also comprises:
Vehicle summary preserves module, and for preservation vehicle summary info after judgement violating the regulations terminates, this summary info comprises: the colour picture of vehicle; If this vehicle peccancy, then also comprise type of violation, time violating the regulations and place violating the regulations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210584612.0A CN103021186B (en) | 2012-12-28 | 2012-12-28 | Vehicle monitoring method and vehicle monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210584612.0A CN103021186B (en) | 2012-12-28 | 2012-12-28 | Vehicle monitoring method and vehicle monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103021186A CN103021186A (en) | 2013-04-03 |
| CN103021186B true CN103021186B (en) | 2015-03-25 |
Family
ID=47969741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210584612.0A Active CN103021186B (en) | 2012-12-28 | 2012-12-28 | Vehicle monitoring method and vehicle monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103021186B (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134222B (en) * | 2014-07-09 | 2017-02-15 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
| CN105721826B (en) * | 2014-12-02 | 2018-06-12 | 四川浩特通信有限公司 | A kind of intelligence actual combat system |
| CN106558224B (en) * | 2015-09-30 | 2019-08-02 | 徐贵力 | A kind of traffic intelligent monitoring and managing method based on computer vision |
| DE102016210023A1 (en) * | 2016-06-07 | 2017-12-07 | Robert Bosch Gmbh | Method Device and system for wrong driver identification |
| DE102016210032A1 (en) * | 2016-06-07 | 2017-12-07 | Robert Bosch Gmbh | Method Device and system for wrong driver identification |
| CN106412508A (en) * | 2016-09-30 | 2017-02-15 | 北京中星微电子有限公司 | Intelligent monitoring method and system of illegal line press of vehicles |
| CN106651911A (en) * | 2016-11-17 | 2017-05-10 | 天津大学 | Fish behavior acquiring method based on image tracking |
| CN106709476A (en) * | 2017-01-24 | 2017-05-24 | 福州市规划设计研究院 | Intersection OD investigation method |
| CN107657628A (en) * | 2017-09-20 | 2018-02-02 | 中国科学院长春光学精密机械与物理研究所 | A kind of real-time color method for tracking target |
| CN108229407A (en) * | 2018-01-11 | 2018-06-29 | 武汉米人科技有限公司 | A kind of behavioral value method and system in video analysis |
| CN108376407A (en) * | 2018-02-05 | 2018-08-07 | 李刚毅 | Hot-zone object aggregation detection method and system |
| CN108388845A (en) * | 2018-02-05 | 2018-08-10 | 李刚毅 | Method for checking object and system |
| CN108256501A (en) * | 2018-02-05 | 2018-07-06 | 李刚毅 | Abnormal motion object detection systems and its method |
| CN108417050A (en) * | 2018-03-02 | 2018-08-17 | 西南交通大学 | A kind of excess speed event real-time detecting method based on continuous hypervelocity GPS track point |
| CN108693532A (en) * | 2018-03-29 | 2018-10-23 | 浙江大学 | Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars |
| CN108492523A (en) * | 2018-05-21 | 2018-09-04 | 四川斐讯信息技术有限公司 | A kind of safety protecting method and system based on intelligent wearable device |
| JP6958500B2 (en) * | 2018-07-20 | 2021-11-02 | 株式会社デンソー | Moving object detector |
| CN110969864A (en) * | 2018-09-28 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Vehicle speed detection method, vehicle driving event detection method and electronic equipment |
| CN109747642B (en) * | 2019-01-04 | 2020-09-08 | 北京博宇通达科技有限公司 | Vehicle travel control method and apparatus |
| CN110032947B (en) * | 2019-03-22 | 2021-11-19 | 深兰科技（上海）有限公司 | Method and device for monitoring occurrence of event |
| CN110910654B (en) * | 2019-12-03 | 2021-07-27 | 上海眼控科技股份有限公司 | Illegal information processing method and device, electronic equipment and readable storage medium |
| CN111047874B (en) * | 2019-12-19 | 2020-12-29 | 安徽寒武纪信息科技有限公司 | Intelligent traffic violation management method and related product |
| CN113257033B (en) * | 2021-07-01 | 2021-09-24 | 成都宜泊信息科技有限公司 | Parking lot management method and system, storage medium and electronic equipment |
| CN114360257B (en) * | 2022-01-07 | 2023-02-28 | 重庆紫光华山智安科技有限公司 | Vehicle monitoring method and system |
| CN116740126A (en) * | 2023-08-09 | 2023-09-12 | 深圳市深视智能科技有限公司 | Target tracking method, high-speed camera, and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6690292B1 (en) * | 2000-06-06 | 2004-02-10 | Bellsouth Intellectual Property Corporation | Method and system for monitoring vehicular traffic using a wireless communications network |
| CN100466008C (en) * | 2006-04-18 | 2009-03-04 | 北京铱星世纪数字应用开发有限责任公司 | Traffic monitoring method and electronic police system |
| JP2008152736A (en) * | 2006-12-20 | 2008-07-03 | Sony Corp | Monitoring system, monitoring device, and monitoring method |
| CN101556737B (en) * | 2008-04-10 | 2012-11-21 | 上海宝康电子控制工程有限公司 | Left-turn violation detection system at vehicle intersection |
| CN201438334U (en) * | 2009-06-02 | 2010-04-14 | 东莞市大一软件科技有限公司 | Red light running electronic police system |
| CN101572803B (en) * | 2009-06-18 | 2010-11-10 | 中国科学技术大学 | Customizable automatic tracking system based on video monitoring |
| CN101572770B (en) * | 2009-06-18 | 2010-11-10 | 中国科学技术大学 | Method for testing motion available for real-time monitoring and device thereof |
| CN201535951U (en) * | 2009-09-23 | 2010-07-28 | 德瑞视(北京)科技发展有限公司 | Intelligent traffic integrated video monitoring system |
| CN102298844A (en) * | 2011-08-15 | 2011-12-28 | 无锡中星微电子有限公司 | Automatic rule breaking vehicle detection system and method |
-
2012
- 2012-12-28 CN CN201210584612.0A patent/CN103021186B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN103021186A (en) | 2013-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103021186B (en) | Vehicle monitoring method and vehicle monitoring system | |
| CN102810250B (en) | Video based multi-vehicle traffic information detection method | |
| CN104537841B (en) | Unlicensed vehicle violation detection method and detection system thereof | |
| CN105632186B (en) | Detection vehicle is jumped a queue the method and apparatus of behavior | |
| Unzueta et al. | Adaptive multicue background subtraction for robust vehicle counting and classification | |
| CN103971521B (en) | Road traffic anomalous event real-time detection method and device | |
| KR100969995B1 (en) | System of traffic conflict decision for signalized intersections using image processing technique | |
| CN105513349B (en) | Mountainous area highway vehicular events detection method based on double-visual angle study | |
| US10699567B2 (en) | Method of controlling a traffic surveillance system | |
| CN103522970B (en) | Based on vehicle driving safety method of inspection and the system of machine vision | |
| CN110371112A (en) | A kind of intelligent barrier avoiding system and method for automatic driving vehicle | |
| CN102622884B (en) | Vehicle illegal turning behavior detection method based on tracking | |
| CN104835323B (en) | Multi-target public transport passenger flow detection method combining with electronic fence | |
| Chen et al. | Conflict analytics through the vehicle safety space in mixed traffic flows using UAV image sequences | |
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| CN105513342A (en) | Video-tracking-based vehicle queuing length calculating method | |
| CN103235933A (en) | Vehicle abnormal behavior detection method based on Hidden Markov Model | |
| CN112078592B (en) | Method and device for predicting vehicle behavior and/or vehicle track | |
| CN110047276A (en) | The congestion status of barrier vehicle determines method, apparatus and Related product | |
| CN105575125A (en) | Vehicle flow video detection and analysis system | |
| CN106023594A (en) | Parking stall shielding determination method and device and vehicle management system | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
| CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
| Dinh et al. | Development of a tracking-based system for automated traffic data collection for roundabouts | |
| Sanberg et al. | Asteroids: A stixel tracking extrapolation-based relevant obstacle impact detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |