CN102646334A - Method for automatically obtaining evidences of highway traffic incidents and system adopting method - Google Patents
Method for automatically obtaining evidences of highway traffic incidents and system adopting method Download PDFInfo
- Publication number
- CN102646334A CN102646334A CN2012101250382A CN201210125038A CN102646334A CN 102646334 A CN102646334 A CN 102646334A CN 2012101250382 A CN2012101250382 A CN 2012101250382A CN 201210125038 A CN201210125038 A CN 201210125038A CN 102646334 A CN102646334 A CN 102646334A
- Authority
- CN
- China
- Prior art keywords
- similarity
- target
- target area
- current frame
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the field of intelligent traffic, and discloses a method for automatically obtaining evidence of highway traffic incidents and a system adopting the method. Problems of coordinate errors, difficulty in matching, high cost and the like during monitoring and tracking by the aid of a plurality of cameras are avoided, and a background is adjusted to reduce false targets when a dome camera returns to an original location to monitor again. The method includes steps of A, panoramically monitoring at a preset position by the dome camera; B, automatically tracking and obtaining the evidence by the dome camera when an unlawful target is detected; C, placing the dome camera at the preset position again; and D, shooting a current image by the dome camera, detecting the unlawful target, computing similarity of a target region of the current image and a region, corresponding to the target region, in a background image if the target is detected, fusing the target region into the background image and entering the step A if the similarity is larger than a preset threshold, entering the step B if the similarity is not larger than the preset threshold, and entering the step A if the target is not detected.
Description
Technical field
The present invention relates to intelligent transportation field, particularly a kind of highway panoramic video monitoring technique.
Background technology
By in June, 2011, national private car recoverable amount surpasses 7,206 ten thousand, and the high speed total kilometrage is above 7.4 ten thousand kilometers.The thing followed is exactly rolling up of all kinds of violating the regulations, anomalous events.Parking offense, the phenomenon of driving in the wrong direction, often occurring on the highways such as reversing, last high speed of pedestrian, traffic congestion have a strong impact on the high speed normal operation, have brought serious potential safety hazard to highway.Though built highway monitoring system at present; And some is an intelligent monitor system, but present intelligent monitor system mostly uses fixed gunlock, can not carry out intelligent-tracking; Even if use the ball machine can not carry out intelligent-tracking; Can only pass through monitor's manual operation, this type systematic can only be reported to the police to the highway anomalous event, reminds the monitor that this target of this highway section is paid close attention to and handled.But for the parking offense that occurs on the road, reversing violating the regulations, the incident in short-term of grade of driving in the wrong direction violating the regulations, this type systematic can not be followed the tracks of candid photograph to target, therefore can not this type car owner be punished, and does not have warning function, thereby limited to the management role of highway.
And in principal and subordinate's tracking means; Because outdoor ball machine and gunlock are in long-time use; Receive factor affecting such as outdoor weather and ball machine mechanical precision deficiency, produce deviation when the image coordinate meeting of overall view monitoring vision sensor and the collection of tracking vision sensor and initial setting up, the camera coordinates parameter when causing initial configuration lost efficacy; Thereby cause after the overall view monitoring camera detects the incident generation, the tracking ball machine can accurately not trace into target.
Simultaneously, when the tracking ball machine returns the overall view monitoring state by tracking mode, because factor affecting such as ball machine machinery control accuracies; Monitoring scene often is difficult to accurately get back to original monitoring position; May produce deviations several even tens pixels, in more existing tracking ball machine treatment mechanisms, when the ball machine is got back to the overall view monitoring position, can rebuild background; But can bring a very big problem like this: if this moment is when having static target (parking) to be present in the image; This target can be updated in the background and go, and works as vehicle after a period of time and drives away, and will produce false target in the position of former parking and cause wrong report to take place.
Summary of the invention
The object of the present invention is to provide a kind of freeway traffic event automatic evidence-collecting method and system thereof, after avoiding adopting at present a gunlock to do the panorama monitoring finding target, the coordinate of two video cameras being followed the tracks of by a ball machine has error; Coupling is difficult for; Cost is than problems such as height, simultaneously, and when the ball machine is got back to original position when carrying out the panorama monitoring again; Background is adjusted, thus the generation of minimizing false target.
For solving the problems of the technologies described above, embodiment of the present invention discloses a kind of freeway traffic event automatic evidence-collecting method, may further comprise the steps:
A ball machine carries out overall view monitoring in the precalculated position;
If detect target violating the regulations during the B overall view monitoring, then the ball machine is followed the tracks of evidence obtaining automatically to this target violating the regulations;
After C followed the tracks of the evidence obtaining end automatically, the ball machine placed the precalculated position again;
D ball machine is taken current frame image, and according to current frame image detection target violating the regulations,
If the target of detecting is then calculated target area and this target area of the current frame image similarity in the background image corresponding region,, otherwise get into step B if similarity greater than predetermined threshold, then incorporates the target area background image and gets into steps A;
If do not detect target, then get into steps A.
Embodiment of the present invention also discloses a kind of freeway traffic event automatic evidence collecting system, comprising:
The ball machine is used for carrying out overall view monitoring in the precalculated position, to Automatic Target Tracking evidence obtaining violating the regulations, or takes current frame image and detects according to current frame image whether target violating the regulations is arranged;
Preset module is used for the Place machine in the precalculated position;
Computing module is used to calculate target area and this target area of the current frame image similarity in the background image corresponding region;
Judge module is used to judge that whether similarity is greater than predetermined threshold;
Incorporate module, be used for the target area is incorporated background image.
Embodiment of the present invention compared with prior art, the key distinction and effect thereof are:
Use a ball machine to carry out overall view monitoring evidence obtaining violating the regulations, after can avoiding adopting at present a gunlock to do the panorama monitoring finding target, the coordinate of two video cameras being followed the tracks of by a ball machine has error, and coupling is difficult for, and cost is than problems such as height.
Get back to original position when the ball machine and carry out panorama when monitoring again, background is adjusted, thereby reduce the generation of false target.
Further, through edge orientation histogram similarity and grey level histogram similarity weighted mean are obtained current frame image target area and the similarity of this target area in the corresponding zone of background image, further increased the accuracy of target detection violating the regulations.
Further; Edge orientation histogram similarity and grey level histogram similarity weighted mean are obtained current frame image target area and the similarity of this target area in the corresponding zone of background image; The edge orientation histogram similarity weight more shared than grey level histogram similarity is big, has further increased target detection result's violating the regulations accuracy.
Description of drawings
Fig. 1 is the schematic flow sheet of a kind of freeway traffic event automatic evidence-collecting method in the first embodiment of the invention;
Fig. 2 is the schematic flow sheet of a kind of freeway traffic event automatic evidence-collecting method in the second embodiment of the invention;
Fig. 3 is the Video processing analysis process synoptic diagram of a kind of freeway traffic event automatic evidence-collecting method in the second embodiment of the invention;
Fig. 4 is that the coordinate of a kind of freeway traffic event automatic evidence-collecting method in second embodiment is selected synoptic diagram;
Fig. 5 is the trace flow synoptic diagram of a kind of freeway traffic event automatic evidence-collecting method in second embodiment;
Fig. 6 is the structural representation of a kind of freeway traffic event automatic evidence collecting system in the third embodiment of the invention;
Fig. 7 is the structural representation of a kind of freeway traffic event automatic evidence collecting system in the four embodiment of the invention;
Fig. 8 is the structural representation of a kind of freeway traffic event automatic evidence collecting system in the four embodiment of the invention.
Embodiment
In following narration, many ins and outs have been proposed in order to make the reader understand the application better.But, persons of ordinary skill in the art may appreciate that even without these ins and outs with based on the many variations and the modification of following each embodiment, also can realize each claim of the application technical scheme required for protection.
For making the object of the invention, technical scheme and advantage clearer, will combine accompanying drawing that embodiment of the present invention is done to describe in detail further below.
First embodiment of the invention relates to a kind of freeway traffic event automatic evidence-collecting method.Fig. 1 is the schematic flow sheet of this freeway traffic event automatic evidence-collecting method.This freeway traffic event automatic evidence-collecting method may further comprise the steps:
A ball machine carries out overall view monitoring in the precalculated position.
If detect target violating the regulations during the B overall view monitoring, then the ball machine is followed the tracks of evidence obtaining automatically to this target violating the regulations.
After C followed the tracks of the evidence obtaining end automatically, the ball machine placed the precalculated position again.
D ball machine is taken current frame image, and according to current frame image detection target violating the regulations,
If the target of detecting is then calculated target area and this target area of the current frame image similarity in the background image corresponding region,, otherwise get into step B if similarity greater than predetermined threshold, then incorporates the target area background image and gets into steps A.
If do not detect target, then get into steps A.
Use a ball machine to carry out overall view monitoring evidence obtaining violating the regulations, after can avoiding adopting at present a gunlock to do the panorama monitoring finding target, the coordinate of two video cameras being followed the tracks of by a ball machine has error, and coupling is difficult for, and cost is than problems such as height.
Get back to original position when the ball machine and carry out panorama when monitoring again, background is adjusted, thereby reduce the generation of false target.
In addition, be appreciated that in the present invention that the ball machine also can be one and have overall view monitoring and module or the unit of following the tracks of the evidence obtaining function.
As a preferred embodiment of the present invention, as shown in Figure 1, this freeway traffic event automatic evidence-collecting method may further comprise the steps:
In step 101, whether the ball machine carries out overall view monitoring in the precalculated position have target violating the regulations to occur.
If have, then get into step 102; Otherwise, return step 101, whether the ball machine continues overall view monitoring in the precalculated position have target violating the regulations to occur.
In step 102, if detect target violating the regulations during overall view monitoring, then the ball machine is followed the tracks of evidence obtaining automatically to this target violating the regulations.
After this get into step 103, the ball machine places the precalculated position after following the tracks of the evidence obtaining end automatically again.
After this get into step 104, the ball machine is taken current frame image.
After this get into step 105, whether the ball machine has target violating the regulations according to the current frame image detection.
If have, then get into step 106; Otherwise, return step 101, whether the ball machine continues overall view monitoring in the precalculated position have target violating the regulations to occur.
In step 106,, then calculate target area and this target area of current frame image similarity in the background image corresponding region if detect target violating the regulations.
After this get into step 107, judge that whether similarity is greater than predetermined threshold.
If then get into step 108; Otherwise return step 102, the ball machine is followed the tracks of evidence obtaining automatically to this target violating the regulations.
In step 108, if similarity greater than predetermined threshold, then incorporates background image with the target area, and return step 101, whether the ball machine continues overall view monitoring in the precalculated position have target violating the regulations to occur.
Second embodiment of the invention relates to a kind of freeway traffic event automatic evidence-collecting method.Fig. 2 is the schematic flow sheet of this freeway traffic event automatic evidence-collecting method.
Second embodiment improves on the basis of first embodiment; Main improvements are: through edge orientation histogram similarity and grey level histogram similarity weighted mean are obtained current frame image target area and the similarity of this target area in the corresponding zone of background image, further increased the accuracy of target detection violating the regulations.Edge orientation histogram similarity and grey level histogram similarity weighted mean are obtained current frame image target area and the similarity of this target area in the corresponding zone of background image; The edge orientation histogram similarity weight more shared than grey level histogram similarity is big, has further increased target detection result's violating the regulations accuracy.Specifically:
As shown in Figure 2, aforementioned calculation current frame image target area and the step 106 of this target area in the similarity in the corresponding zone of background image also comprise following substep:
In step 201, calculate current frame image target area gradient texture and this target area gradient texture respectively in the background image corresponding region.
After this get into step 202, obtain said object edge image separately.
After this get into step 203, add up the direction histogram of object edge image separately.
After this get into step 204, statistics and the histogrammic edge orientation histogram similarity of calculated direction.
After this get into step 205, calculate current frame image target area and the grey level histogram similarity of this target area in the corresponding zone of background image.
After this get into step 206, to edge orientation histogram similarity and grey level histogram similarity weighted mean, as current frame image target area and the similarity of this target area in the corresponding zone of background image, after this process ends.
Above-mentioned steps 201 to step 204 edge calculation direction histogram similarity process and step 205 are calculated grey level histogram similarity process can the exchange order, promptly calculates grey level histogram similarity edge calculation direction histogram similarity more earlier.
In addition; Be appreciated that in some other embodiments of the present invention, carry out current frame image target area and this target area when the weighted calculation of the similarity in the corresponding zone of background image; Be not limited to weighted calculation to structural similarity and texture similarity; Also comprise weighted calculation, belong to known technology, do not explain here because the color similarity degree calculates to the color similarity degree.
In some other embodiments of the present invention; Current frame image target area and this target area the similarity in the corresponding zone of background image also can the reference texture similarity, in the color similarity degree, grey level histogram similarity one, perhaps also can the reference texture similarity, in the color similarity degree, grey level histogram similarity several carry out the resulting similarity of weighted mean.
The edge orientation histogram similarity weight more shared than grey level histogram similarity is big.
If detect target violating the regulations during overall view monitoring, also target violating the regulations is carried out interlink warning.
Calculate current frame image target area and the step of this target area, calculate based on identical image coordinate system in the similarity in the corresponding zone of background image.
As a preferred embodiment of the present invention, at highway ring road mouth, the high speed ball-shaped camera is installed in intercommunication gateway and each highway section, makes the effective field of view scope of the vision sensor of video camera cover whole crossing, non-blind area, comprehensive detection vehicular traffic.
The target that gets into guarded region is detected detection module in the ball machine automatically and panorama is followed the tracks of, and grasps the movement locus of each target, thereby detect the various act of violating regulations information of each target at guarded region, and concrete processing procedure is as shown in Figure 3:
Day mode is at first carried out background extracting to input picture, and the method for background extracting is existing method, and like the mixed Gauss model background extracting, the comparison through present image and background image after the extraction background can obtain moving target in the present image.Night mode is through detecting definite moving target to car light.
In step 301, the ball machine is gathered or input picture.
After this get into step 302, detection module extracts moving target from the image of input.
After this get into step 303; Automatically following the tracks of the evidence obtaining module collects evidence to motion target tracking; After detecting moving target, use Kalman Kalman, methods such as average drifting Mean Shift or particle filter Particle Filter are followed the tracks of moving target, obtain the movement locus of target.
After this get into step 304, the variation of the movement locus of evaluating objects when target trajectory and actual track is in the opposite direction or during greater than set angle, thinks that target drives in the wrong direction; Static and when surpassing the setting-up time restriction when target trajectory, judge that target is for stopping.
After detection module detects act of violating regulations or incident violating the regulations or target violating the regulations; The initial coordinate of following the tracks of at first definite image; Can follow the tracks of the selection of initial coordinate and finally see and please substantial connection be arranged car plate, the selection of following the tracks of initial point be relevant with the angle of type, target and the camera of target.
Can be known that by projection theory under the constant situation of camera heights, target and camera distance are near more, angle is big more, and the car plate of target is just the closer to the below, target area; Target longer (like semitrailer, motor bus), car plate position in image also below target.Therefore selecting initial type and the camera antenna height that coordinate time needs the analysis-by-synthesis target of following the tracks of, camera sets up distance, confirms to follow the tracks of the coordinate of initial point in image.
In the distance (pixel) of promptly following the tracks of initial point distance objective lower limb and the image ratio P of the length (pixel) of target be proportional to camera and target apart from d, be inversely proportional to camera antenna height h and target length l.When the target infinite distance, the position of P is the ratio P0 of car plate position apart from floor level Ph and height of car Vh in theory, like figure, and P0=Ph/Vh, P0=1/4 usually.As shown in Figure 4.
H is the height of camera, and d1 is that headstock is according to the vertical actual range of camera in the image, and d2 is that the tailstock is apart from the vertical actual range of camera in the image, and the formula that calculates P is following:
α＝arctan(d1/h)；
β＝arctan(d2/h)；
P＝P0＊Cos(β-α)；
Wherein, α is the vertical angle of headstock and camera lens, and β is the vertical angle of the tailstock and camera lens.
Detection module will initially be followed the tracks of coordinate and pass to after motion tracking quick or module, quick control PTZ (wherein, P: horizontally rotate angle; T: vertical rotation angle; Z (zoom) focal length) target is amplified, and tracking target is carried out motion compensation, mate clarification of objective after the motion compensation, upgrade and follow the tracks of coordinate.When car plate is high-visible, stop multiplying power and amplify, and the P (Pan) and the T (Tilt) of continuation control marble forming machine follow the tracks of target.
In this overall view monitoring tracking violating the regulations evidence-obtaining system; The video image that tracking module and detection module use same vision sensor to gather, so tracking module and detection module be under same image coordinate, tracking module is after having obtained the initial tracking coordinate that detection module provides; Need not carry out any coordinate conversion; Can directly start trace routine, the characteristic of evaluating objects in image drives the fire ball machine and becomes doubly; Actions such as zoom are followed the tracks of, and in the process of following the tracks of, revise and follow the tracks of coordinate.
After detecting act of violating regulations, the ball machine is recorded a video to incident violating the regulations, punishes suitable as the law enforcement foundation to the car owner afterwards.
As a preferred embodiment of the present invention, concrete trace flow is as shown in Figure 5:
In step 501, initialization ball machine trace point.
After this get into step 502, automatically track target.
After this get into step 503, the target signature coupling.
After this get into step 504, upgrade and follow the tracks of coordinate, after this process ends.
Each method embodiment of the present invention all can be realized with modes such as software, hardware, firmwares.No matter the present invention be with software, hardware, or the firmware mode realize; Instruction code can be stored in the storer of computer-accessible of any kind (for example permanent or revisable; Volatibility or non-volatile; Solid-state or non-solid-state, fixing perhaps removable medium or the like).Equally; Storer can for example be programmable logic array (Prog rammable Array Logic; Abbreviation " PAL "), RAS (Random Access Memory; Abbreviation " RAM "), programmable read only memory (Programmable Read Only Memory is called for short " PROM "), ROM (read-only memory) (Read-Only Memory is called for short " ROM "), Electrically Erasable Read Only Memory (Electrically Erasable Programmable ROM; Abbreviation " EEPROM "), disk, CD, digital versatile disc (Digital Versatile Disc is called for short " DVD ") or the like.
Third embodiment of the invention relates to a kind of freeway traffic event automatic evidence collecting system.Fig. 6 is the structural representation of this freeway traffic event automatic evidence collecting system.This freeway traffic event automatic evidence collecting system comprises:
The ball machine is used for carrying out overall view monitoring in the precalculated position, to Automatic Target Tracking evidence obtaining violating the regulations, or takes current frame image and detects according to current frame image whether target violating the regulations is arranged.
Preset module is used for the Place machine in the precalculated position.
Computing module is used to calculate target area and this target area of the current frame image similarity in the background image corresponding region.
Judge module is used to judge that whether similarity is greater than predetermined threshold.
Incorporate module, be used for the target area is incorporated background image.
First embodiment is and the corresponding method embodiment of this embodiment, this embodiment can with the enforcement of working in coordination of first embodiment.The correlation technique details of mentioning in first embodiment is still effective in this embodiment, in order to reduce repetition, repeats no more here.Correspondingly, the correlation technique details of mentioning in this embodiment also can be applicable in first embodiment.
Four embodiment of the invention relates to a kind of freeway traffic event automatic evidence collecting system.Fig. 7 and Fig. 8 are the structural representations of this freeway traffic event automatic evidence collecting system.
The 4th embodiment improves on the basis of the 3rd embodiment, and main improvements are: the edge orientation histogram similarity weight more shared than grey level histogram similarity is big, has further increased target detection result's violating the regulations accuracy.As shown in Figure 7, specifically:
Computing module also comprises following subelement:
The texture computation subunit is used for calculating respectively current frame image target area gradient texture and this target area gradient texture in the background image corresponding region.
The edge obtains subelement, is used to obtain the image of object edge separately that the texture computation subunit is calculated.
The statistics with histogram subelement is used to add up the direction histogram that the edge obtains the image of object edge separately that subelement obtains.
The first similarity subelement is used to add up the also edge orientation histogram similarity of the compute histograms statistics direction histogram that subelement counted.
The second similarity subelement is used to calculate current frame image target area and the grey level histogram similarity of this target area in the corresponding zone of background image.
The weighted mean subelement; The grey level histogram similarity weighted mean that the edge orientation histogram similarity that is used for the first similarity subunit computes is gone out and the second similarity subunit computes go out is as current frame image target area and the similarity of this target area in the corresponding zone of background image.
In addition; Be appreciated that in some other embodiments of the present invention, carry out current frame image target area and this target area when the weighted calculation of the similarity in the corresponding zone of background image; Be not limited to weighted calculation to structural similarity and texture similarity; Also comprise weighted calculation, belong to known technology, do not explain here because the color similarity degree calculates to the color similarity degree.
In some other embodiments of the present invention; Current frame image target area and this target area the similarity in the corresponding zone of background image also can the reference texture similarity, in the color similarity degree, grey level histogram similarity one, perhaps also can the reference texture similarity, in the color similarity degree, grey level histogram similarity several carry out the resulting similarity of weighted mean.
The edge orientation histogram similarity weight more shared than grey level histogram similarity is big.
As shown in Figure 8, this freeway traffic event automatic evidence collecting system also comprises:
The interlink warning module is carried out interlink warning if detect target violating the regulations when being used for ball machine overall view monitoring to target violating the regulations.
Computing module calculates target area and this target area of the current frame image similarity in the background image corresponding region based on identical image coordinate system.
Second embodiment is and the corresponding method embodiment of this embodiment, this embodiment can with the enforcement of working in coordination of second embodiment.The correlation technique details of mentioning in second embodiment is still effective in this embodiment, in order to reduce repetition, repeats no more here.Correspondingly, the correlation technique details of mentioning in this embodiment also can be applicable in second embodiment.
Need to prove; Each unit of mentioning in each equipment embodiment of the present invention all is logical block or module; Physically; Logical block or module can be a physical location or module, also can be the parts of a physical location or module, can also realize with the combination of a plurality of physical locations or module; The physics realization mode of these logical blocks or module itself is not most important, and the combination of the function that these logical block or modules realized is the key that just solves technical matters proposed by the invention.In addition; For outstanding innovation part of the present invention; Above-mentioned each the equipment embodiment of the present invention will not too close unit or module not introduced with solving technical matters relation proposed by the invention, and this does not show that there be not other unit or module in the said equipment embodiment.
Though through reference some preferred implementation of the present invention; The present invention is illustrated and describes; But those of ordinary skill in the art should be understood that and can do various changes to it in form with on the details, and without departing from the spirit and scope of the present invention.
Claims (10)
1. a freeway traffic event automatic evidence-collecting method is characterized in that, may further comprise the steps:
A ball machine carries out overall view monitoring in the precalculated position;
If detect target violating the regulations during the B overall view monitoring, then said ball machine is followed the tracks of evidence obtaining automatically to this target violating the regulations;
After C followed the tracks of the evidence obtaining end automatically, said ball machine placed said precalculated position again;
The said ball machine of D is taken current frame image, and according to current frame image detection target violating the regulations,
If the target of detecting is then calculated target area and this target area of the current frame image similarity in the background image corresponding region,, otherwise get into step B if said similarity greater than predetermined threshold, then incorporates the target area background image and gets into steps A;
If do not detect target, then get into steps A.
2. freeway traffic event automatic evidence-collecting method according to claim 1 is characterized in that, said calculating current frame image target area and the step of this target area in the similarity in the corresponding zone of background image comprise following substep:
Calculate current frame image target area gradient texture and this target area gradient texture respectively, and obtain said object edge image separately in the background image corresponding region;
Add up the direction histogram of object edge image separately;
Statistics is also calculated the edge orientation histogram similarity of direction histogram separately;
Calculate current frame image target area and the grey level histogram similarity of this target area in the corresponding zone of background image;
To said edge orientation histogram similarity and grey level histogram similarity weighted mean, as current frame image target area and the similarity of this target area in the corresponding zone of background image.
3. freeway traffic event automatic evidence-collecting method according to claim 2 is characterized in that, the said edge orientation histogram similarity weight more shared than grey level histogram similarity is big.
4. freeway traffic event automatic evidence-collecting method according to claim 1 is characterized in that, if detect target violating the regulations during overall view monitoring, also said target violating the regulations is carried out interlink warning.
5. according to each described freeway traffic event automatic evidence-collecting method in the claim 1 to 4; It is characterized in that; Said calculating current frame image target area and the step of this target area in the similarity in the corresponding zone of background image are calculated based on identical image coordinate system.
6. a freeway traffic event automatic evidence collecting system is characterized in that, comprising:
The ball machine is used for carrying out overall view monitoring in the precalculated position, to Automatic Target Tracking evidence obtaining violating the regulations, or takes current frame image and detects according to current frame image whether target violating the regulations is arranged;
Preset module is used to put said ball machine in said precalculated position;
Computing module is used to calculate target area and this target area of the said current frame image similarity in the background image corresponding region;
Judge module is used to judge that whether said similarity is greater than predetermined threshold;
Incorporate module, be used for said target area is incorporated background image.
7. freeway traffic event automatic evidence collecting system according to claim 6 is characterized in that, said computing module also comprises following subelement:
The texture computation subunit is used for calculating respectively current frame image target area gradient texture and this target area gradient texture in the background image corresponding region;
The edge obtains subelement, is used to obtain the image of object edge separately that said texture computation subunit is calculated;
The statistics with histogram subelement is used to add up the direction histogram that said edge obtains the image of object edge separately that subelement obtains;
The first similarity subelement is used to add up and calculate the edge orientation histogram similarity of the direction histogram that said statistics with histogram subelement counted;
The second similarity subelement is used to calculate current frame image target area and the grey level histogram similarity of this target area in the corresponding zone of background image;
The weighted mean subelement; The grey level histogram similarity weighted mean that edge orientation histogram similarity that is used for the said first similarity subunit computes is gone out and the said second similarity subunit computes go out is as current frame image target area and the similarity of this target area in the corresponding zone of background image.
8. freeway traffic event automatic evidence collecting system according to claim 7 is characterized in that, the said edge orientation histogram similarity weight more shared than grey level histogram similarity is big.
9. freeway traffic event automatic evidence collecting system according to claim 6 is characterized in that, also comprises:
The interlink warning module is carried out interlink warning if detect target violating the regulations when being used for said ball machine overall view monitoring to said target violating the regulations.
10. according to each described freeway traffic event automatic evidence collecting system in the claim 6 to 9; It is characterized in that; Said computing module calculates target area and this target area of the current frame image similarity in the background image corresponding region based on identical image coordinate system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210125038.2A CN102646334B (en) | 2012-04-25 | 2012-04-25 | Method for automatically obtaining evidences of highway traffic incidents and system adopting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210125038.2A CN102646334B (en) | 2012-04-25 | 2012-04-25 | Method for automatically obtaining evidences of highway traffic incidents and system adopting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102646334A true CN102646334A (en) | 2012-08-22 |
| CN102646334B CN102646334B (en) | 2014-04-02 |
Family
ID=46659145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210125038.2A Active CN102646334B (en) | 2012-04-25 | 2012-04-25 | Method for automatically obtaining evidences of highway traffic incidents and system adopting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102646334B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198665A (en) * | 2013-03-18 | 2013-07-10 | 陕西科技大学 | Device for detecting back-up action and detecting method thereof |
| WO2014044161A1 (en) * | 2012-09-18 | 2014-03-27 | 杭州海康威视数字技术股份有限公司 | Target tracking method and system for intelligent tracking high speed dome camera |
| CN105679017A (en) * | 2016-01-27 | 2016-06-15 | 福建工程学院 | Slight traffic accident assistant evidence collection method and system |
| CN103679688B (en) * | 2012-09-18 | 2016-11-09 | 浙江大华技术股份有限公司 | A kind of method and device extracting target image |
| CN106878669A (en) * | 2015-12-10 | 2017-06-20 | 财团法人工业技术研究院 | Image identification method |
| CN109935074A (en) * | 2017-12-16 | 2019-06-25 | 北京嘀嘀无限科技发展有限公司 | A kind of system, method, apparatus and storage medium for judging user and whether riding safely |
| CN110321806A (en) * | 2019-06-12 | 2019-10-11 | 浙江大华技术股份有限公司 | Object detection method, image processing equipment and the equipment with store function |
| CN112307830A (en) * | 2019-07-31 | 2021-02-02 | 北京博雅慧视智能技术研究院有限公司 | Digital retina mass target retrieval and deployment control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999028759A1 (en) * | 1997-12-03 | 1999-06-10 | Raytheon Company | Method and system for imaging target detection |
| KR100837435B1 (en) * | 2006-10-25 | 2008-06-12 | 삼성전자주식회사 | Photographing apparatus for controlling object tracking and method thereof |
| CN101610420A (en) * | 2008-06-20 | 2009-12-23 | 睿致科技股份有限公司 | The method of Automatic white balance |
| US7869090B2 (en) * | 2008-12-17 | 2011-01-11 | Xerox Corporation | Variable data digital pantographs |
| CN102254395A (en) * | 2011-06-07 | 2011-11-23 | 北京引创科技有限责任公司 | Article theft detecting and alarming device and method based on intelligent video analysis |
-
2012
- 2012-04-25 CN CN201210125038.2A patent/CN102646334B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999028759A1 (en) * | 1997-12-03 | 1999-06-10 | Raytheon Company | Method and system for imaging target detection |
| KR100837435B1 (en) * | 2006-10-25 | 2008-06-12 | 삼성전자주식회사 | Photographing apparatus for controlling object tracking and method thereof |
| CN101610420A (en) * | 2008-06-20 | 2009-12-23 | 睿致科技股份有限公司 | The method of Automatic white balance |
| US7869090B2 (en) * | 2008-12-17 | 2011-01-11 | Xerox Corporation | Variable data digital pantographs |
| CN102254395A (en) * | 2011-06-07 | 2011-11-23 | 北京引创科技有限责任公司 | Article theft detecting and alarming device and method based on intelligent video analysis |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014044161A1 (en) * | 2012-09-18 | 2014-03-27 | 杭州海康威视数字技术股份有限公司 | Target tracking method and system for intelligent tracking high speed dome camera |
| CN103679688B (en) * | 2012-09-18 | 2016-11-09 | 浙江大华技术股份有限公司 | A kind of method and device extracting target image |
| US9955074B2 (en) | 2012-09-18 | 2018-04-24 | Hangzhou Hikvision Digital Technology Co., Ltd. | Target tracking method and system for intelligent tracking high speed dome camera |
| CN103198665A (en) * | 2013-03-18 | 2013-07-10 | 陕西科技大学 | Device for detecting back-up action and detecting method thereof |
| CN106878669A (en) * | 2015-12-10 | 2017-06-20 | 财团法人工业技术研究院 | Image identification method |
| CN106878669B (en) * | 2015-12-10 | 2019-12-03 | 财团法人工业技术研究院 | Image identification method |
| CN105679017A (en) * | 2016-01-27 | 2016-06-15 | 福建工程学院 | Slight traffic accident assistant evidence collection method and system |
| WO2017128875A1 (en) * | 2016-01-27 | 2017-08-03 | 福建工程学院 | Minor traffic accident auxiliary forensics method and system |
| CN109935074A (en) * | 2017-12-16 | 2019-06-25 | 北京嘀嘀无限科技发展有限公司 | A kind of system, method, apparatus and storage medium for judging user and whether riding safely |
| CN110321806A (en) * | 2019-06-12 | 2019-10-11 | 浙江大华技术股份有限公司 | Object detection method, image processing equipment and the equipment with store function |
| CN112307830A (en) * | 2019-07-31 | 2021-02-02 | 北京博雅慧视智能技术研究院有限公司 | Digital retina mass target retrieval and deployment control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102646334B (en) | 2014-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102646334B (en) | Method for automatically obtaining evidences of highway traffic incidents and system adopting method | |
| KR101698026B1 (en) | Police enfoforcement system of illegal stopping and parking vehicle by moving vehicle tracking | |
| US11238730B2 (en) | System and method for detecting and recording traffic law violation events | |
| CN107134147B (en) | Method, device and system for managing parking spaces under pole based on camera and sensor | |
| CN105894817B (en) | The evidence collecting method and its device of vehicle violation parking | |
| CN103927878B (en) | A kind of automatic shooting device for parking offense and automatically grasp shoot method | |
| CA2747337C (en) | Multiple object speed tracking system | |
| CN205194072U (en) | Linkage snapshot system and integration camera are detected to violating regulations parking | |
| CN106571039A (en) | Automatic snapshot system for highway traffic offence | |
| CN103473926A (en) | Gun-ball linkage road traffic parameter collection and rule breaking snapshooting system | |
| KR101032495B1 (en) | Multi-function detecting system of illegally parked vehicles using digital ptz technique and method of detecting thereof | |
| CN102592450A (en) | System and method for snapshotting behavior of motor vehicles not giving precedence to pedestrians on zebra stripes | |
| CN105336170A (en) | Traffic peccancy monitoring method and device | |
| CN102521979A (en) | High-definition camera-based method and system for pavement event detection | |
| CN111914592B (en) | Multi-camera combined evidence obtaining method, device and system | |
| CN107316463A (en) | A kind of method and apparatus of vehicle monitoring | |
| RU2587662C1 (en) | Automated system for detecting road traffic violation at crossroad, railway crossing or pedestrian crossing | |
| CN209447332U (en) | A kind of Roadside Parking management system based on longitudinal multi-view image | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| KR101033237B1 (en) | Multi-function detecting system for vehicles and security using 360 deg. wide image and method of detecting thereof | |
| CN101533558A (en) | Fixed intersection monitoring system | |
| CN112601049B (en) | Video monitoring method and device, computer equipment and storage medium | |
| CN111951598A (en) | Vehicle tracking monitoring method, device and system | |
| CN111739305B (en) | Multi-type camera-based illegal parking management method and system | |
| CN202563684U (en) | System for shooting non-comity actions of automotive vehicles toward pedestrians at zebra crossing |
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 |