CN102663368A - Moving target regional integration and optimization method on basis of Gestalt visual principle - Google Patents
Moving target regional integration and optimization method on basis of Gestalt visual principle Download PDFInfo
- Publication number
- CN102663368A CN102663368A CN2012101110160A CN201210111016A CN102663368A CN 102663368 A CN102663368 A CN 102663368A CN 2012101110160 A CN2012101110160 A CN 2012101110160A CN 201210111016 A CN201210111016 A CN 201210111016A CN 102663368 A CN102663368 A CN 102663368A
- Authority
- CN
- China
- Prior art keywords
- target
- gestalt
- targets
- integrated optimization
- ratio
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 230000010354 integration Effects 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000000007 visual effect Effects 0.000 title claims abstract description 24
- 230000015572 biosynthetic process Effects 0.000 claims description 10
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a moving target regional integration and optimization method on the basis of a Gestalt visual principle, which comprises a regularly abstracting stage and an integrating and optimizing stage. In the moving target regional integration and optimization method on the basis of the Gestalt visual principle, which is disclosed by the invention, according to two principles of the Gestalt visual principle, rules for integrating two target vehicle regions are abstracted; and when two targets meet all integration conditions, the two targets are integrated into one target to return the integrated features of the two targets.
Description
Technical field
The present invention relates to a kind of moving target integrated optimization method, relate in particular to a kind of motion target area integrated optimization method based on the Gestalt visual theory.
Background technology
Intelligent traffic management systems (ITS:Intelligent Traffic System) is the focus that present countries in the world traffic and transport field is is competitively researched and developed.Its main target is to obtain road information and vehicle behavioural information, comprises vehicle flowrate, the speed of a motor vehicle, roadway occupancy, traffic hazard detection etc.What in image, carry out the regional detection of moving vehicle is one of important technology of intelligent transportation system, is the core methed of realizing the ITS target, also is that ITS realizes robotization, intellectuality and real-time key in application.
In conventional target detection method based on background subtraction, because interference such as illumination and body colors, the phenomenon of " over-segmentation " usually can appear, show as and on the result who detects, occur a vehicle is divided into several disconnected zones.Yet; Use connected component analysis to distinguish the method for different vehicle target; Finally can these disconnected zones (be belonged to a moving vehicle originally; Owing to " over-segmentation " is divided into several sections) be designated the different vehicles target, had a strong impact on the correctness that detects, it is very unfavorable that follow-up tracking to vehicle target is reached more senior video analysis behavior.Therefore it is very important that the problem that adopts certain method to solve " over-segmentation " seems.
Summary of the invention
The object of the invention is to provide a kind of motion target area integrated optimization method based on the Gestalt visual theory, to improve the correctness of moving object detection.
For reaching above-mentioned purpose, the motion target area integrated optimization method based on the Gestalt visual theory of the present invention comprises the steps:
1) the rule level of abstration straction:
A, the proximity principle that the Gestalt visual theory is followed and closed principle are abstract integrates required satisfied integrated optimization rule for target; Promptly selected characteristic parameter; And be the characteristic parameter setting threshold, when characteristic parameter and threshold value satisfy when imposing a condition, integrate two targets;
B, end.
2) the integrated optimization stage
All target vehicle zones that a, the extraction of collection target obtain are to waiting to integrate among the formation Q;
Two target t among b, the calculating Q
1And t
2The integration characteristics parameter, if all integration parameters of this two targets can both satisfy the integrated optimization rule, then two targets are merged into a target t
New, in Q, delete t
1And t
2And adding t
NewOtherwise, continue to seek can and t
1The target of integrating;
C, circulation execution in step 2)-b, all can not satisfy the integration condition up to the integration characteristics parameter of any two targets;
D, end.
Further, among the present invention, the characteristic ginseng value described in step 1)-a comprises width and rise, wide ratio of similitude and high ratio of similitude, area coverage coefficient, with two target t
1And t
2The rise threshold value setting be the picture height 1/10th with the width threshold value setting be 1/10th of picture width, high ratio of similitude Ratio
HWith wide ratio of similitude Ratio
WAll be set to 0.7, the area coverage coefficient is set to 0.5, when width and rise respectively less than rise threshold values and width threshold values, high ratio of similitude Ratio
HWith wide ratio of similitude Ratio
WAll greater than 0.7 and the area coverage coefficient greater than 0.5 o'clock, integrate two target t
1And t
2
Among the present invention, step 2)-a among the Q each target vehicle zone comprise the boundary rectangle of vehicle region, the information such as particular location in image.
Further, among the present invention, step 2)-detailed process of b is following:
To two target t among the Q
1And t
2, calculate the integration characteristics parameter value of these two targets respectively, comprise width and rise (is unit with the pixel), wide ratio of similitude and high ratio of similitude, area coverage coefficient.
Judge t
1And t
2All integration characteristics parameters whether all meet the integration condition.If, then with t
1And t
2Merge into t
New, with t
1And t
2In formation Q, delete, add t simultaneously
NewBe the fresh target zone; Otherwise, cycle criterion t
1With whether can integrating of remaining target;
Further, among the present invention, step 2)-c in when finding that all targets all can not satisfy the integration condition in the current queue, then finish scan queue; Return integrated results; Finish to integrate.
Beneficial effect of the present invention is following: the motion target area integrated optimization method based on the Gestalt visual theory of the present invention; Proximity principle and closed principle according to the Gestalt visual theory; Take out rule with two target vehicle Regional Integration; When two targets satisfy all integration conditions, two targets are integrated into a target, return this this overall permanence that has of two targets itself.
Description of drawings
Fig. 1 is the Intelligent traffic management systems workflow diagram.
Fig. 2 is the process flow diagram of the motion target area integrated optimization method based on the Gestalt visual theory of the present invention.
Fig. 3 is the detail flowchart based on the motion target area integrated optimization method of Gestalt visual theory.
Embodiment
In order more to understand technology contents of the present invention, special act specific embodiment also cooperates appended graphic explanation following.
As shown in Figure 1, Intelligent traffic management systems is obtained vedio data through video image acquisition equipment, and through the image pre-service, moving vehicle detects, target is integrated, and carries out moving vehicle then and follows the tracks of and follow-up advanced processes.The moving target integrated optimization is great to back total system influence.
Vehicle detection is the core procedure of Intelligent traffic management systems; The appearance of " over-segmentation " phenomenon is difficult to avoid when carrying out vehicle detection through the method for background subtraction; Thinking of the present invention is exactly through back by its whole phenomenon of the vehicle of over-segmentation recovery to detecting, thereby improves the performance of whole Intelligent traffic management systems.The vehicle target integration process is the process flow diagram of the motion target area integrated optimization method based on the Gestalt visual theory of the present invention, and is as shown in Figure 2.
In the rule level of abstration straction (step 1); Two cardinal principles with the Gestalt visual theory; Being that proximity principle and closed principle are abstract integrates required satisfied integrated optimization rule for target, promptly selects characteristic parameter, and is these characteristic parameter setting thresholds; In order to integrating the foundation of two targets, the integration characteristics parameter comprises width and rise, wide ratio of similitude and high ratio of similitude, area coverage coefficient; In the present embodiment, with two target t
1And t
2The rise threshold value setting be that 70 pixel sizes (picture height 1/10th) and width threshold value setting are 50 pixel sizes (picture width 1/10th), high ratio of similitude Ratio
HWith wide ratio of similitude Ratio
WAll be set to 0.7, the area coverage coefficient is set to 0.5, when width and rise respectively less than rise threshold values and width threshold values, high ratio of similitude Ratio
HWith wide ratio of similitude Ratio
WAll greater than 0.7 and the area coverage coefficient greater than 0.5 o'clock, integrate two target t
1And t
2
At integrated optimization stage (step 2-4), step 2 is collected the information of all moving vehicles in the current image frame, and these moving vehicle information are kept in the formation;
Fig. 3 is the detail flowchart based on the motion target area integrated optimization method of Gestalt visual theory.
Whether the integration parameters value that step 35 determining step 34 calculates satisfies the integration condition, if then turn to step 36, otherwise turn to 37;
Whether identical step 39 judge continuous two-wheeled scanning result (i.e. i wheel scan result and i-1 wheel contrast, i 1).If the two-wheeled result is different, then continues next round and integrate; Otherwise, turn to 3a;
Step 3a finishes.
Motion target area integrated optimization method based on the Gestalt visual theory of the present invention; Proximity principle and closed principle according to the Gestalt visual theory; Take out rule with two target vehicle Regional Integration; When two targets satisfy all integration conditions, two targets are integrated into a target, return this this overall permanence that has of two targets itself.
Though the present invention discloses as above with preferred embodiment, so it is not in order to limit the present invention.Have common knowledge the knowledgeable in the technical field under the present invention, do not breaking away from the spirit and scope of the present invention, when doing various changes and retouching.Therefore, protection scope of the present invention is as the criterion when looking claims person of defining.
Claims (5)
1. the motion target area integrated optimization method based on the Gestalt visual theory is characterized in that, comprises the steps:
1) the rule level of abstration straction:
A, the proximity principle that the Gestalt visual theory is followed and closed principle are abstract integrates required satisfied integrated optimization rule for target; Promptly selected characteristic parameter; And be the characteristic parameter setting threshold, when characteristic parameter and threshold value satisfy when imposing a condition, integrate two targets;
B, end.
2) the integrated optimization stage
All target vehicle zones that a, the extraction of collection target obtain are to waiting to integrate among the formation Q;
Two target t among b, the calculating Q
1And t
2The integration characteristics parameter, if all integration parameters of this two targets can both satisfy the integrated optimization rule, then two targets are merged into a target t
New, in Q, delete t
1And t
2And adding t
NewOtherwise, continue to seek can and t
1The target of integrating;
C, circulation execution in step 2)-b, all can not satisfy the integration condition up to the integration characteristics parameter of any two targets;
D, end.
2. the motion target area integrated optimization method based on the Gestalt visual theory according to claim 1; It is characterized in that; Wherein the characteristic ginseng value described in step 1)-a comprises width and rise, wide ratio of similitude and high ratio of similitude, area coverage coefficient, with two target t
1And t
2The rise threshold value setting be the picture height 1/10th with the width threshold value setting be 1/10th of picture width, high ratio of similitude Ratio
HWith wide ratio of similitude Ratio
WAll be set to 0.7, the area coverage coefficient is set to 0.5, when width and rise respectively less than rise threshold values and width threshold values, high ratio of similitude Ratio
HWith wide ratio of similitude Ratio
WAll greater than 0.7 and the area coverage coefficient greater than 0.5 o'clock, integrate two target t
1And t
2
3. the motion target area integrated optimization method based on the Gestalt visual theory according to claim 1; It is characterized in that, wherein step 2)-a among the Q each target vehicle zone comprise the boundary rectangle of vehicle region, the information such as particular location in image.
4. the motion target area integrated optimization method based on the Gestalt visual theory according to claim 1 is characterized in that, wherein step 2)-detailed process of b is following:
To two target t among the Q
1And t
2, calculate the integration characteristics parameter of these two targets respectively;
Judge t
1And t
2All integration characteristics parameters whether all meet the integrated optimization rule, if, then with t
1And t
2Merge into t
New, with t
1And t
2In formation Q, delete, add t simultaneously
NewBe the fresh target zone; Otherwise, cycle criterion t
1With whether can integrating of remaining target.
5. based on the described motion target area integrated optimization method of claim 1, it is characterized in that step 2 based on the Gestalt visual theory)-c in when finding that all targets all can not satisfy the integrated optimization rule in the current queue, then finish scan queue; Return integrated results; Finish to integrate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210111016.0A CN102663368B (en) | 2012-04-16 | 2012-04-16 | Moving target regional integration and optimization method on basis of Gestalt visual principle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210111016.0A CN102663368B (en) | 2012-04-16 | 2012-04-16 | Moving target regional integration and optimization method on basis of Gestalt visual principle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102663368A true CN102663368A (en) | 2012-09-12 |
CN102663368B CN102663368B (en) | 2014-09-17 |
Family
ID=46772852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210111016.0A Expired - Fee Related CN102663368B (en) | 2012-04-16 | 2012-04-16 | Moving target regional integration and optimization method on basis of Gestalt visual principle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102663368B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109615874A (en) * | 2018-12-28 | 2019-04-12 | 浙江大学 | A kind of road condition analyzing method based on Gestalt psychology criterion |
CN111461139A (en) * | 2020-03-27 | 2020-07-28 | 武汉工程大学 | Multi-target visual saliency layered detection method in complex scene |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090116728A1 (en) * | 2007-11-07 | 2009-05-07 | Agrawal Amit K | Method and System for Locating and Picking Objects Using Active Illumination |
CN102004922A (en) * | 2010-12-01 | 2011-04-06 | 南京大学 | High-resolution remote sensing image plane extraction method based on skeleton characteristic |
US20110175905A1 (en) * | 2010-01-15 | 2011-07-21 | American Propertunity, LLC. | Infoshape: displaying multidimensional information |
-
2012
- 2012-04-16 CN CN201210111016.0A patent/CN102663368B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090116728A1 (en) * | 2007-11-07 | 2009-05-07 | Agrawal Amit K | Method and System for Locating and Picking Objects Using Active Illumination |
US20110175905A1 (en) * | 2010-01-15 | 2011-07-21 | American Propertunity, LLC. | Infoshape: displaying multidimensional information |
CN102004922A (en) * | 2010-12-01 | 2011-04-06 | 南京大学 | High-resolution remote sensing image plane extraction method based on skeleton characteristic |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109615874A (en) * | 2018-12-28 | 2019-04-12 | 浙江大学 | A kind of road condition analyzing method based on Gestalt psychology criterion |
CN109615874B (en) * | 2018-12-28 | 2021-02-02 | 浙江大学 | Road condition analysis method based on form tower psychological criterion |
CN111461139A (en) * | 2020-03-27 | 2020-07-28 | 武汉工程大学 | Multi-target visual saliency layered detection method in complex scene |
Also Published As
Publication number | Publication date |
---|---|
CN102663368B (en) | 2014-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104537841B (en) | Unlicensed vehicle violation detection method and detection system thereof | |
Lai et al. | Image-based vehicle tracking and classification on the highway | |
CN103077617B (en) | Based on crossing intelligent traffic light supervisory systems and the method for computer vision | |
CN102289948B (en) | Multi-characteristic fusion multi-vehicle video tracking method under highway scene | |
CN102622884B (en) | Vehicle illegal turning behavior detection method based on tracking | |
CN101840507B (en) | Target tracking method based on character feature invariant and graph theory clustering | |
Hoermann et al. | Object detection on dynamic occupancy grid maps using deep learning and automatic label generation | |
CN108320510A (en) | One kind being based on unmanned plane video traffic information statistical method and system | |
CN105632186A (en) | Method and device for detecting vehicle queue jumping behavior | |
CN102496281B (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
CN104599502A (en) | Method for traffic flow statistics based on video monitoring | |
CN105513349A (en) | Double-perspective learning-based mountainous area highway vehicle event detection method | |
CN104200466A (en) | Early warning method and camera | |
CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
EP2813973B1 (en) | Method and system for processing video image | |
CN102682453A (en) | Moving vehicle tracking method based on multi-feature fusion | |
CN108447076A (en) | Multi-object tracking method based on depth enhancing study | |
CN103020991A (en) | Method and system for sensing moving objects in video scene | |
CN103971524A (en) | Traffic flow detection method based on machine vision | |
CN110443142A (en) | A kind of deep learning vehicle count method extracted based on road surface with segmentation | |
Li et al. | Intelligent transportation video tracking technology based on computer and image processing technology | |
CN102156989A (en) | Vehicle blocking detection and segmentation method in video frame | |
CN102663368B (en) | Moving target regional integration and optimization method on basis of Gestalt visual principle | |
CN104036639B (en) | Magnitude of traffic flow statistical method | |
CN104282157A (en) | Main line video traffic detecting method for traffic signal control |
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 | ||
C56 | Change in the name or address of the patentee | ||
CP02 | Change in the address of a patent holder |
Address after: Hongqiao Industrial Park in Taixing city of Jiangsu province Taizhou city 225400 six Wei Hong Kong Avenue Patentee after: Nanjing University Address before: 210093 Nanjing, Gulou District, Jiangsu, No. 22 Hankou Road Patentee before: Nanjing University |
|
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140917 Termination date: 20180416 |
|
CF01 | Termination of patent right due to non-payment of annual fee |