CN102881025A - Method for detecting multiple moving targets - Google Patents
Method for detecting multiple moving targets Download PDFInfo
- Publication number
- CN102881025A CN102881025A CN2012103426717A CN201210342671A CN102881025A CN 102881025 A CN102881025 A CN 102881025A CN 2012103426717 A CN2012103426717 A CN 2012103426717A CN 201210342671 A CN201210342671 A CN 201210342671A CN 102881025 A CN102881025 A CN 102881025A
- Authority
- CN
- China
- Prior art keywords
- moving target
- pixel
- point
- target
- moving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to the field of target identification and target tracking, and in particular relates to a method for detecting multiple moving targets. In a fixed scene, when a moving object exists, two adjacent acquired frames of images are different, and a moving target can be extracted by differential calculation for adjacent images; a pixel point of the extracted moving target is used as a central point of a potential function; a geopotential graph of the scene is constructed; and a maximum value point of the geopotential graph is determined as a central position of the moving target. The method can be applied to video monitoring systems.
Description
Technical field
The invention belongs to target identification and target tracking domain, relate to a kind of detection method of multiple mobile object, particularly a kind of multiple mobile object detection method that adopts frame difference method to combine with potential function method.
Background technology
The detection of moving target is the important research content of machine vision and image processing field always.At aspects such as supervisory system, safety-protection system, military fields important using value is arranged.Object detection method commonly used have powerful connections method of difference, optical flow method, frame difference method etc.The background subtraction point-score can be partitioned into Moving Objects complete, rapidly.Weak point is to be subject to the impact that light changes.Optical flow method can detect the object of self-movement, can be used for the situation of cam movement, but calculation of complex is consuming time, is difficult to detect in real time.Frame difference method is subjected to the light variable effect less, Simple fast, but can not be partitioned into complete Moving Objects, need further to use the Target Segmentation algorithm.In addition, because general target identification system has the requirement of real-time to the detection of target, the algorithm that operand is larger is difficult to satisfy this requirement.
Therefore design that a kind of operand is less, the more much higher moving target detecting method of reliability has important using value.
Summary of the invention
Technical matters to be solved by this invention is, designs a kind of moving target detecting method, can realize the detection to multiple mobile object in the consecutive image.
The technical solution adopted in the present invention is: a kind of multiple mobile object detection method, and adopt frame difference method to carry out the extraction of moving target, utilize potential function method to carry out the location of target.In a fixing scene, when having moving object, can there be certain difference between adjacent two two field pictures that collect, can extract moving target by the calculus of differences to adjacent image.Central point take the pixel of the moving target that extracts as potential function is set up the potential map of scene, and the maximum point of potential map is defined as the center of moving target.
The object of the invention is to propose a kind of moving target detecting method, detection and location that the mode that adopts frame difference method to combine with potential function method realizes moving target, accuracy and the validity of raising moving object detection.
Description of drawings
Fig. 1 sequence image video figure.
Fig. 2 moving object detection result.
Embodiment
Below in conjunction with embodiment and accompanying drawing the present invention is described in further detail.
The present invention adopts frame difference method to carry out the detection of moving target.If f
K-1(x, y), f
k(x, y) and f
K+1(x, y) be respectively k-1 constantly, k constantly and three two field pictures that constantly obtain of k+1 at coordinate (x, y) grey scale pixel value of locating, adjacent two two field pictures are wherein carried out calculus of differences, and compare with threshold value T, interpolation is defined as the background pixel point less than or equal to the pixel of threshold value, represents with 0; Interpolation is defined as the moving target pixel greater than the pixel of threshold value, represents with 1.Its formula is as follows:
In order to detect accurately moving target, the bianry image F after the consecutive frame difference that above-mentioned two formula are tried to achieve
-(x, y) and F
+(x, y) carries out AND-operation, extracts the location of pixels of moving target, that is:
F(x,y)=F
-(x,y)&F
+(x,y) (3)
Among the bianry image F (x, y) by the following formula acquisition, pixel value is the moving target pixel for the pixel of " 1 ", and pixel value is the background pixel point for the pixel of " 0 ".
Generally, the moving target pixel of above-mentioned acquisition connective bad, the accurate location that is not easy to realize moving target.In order to realize the effective location of moving target, the present invention is defined as unique point with the moving target pixel among the above-mentioned bianry image F (x, y) that tries to achieve.If feature point set is V={v
i(x
i, y
i), i=1,2 ..., M.Wherein, M is the sum of moving target pixel.Centered by unique point, determine that M potential function is as follows:
K(v,v
i)=exp[-α||v-v
1||
2],i=1,2,...,M (4)
An above-mentioned M potential function is sued for peace, obtains the potential map of entire image:
Because the unique point of same moving target is relatively concentrated, therefore its center position will be defined as the center of moving target in the maximum point place of potential map greater than the maximum point of threshold value H in the potential map.
The present invention adopts frame difference method to carry out the extraction of moving target, utilize potential function method to carry out the location of target, also can realize effectively locating for disconnected target, and can suppress distance objective noise far away to the impact of target localization, be conducive to improve the accuracy of moving object detection.
Embodiment
Fig. 1 provides the video image of sequence image, and the black cross curve among Fig. 2 has been indicated the testing result of Moving Targets in Sequent Images.Can be found out by sample result, the inventive method can be carried out comparatively accurately detection and location to the moving target in the consecutive image.
Claims (3)
1. the detection method of a multiple mobile object is characterized in that, adopts frame difference method to carry out the extraction of moving target, utilizes potential function method to carry out the location of target.In a fixing scene, when having moving object, can there be certain difference between adjacent two two field pictures that collect, can extract moving target by the calculus of differences to adjacent image.Central point take the pixel of the moving target that extracts as potential function is set up the potential map of scene, and the maximum point of potential map is defined as the center of moving target.
2. the detection method of a kind of multiple mobile object according to claim 1 is characterized in that, establishes f
K-1(x, y), f
k(x, y) and f
K+1(x, y) be respectively k-1 constantly, k constantly and three two field pictures that constantly obtain of k+1 at coordinate (x, y) grey scale pixel value of locating, adjacent two two field pictures are wherein carried out calculus of differences, and compare with threshold value T, interpolation is defined as the background pixel point less than or equal to the pixel of threshold value, represents with 0; Interpolation is defined as the moving target pixel greater than the pixel of threshold value, represents with 1.Its formula is as follows:
In order to detect accurately moving target, the bianry image f after the consecutive frame difference that above-mentioned two formula are tried to achieve
-(x, y) and F
+(x, y) carries out AND-operation, extracts the location of pixels of moving target, that is:
F(x,y)=F
-(x,y)&F
+(x,y)(3)
Among the bianry image F (x, y) by the following formula acquisition, pixel value is the moving target pixel for the pixel of " 1 ", and pixel value is the background pixel point for the pixel of " 0 ".
3. according to claim 1, the detection method of 2 described a kind of multiple mobile objects, it is characterized in that, the moving target pixel among the bianry image F (x, y) that tries to achieve is defined as unique point.If feature point set is V={v
i(x
i, y
i), i=1,2 ..., M.Wherein, M is the sum of moving target pixel.Centered by unique point, determine that M potential function is as follows:
K(v,v
i)=exp[-α||v-v
i||
2],i=1,2,...,M (4)
An above-mentioned M potential function is sued for peace, obtains the potential map of entire image:
Because the unique point of same moving target is relatively concentrated, therefore its center position will be defined as the center of moving target in the maximum point place of potential map greater than the maximum point of threshold value H in the potential map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012103426717A CN102881025A (en) | 2012-09-17 | 2012-09-17 | Method for detecting multiple moving targets |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012103426717A CN102881025A (en) | 2012-09-17 | 2012-09-17 | Method for detecting multiple moving targets |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102881025A true CN102881025A (en) | 2013-01-16 |
Family
ID=47482338
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012103426717A Pending CN102881025A (en) | 2012-09-17 | 2012-09-17 | Method for detecting multiple moving targets |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102881025A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103674104A (en) * | 2013-10-28 | 2014-03-26 | 中国科学院长春光学精密机械与物理研究所 | Method for increasing tracking distance of photoelectric device |
CN104966375A (en) * | 2015-07-01 | 2015-10-07 | 安徽创世科技有限公司 | Security monitoring system and monitoring method |
CN106056623A (en) * | 2016-05-18 | 2016-10-26 | 深圳众思科技有限公司 | Fixed scene moving object extraction method and device |
CN106651923A (en) * | 2016-12-13 | 2017-05-10 | 中山大学 | Method and system for video image target detection and segmentation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101702263A (en) * | 2009-11-17 | 2010-05-05 | 重庆大学 | Pedestrian crosswalk signal lamp green wave self-adaption control system and method |
CN101806752A (en) * | 2010-03-12 | 2010-08-18 | 长沙图创机电科技有限公司 | Method and equipment for visual detection of visible foreign matters in bottled liquid medicine |
CN102270346A (en) * | 2011-07-27 | 2011-12-07 | 宁波大学 | Method for extracting target object from interactive video |
-
2012
- 2012-09-17 CN CN2012103426717A patent/CN102881025A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101702263A (en) * | 2009-11-17 | 2010-05-05 | 重庆大学 | Pedestrian crosswalk signal lamp green wave self-adaption control system and method |
CN101806752A (en) * | 2010-03-12 | 2010-08-18 | 长沙图创机电科技有限公司 | Method and equipment for visual detection of visible foreign matters in bottled liquid medicine |
CN102270346A (en) * | 2011-07-27 | 2011-12-07 | 宁波大学 | Method for extracting target object from interactive video |
Non-Patent Citations (1)
Title |
---|
修春波等: "基于兴趣点检测的目标识别算法", 《武汉大学学报(理学版)》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103674104A (en) * | 2013-10-28 | 2014-03-26 | 中国科学院长春光学精密机械与物理研究所 | Method for increasing tracking distance of photoelectric device |
CN103674104B (en) * | 2013-10-28 | 2017-01-25 | 中国科学院长春光学精密机械与物理研究所 | Method for increasing tracking distance of photoelectric device |
CN104966375A (en) * | 2015-07-01 | 2015-10-07 | 安徽创世科技有限公司 | Security monitoring system and monitoring method |
CN106056623A (en) * | 2016-05-18 | 2016-10-26 | 深圳众思科技有限公司 | Fixed scene moving object extraction method and device |
CN106651923A (en) * | 2016-12-13 | 2017-05-10 | 中山大学 | Method and system for video image target detection and segmentation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Three-frame difference algorithm research based on mathematical morphology | |
Cheng et al. | A motion image detection method based on the inter-frame difference method | |
CN102982537B (en) | A kind of method and system detecting scene change | |
CN105225482A (en) | Based on vehicle detecting system and the method for binocular stereo vision | |
CN102789578B (en) | Infrared remote sensing image change detection method based on multi-source target characteristic support | |
CN103679748B (en) | A kind of infrared remote sensing image dim point-target extraction element and method | |
CN103745216B (en) | A kind of radar image clutter suppression method based on Spatial characteristic | |
CN105760846A (en) | Object detection and location method and system based on depth data | |
KR101348680B1 (en) | Target acquisition method for video tracker, and target acquisition apparatus using the same | |
CN104463911A (en) | Small infrared moving target detection method based on complicated background estimation | |
Wang | Research of vehicle speed detection algorithm in video surveillance | |
Lian et al. | A novel method on moving-objects detection based on background subtraction and three frames differencing | |
CN103646242B (en) | Extended target tracking based on maximum stable extremal region feature | |
CN102881025A (en) | Method for detecting multiple moving targets | |
CN102609945A (en) | Automatic registration method of visible light and thermal infrared image sequences | |
Fan et al. | Moving target detection algorithm based on Susan edge detection and frame difference | |
CN104199009B (en) | A kind of radar image clutter suppression method based on time domain specification | |
CN104391294A (en) | Connection domain characteristic and template matching based radar plot correlation method | |
CN103065329B (en) | Space rope tying robot camera automatic motion detection and compensation method | |
Widyawan et al. | Adaptive motion detection algorithm using frame differences and dynamic template matching method | |
CN106570889A (en) | Detecting method for weak target in infrared video | |
CN103400395A (en) | Light stream tracking method based on HAAR feature detection | |
CN110969605A (en) | Method and system for detecting moving small target based on space-time saliency map | |
CN103093481A (en) | Moving object detection method under static background based on watershed segmentation | |
CN104933732A (en) | Method for detecting and tracking movement target based on omnidirectional vision of robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130116 |