CN104217442B - Aerial video moving object detection method based on multiple model estimation - Google Patents
Aerial video moving object detection method based on multiple model estimation Download PDFInfo
- Publication number
- CN104217442B CN104217442B CN201410431932.1A CN201410431932A CN104217442B CN 104217442 B CN104217442 B CN 104217442B CN 201410431932 A CN201410431932 A CN 201410431932A CN 104217442 B CN104217442 B CN 104217442B
- Authority
- CN
- China
- Prior art keywords
- pset
- area
- model
- foreground blocks
- represent
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to an aerial video moving object detection method based on multiple model estimation. The aerial photography video moving object detection method comprises the following steps: firstly, utilizing a Mean shift color segmentation method to segment a scene into a plurality of color blocks; then, utilizing dense pyramid luminous flux characteristics, and adopting a RANSAC (Random Sample Consensus) method to calculate an affine transformation model corresponding the color blocks with a large area; managing smaller color blocks, and analyzing point movement consistency in the blocks so as to carry out multiple model membership degree calculation, wherein the color blocks with the big membership degree are moving blocks, and otherwise, the color blocks are false alarm targets; and finally, combining and denoising the moving blocks, and outputting and displaying a detection result. The invention obtains a 5% detection error rate of a test in a public aerial video database, and the error rate is lowered by 5% than a traditional 10% error rate.
Description
Technical field
The present invention relates to Detection for Moving Target, more particularly to a kind of video motion of taking photo by plane based on multiple-model estimator
Object detection method.
Background technology
Video frequency motion target of taking photo by plane detection is the important subject of computer vision field.Existing video motion of taking photo by plane
Object detection method is based primarily upon the moving object detection framework that single background model is estimated.Document " moving object
Detection in aerial video based on spatiotemporal saliency, chinese journal of
Aeronautics, 2013,26 (5): 1211-1217 " propose a kind of video motion mesh of taking photo by plane based on time and space significance analysis
Mark detection algorithm.The method first passes through the marking area that estimation background model and frame difference obtain on time dimension, as slightly extracts
Candidate region, carry out significance analysis in space dimension afterwards, obtain the appearance details of target in candidate region, finally by the time
Significant characteristics spatially combine, and obtain accurate moving object detection result.But the method testing result is fine or not
Depend critically upon the complexity of scene, once there is overhead building constructions, electric pole, overpass etc. in scene not in the back of the body
Static object in scape plane, will occur false-alarm, detect error rate averagely about 10%.
Content of the invention
Technical problem to be solved
In order to avoid video moving object detection method of taking photo by plane of the prior art is easily affected by scene complexity, on the scene
There are multiple background models in scape, overhead static state building, electric pole etc. cause parallax object in the case of false alarm rate very
Height, thus leading to detect mistake, the present invention proposes a kind of video moving object detection method of taking photo by plane based on multiple-model estimator.
Technical scheme
A kind of video moving object detection method of taking photo by plane based on multiple-model estimator is it is characterised in that step is as follows:
Step 1: using pyramid mean shift method, Color Segmentation is carried out to current frame image, take area to be more than given
The colored block of threshold value thresh is background block { patchbi| i=1,2 ..., bnum }, remaining is foreground blocks { patchfj| j=1,
2 ..., fnum }, wherein bnum represents background block number in frame segmentation result, i-th piece of patchbi={ areai,pseti,
pseti', areaiRepresent that i-th piece of area is comprised to count, psetiRepresent i-th piece of coordinate set being comprised a little,
pseti' represent psetiThe coordinate set of middle corresponding point a little in consecutive frame;Fnum represents foreground blocks number, jth block
patchfj={ areaj,psetj,psetj'},areajRepresent that the area of j-th foreground blocks is comprised to count, psetjRepresent
J-th foreground blocks are comprised coordinate set a little, psetj' represent psetjThe coordinate set of middle corresponding point a little in consecutive frame
Close;
Step 2: using pyramid optical flow algorithm to the point set pset in background blockiCarry out dense optical flow sign extraction, meter
Calculate psetiPixel (x0,y0) in consecutive frame, the coordinate of corresponding point is (x0',y0'):
x0'=x0+u(x0,y0)
y0'=y0+v(x0,y0)
u(x0,y0),v(x0,y0) represent pixel (x respectively0,y0) horizontal direction at place, the light stream of vertical direction;Using
Same method calculates foreground blocks Point Set psetjPixel (x1,y1) in consecutive frame, the coordinate of corresponding point is (x1',y1'):
x1'=x1+u(x1,y1)
y1'=y1+v(x1,y1)
Step 3: calculate background block patchb using ransac methodiAffine Transform Model afi, calculate psetiPixel
Point (x0,y0) corresponding projection error
IfThen (x0,y0) for meeting affine Transform Model afiBackground dot, otherwise for the back of the body
Noise spot in scape;Multi-model set is designated as af={ afi| i=1,2 ..., bnum }, afi=[ri|ti], wherein riAnd tiPoint
Wei not spin matrix and translation matrix;
Step 4: calculate current j-th foreground blocks patchfjIn k-th point of (xj,k,yj,k) under i-th background model
Motion vector:
Wherein (xj,k',yj,k') represent (xj,k,yj,k) in psetj' in corresponding point coordinate, vj,k(x) and vj,k(y) difference
Represent movement velocity both horizontally and vertically;
Calculate j-th foreground blocks degree of membership to i-th background model:
Step 5: according to degree of membership calculating Subject Matrix p:
Wherein θ is degree of membership threshold value, ifThen determine that j-th foreground blocks is moving mass;Moving mass is entered
Row merges:
A) initialization model integrates queue q as null, and object set queue o is null;
B) count the background model that current j-th foreground blocks are subordinate to, the set of these background models is designated as sj:
C) travel through Models Sets queue q, ifMake q (m) ∩ sj≠ null, then by sjIt is incorporated to q (m), q (m)=q (m) ∪
sj, j-th foreground blocks is incorporated to corresponding object set queue o, otherwise execution step d);
D) by sjAdd Models Sets queue q as newcomer, corresponding foreground blocks add object set queue o as newcomer;
Step 6: traversal object set queue o, if there are two block centre distances in current membership to be less than first threshold, enters
Row merges, and carries out noise remove after merging, area in testing result is less than to the moving mass of Second Threshold, as mistake inspection
Survey is removed, finally by testing result display output.
Described threshold value thresh=0.01 × imgwidth × imgheight, imgwidth and imgheight table respectively
Show width and the height of inputted video image.
Described dis takes 1.
Described θ=0.6.
Described first threshold takes 1.5 times of two block radius sums.
Described Second Threshold takes 100 pixels.
Beneficial effect
A kind of video moving object detection method of taking photo by plane based on multiple-model estimator proposed by the present invention, using Color Segmentation
Scene partitioning is multiple models, and extract pyramid Optical-flow Feature multiple-model estimator is carried out to scene so that testing result not
Uniform background is depended on to estimate again and registering result, thus improving detection algorithm robustness;Additionally, by target to multi-model
Degree of membership calculate, can effectively remove the false-alarm targets such as building constructions, electric pole, tall and big trees, detection lower error rate is extremely
5%.
Specific embodiment
In conjunction with embodiment, the invention will be further described:
1st, mean shift Color Segmentation
One section of video sequence of taking photo by plane of input, is to carry out coloured silk using pyramid mean shift method to current frame image first
Color is split.In order to ensure computational efficiency and degree of accuracy simultaneously, originally apply in example and take the pyramid number of plies to be 3, color window width is 10, space
Position window width is 10.The colored block that area is more than given threshold value thresh is taken to be background block, remaining is foreground blocks, originally applies in example and takes
Thresh=0.01 × imgwidth × imgheight, imgwidth and imgheight represent the width of inputted video image respectively
And height.{patchbi| i=1,2 ..., bnum } represent background block in present frame segmentation result, wherein bnum represents frame segmentation knot
Background block number in fruit, i-th piece of patchbi={ areai,pseti,pseti', areaiRepresent that i-th piece of area is comprised
Points, psetiRepresent i-th piece of coordinate set being comprised a little, pseti' represent psetiMiddle corresponding point a little in consecutive frame
Coordinate, be set to null.{patchfj| j=1,2 ..., fnum } represent foreground blocks in present frame segmentation result, fnum
Represent foreground blocks number, each foreground blocks equally also comprises area and point set patchfj={ areaj,psetj,psetj'},
areajRepresent that the area of j-th foreground blocks is comprised to count, psetjRepresent that j-th foreground blocks are comprised coordinate set a little,
psetj' represent psetjThe coordinate of middle corresponding point a little in consecutive frame, is set to null.
2nd, dense optical flow signature tracking
In view of ageing and accuracy, using pyramid optical flow algorithm, dense optical flow body is carried out to present frame and consecutive frame
Levy extraction, calculate the light stream vector of each point pixel-by-pixel, that is, predict position in consecutive frame for each pixel, originally apply in example and take
Pyramid coefficient is 0.5, and the pyramid number of plies is 3, window width 15, and iterationses are 3, smoothing windows a width of 5, and variance is 1.2.u(x,
Y), v (x, y) represents the horizontal direction at pixel (x, y) place, the light stream of vertical direction respectively, then pixel (x, y) is adjacent
In frame, the coordinate of corresponding point is (x', y').
X '=x+u (x, y) (3)
Y '=y+v (x, y)
So far, background block Point Set pset can be calculatediCorresponding point set pset in consecutive framei':There is (x0',y0')∈pseti', wherein x0'=x0+u(x0,y0),y0'=y0+v(x0,y0).
Foreground blocks Point Set pset can also be calculatedjCorresponding point set pset in consecutive framej':Have
(x1',y1')∈psetj', wherein x1'=x1+u(x1,y1),y1'=y1+v(x1,y1).
3rd, multiple background model estimation
Each background block patchb in segmentation resultiA corresponding affine Transform Model.Using ransac method and background
Pixel point set pset in blocki、pseti' to the affine Transform Model af calculating between present frame and next framei, and by psetiIn
Institute is a little according to affine model afiProjection error be divided into interior point and exterior point, interior point as meets transformation model afiBackground
Point, exterior point is then the noise spot in this background.(x0,y0) corresponding projection errorIt is calculated as follows:
IfThen (x0,y0) it is interior point, otherwise for exterior point.Originally apply in example and take distance threshold dis
For 1, confidence level takes 0.99.Multi-model set is designated as af={ afi| i=1,2 ..., bnum }.
afi=[ri|ti] (5)
Wherein riAnd tiIt is respectively spin matrix and translation matrix.
4th, degree of membership calculates
Calculate subordinated-degree matrix mbnum×fnum, the degree of membership to i-th background model for m (i, j) j-th foreground blocks of expression, this
In degree of membership be defined as the correlation coefficient of point motion vector in block, i.e. point Movement consistency tolerance in block.Theoretically analyze, very
Positive target all point motion vectors in its background model more consistent it should have larger degree of membership, and building construction,
The decoys such as electric pole trees then do not possess above-mentioned attribute.So current j-th foreground blocks patchfjIn k-th point of (xj,k,
yj,k) the motion vector computation formula under i-th background model is as follows:
Wherein (xj,k',yj,k') represent (xj,k,yj,k) in psetj' in corresponding point coordinate, vj,k(x) and vj,k(y) difference
Represent movement velocity both horizontally and vertically.The average of j-th foreground blocks movement velocity is:
So j-th foreground blocks are as follows to the degree of membership computing formula of i-th background model:
M (i, j) ∈ [0,1], and closer to 1, m (i, j) shows that j-th foreground blocks is subordinate to i-th foreground model
Degree is bigger, is that the probability of moving target in this background is bigger.
5th, testing result management and output
First Subject Matrix p is calculated according to degree of membership as follows:
Wherein θ it is contemplated that influence of noise and edge's light stream mistake, originally applies in example and takes θ=0.6 for degree of membership threshold value.IfThen determine that j-th foreground blocks is moving mass.In view of moving target itself because of color inconsistent and
It is divided into multiple moving mass, need to carry out the merging of moving mass.
Initialization model integrates queue q as null, and object set queue o is null.Traversal Subject Matrix p holds line by line from top to bottom
Row is following to be operated:
A) count the background model that current j-th foreground blocks are subordinate to, the set of these background models is designated as sj:
B) travel through Models Sets queue q, ifMake q (m) ∩ sj≠ null, then by sjIt is incorporated to q (m), q (m)=q (m) ∪
sj, j-th foreground blocks is incorporated to corresponding object set queue o, otherwise execution step c);
C) by sjAdd Models Sets queue q as newcomer, corresponding foreground blocks add object set queue o as newcomer.
So far obtain Models Sets queue and corresponding object set queue, carry out the merging of foreground blocks below.Traversal target
Collection queue, if there are two block centre distances in current membership and (originally applying and take the 1.5 of two block radius sums in example less than given threshold value
Times) then merge.Carry out noise remove after merging, area in testing result (is originally applied in example less than given threshold value
100 pixels) moving mass, be removed as error detection.Finally by testing result display output.
Claims (6)
1. a kind of video moving object detection method of taking photo by plane based on multiple-model estimator is it is characterised in that step is as follows:
Step 1: using pyramid mean shift method, Color Segmentation is carried out to current frame image, take area to be more than given threshold value
The colored block of thresh is background block { patchbi| i=1,2 ..., bnum }, remaining is foreground blocks { patchfj| j=1,
2 ..., fnum }, wherein bnum represents background block number in frame segmentation result, i-th piece of patchbi={ areai,pseti,
pseti', areaiRepresent that i-th piece of area is comprised to count, psetiRepresent i-th piece of coordinate set being comprised a little,
pseti' represent psetiThe coordinate set of middle corresponding point a little in consecutive frame;Fnum represents foreground blocks number, jth block
patchfj={ areaj,psetj,psetj'},areajRepresent that the area of j-th foreground blocks is comprised to count, psetjRepresent
J-th foreground blocks are comprised coordinate set a little, psetj' represent psetjThe coordinate set of middle corresponding point a little in consecutive frame
Close;
Step 2: using pyramid optical flow algorithm to the point set pset in background blockiCarry out dense optical flow sign extraction, calculate
psetiPixel (x0,y0) in consecutive frame, the coordinate of corresponding point is (x0',y0'):
x0'=x0+u(x0,y0)
y0'=y0+v(x0,y0)
u(x0,y0),v(x0,y0) represent pixel (x respectively0,y0) horizontal direction at place, the light stream of vertical direction;Using same
Method calculates foreground blocks Point Set psetjPixel (x1,y1) in consecutive frame, the coordinate of corresponding point is (x1',y1'):
x1'=x1+u(x1,y1)
y1'=y1+v(x1,y1)
Step 3: calculate background block patchb using ransac methodiAffine Transform Model afi, calculate psetiPixel
(x0,y0) corresponding projection error
IfThen (x0,y0) for meeting affine Transform Model afiBackground dot, otherwise in background
Noise spot;Multi-model set is designated as af={ afi| i=1,2 ..., bnum }, afi=[ri|ti], wherein riAnd tiIt is respectively and revolve
Torque battle array and translation matrix;
Step 4: calculate current j-th foreground blocks patchfjIn k-th point of (xj,k,yj,k) motion under i-th background model
Vector:
Wherein (xj,k',yj,k') represent (xj,k,yj,k) in psetj' in corresponding point coordinate, vj,k(x) and vj,kY () represents respectively
Movement velocity both horizontally and vertically;
Calculate j-th foreground blocks degree of membership to i-th background model:
Step 5: according to degree of membership calculating Subject Matrix p:
Wherein θ is degree of membership threshold value, ifThen determine that j-th foreground blocks is moving mass;Moving mass is closed
And:
A) initialization model integrates queue q as null, and object set queue o is null;
B) count the background model that current j-th foreground blocks are subordinate to, the set of these background models is designated as sj:
C) travel through Models Sets queue q, ifMake q (m) ∩ sj≠ null, then by sjIt is incorporated to q (m), q (m)=q (m) ∪ sj, will
J-th foreground blocks is incorporated to corresponding object set queue o, otherwise execution step d);
D) by sjAdd Models Sets queue q as newcomer, corresponding foreground blocks add object set queue o as newcomer;
Step 6: traversal object set queue o, if there are two block centre distances in current membership to be less than first threshold, is closed
And, carry out noise remove after merging, area in testing result is less than to the moving mass of Second Threshold, enters as error detection
Row removes, finally by testing result display output.
2. according to claim 1 based on multiple-model estimator take photo by plane video moving object detection method it is characterised in that
Described threshold value thresh=0.01 × imgwidth × imgheight, imgwidth and imgheight represents that input regards respectively
The width of frequency image and height.
3. according to claim 1 based on multiple-model estimator take photo by plane video moving object detection method it is characterised in that
Described dis takes 1.
4. according to claim 1 based on multiple-model estimator take photo by plane video moving object detection method it is characterised in that
Described θ=0.6.
5. according to claim 1 based on multiple-model estimator take photo by plane video moving object detection method it is characterised in that
Described first threshold takes 1.5 times of two block radius sums.
6. according to claim 1 based on multiple-model estimator take photo by plane video moving object detection method it is characterised in that
Described Second Threshold takes 100 pixels.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410431932.1A CN104217442B (en) | 2014-08-28 | 2014-08-28 | Aerial video moving object detection method based on multiple model estimation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410431932.1A CN104217442B (en) | 2014-08-28 | 2014-08-28 | Aerial video moving object detection method based on multiple model estimation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104217442A CN104217442A (en) | 2014-12-17 |
CN104217442B true CN104217442B (en) | 2017-01-25 |
Family
ID=52098884
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410431932.1A Active CN104217442B (en) | 2014-08-28 | 2014-08-28 | Aerial video moving object detection method based on multiple model estimation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104217442B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105975918B (en) * | 2016-04-29 | 2019-04-02 | 厦门大学 | The moving target detecting method towards mobile camera based on multiple-model estimator |
CN107316030A (en) * | 2017-07-04 | 2017-11-03 | 西北工业大学深圳研究院 | Unmanned plane is to terrain vehicle automatic detection and sorting technique |
CN107330922A (en) * | 2017-07-04 | 2017-11-07 | 西北工业大学 | Video moving object detection method of taking photo by plane based on movable information and provincial characteristics |
CN108540769B (en) * | 2018-02-05 | 2019-03-29 | 东营金丰正阳科技发展有限公司 | Unmanned flight's platform real-time image transmission system |
CN108491818B (en) * | 2018-03-30 | 2019-07-05 | 北京三快在线科技有限公司 | Detection method, device and the electronic equipment of target object |
CN109102503A (en) * | 2018-08-13 | 2018-12-28 | 北京市遥感信息研究所 | It is a kind of based on color space smoothly and improve the significant model of frequency tuning high score image change detection method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110020961A (en) * | 2009-08-25 | 2011-03-04 | 삼성전자주식회사 | Method of detecting and tracking moving object for mobile platform |
CN103413324A (en) * | 2013-07-29 | 2013-11-27 | 西北工业大学 | Automatic target tracking method for aerially photographed videos |
CN103426172A (en) * | 2013-08-08 | 2013-12-04 | 深圳一电科技有限公司 | Vision-based target tracking method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9147260B2 (en) * | 2010-12-20 | 2015-09-29 | International Business Machines Corporation | Detection and tracking of moving objects |
-
2014
- 2014-08-28 CN CN201410431932.1A patent/CN104217442B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110020961A (en) * | 2009-08-25 | 2011-03-04 | 삼성전자주식회사 | Method of detecting and tracking moving object for mobile platform |
CN103413324A (en) * | 2013-07-29 | 2013-11-27 | 西北工业大学 | Automatic target tracking method for aerially photographed videos |
CN103426172A (en) * | 2013-08-08 | 2013-12-04 | 深圳一电科技有限公司 | Vision-based target tracking method and device |
Non-Patent Citations (6)
Title |
---|
Moving object detection in aerial video based on spatiotemporal saliency;Shen Hao 等;《Chinese Journal of Aeronautics》;20131231;第26卷(第5期);1211-1217 * |
Random Sample Consensus:A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography;Martin A. Fischler 等;《Communications of the ACM》;19810630;第24卷(第6期);381-395 * |
Two-Frame Motion Estimation Based on Polynomial Expansion;Gunnar Farneback;《SCIA 2003》;20031231;第2749卷;363-370 * |
全局-局部联合滤波的红外小目标背景抑制方法;莫金花 等;《中国体视学与图像分析》;20111231;第16卷(第3期);223-231 * |
自适应的均值漂移分割算法;马瑜 等;《激光与红外》;20131031;第43卷(第10期);1162-1165 * |
航拍视频图像中地面运动目标的快速锁定;于映雪;《通讯世界》;20140630;8-9 * |
Also Published As
Publication number | Publication date |
---|---|
CN104217442A (en) | 2014-12-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104217442B (en) | Aerial video moving object detection method based on multiple model estimation | |
CN111539273B (en) | Traffic video background modeling method and system | |
CN106910203B (en) | The quick determination method of moving target in a kind of video surveillance | |
CN103164706B (en) | Object counting method and device based on video signal analysis | |
Sidla et al. | Pedestrian detection and tracking for counting applications in crowded situations | |
EP2858008B1 (en) | Target detecting method and system | |
CN110175576A (en) | A kind of driving vehicle visible detection method of combination laser point cloud data | |
CN109598794B (en) | Construction method of three-dimensional GIS dynamic model | |
CN103077521B (en) | A kind of area-of-interest exacting method for video monitoring | |
CN110490911B (en) | Multi-camera multi-target tracking method based on non-negative matrix factorization under constraint condition | |
US8712096B2 (en) | Method and apparatus for detecting and tracking vehicles | |
CN102799883B (en) | Method and device for extracting movement target from video image | |
CN106875424A (en) | A kind of urban environment driving vehicle Activity recognition method based on machine vision | |
CN102156880A (en) | Method for detecting abnormal crowd behavior based on improved social force model | |
CN109460764A (en) | A kind of satellite video ship monitoring method of combination brightness and improvement frame differential method | |
CN105279769A (en) | Hierarchical particle filtering tracking method combined with multiple features | |
CN106778633B (en) | Pedestrian identification method based on region segmentation | |
Hinz et al. | Car detection in aerial thermal images by local and global evidence accumulation | |
CN109636771A (en) | Airbound target detection method and system based on image procossing | |
CN103747240A (en) | Fusion color and motion information vision saliency filtering method | |
CN103735269A (en) | Height measurement method based on video multi-target tracking | |
CN103679677A (en) | Dual-model image decision fusion tracking method based on mutual updating of models | |
CN106156714A (en) | The Human bodys' response method merged based on skeletal joint feature and surface character | |
CN106657948A (en) | low illumination level Bayer image enhancing method and enhancing device | |
Wang et al. | Low-altitude infrared small target detection based on fully convolutional regression network and graph matching |
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 |