CN105389832B - A kind of video target tracking method based on Grassmann manifolds and projection group - Google Patents
A kind of video target tracking method based on Grassmann manifolds and projection group Download PDFInfo
- Publication number
- CN105389832B CN105389832B CN201510804824.9A CN201510804824A CN105389832B CN 105389832 B CN105389832 B CN 105389832B CN 201510804824 A CN201510804824 A CN 201510804824A CN 105389832 B CN105389832 B CN 105389832B
- Authority
- CN
- China
- Prior art keywords
- feature
- space
- target
- sampling
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
A kind of video target tracking method based on Grassmann manifolds and projection group, is related to a kind of modeling method, including inputted video image sequence, is predicted according to formula, j=1,2 ... .L.L is sampling population；V is the velocity vector that state is moved to moment t by moment t 1；；Image-region corresponding to each sampling, calculates the feature basic matrix of corresponding apparent gray matrix, calculated in sampling by formula and accumulate mean value, according to the more new strategy in target signature space, update feature space；This method is undergoing significantly nonplanar geometric deformation, illumination variation and experience partial occlusion to target, it can realize stable tracking, using the geometric deformation model of more accurate projective transformation design object, bimodulus video frequency object tracking algorithm is devised.
Description
Technical field
The present invention relates to a kind of modeling methods, more particularly to a kind of video based on Grassmann manifolds and projection group
Method for tracking target.
Background technology
For video object significantly nonplanar attitudes vibration, the method for tracking target based on Euclidean space is often
The tracking of target is caused to deviate or fail.It is not main reason is that the characteristic of the apparent different postures in description target area is
It is present in some individual vector space, traditional linear vector space processing mode cannot be satisfied actual needs.It considers
Grassmann manifolds are a kind of entropy flow shapes in Lie Group Manifold, have the characteristic of distance between being more suitable for metric data point, together
When in view of the imaging process of image is substantially projective transformation process, that is, obey projective transformation group（SL(3)）.
Invention content
The purpose of the present invention is to provide a kind of based on Grassmann manifolds and projects the video target tracking method of group,
This method is undergoing significantly nonplanar geometric deformation, illumination variation and experience partial occlusion to target, can
Realize that stable tracking, the geometric deformation model of the more accurate projective transformation design object of use devise bimodulus video mesh
Mark track algorithm.
The purpose of the present invention is what is be achieved through the following technical solutions：
A kind of video target tracking method based on Grassmann manifolds and projection group, the method includes following procedure：
Step 1：Inputted video image sequence, totalframes k, original template size are m*n（Unit：Picture
Element）；For first frame image, the target area of manually determined image, 8 dimensional vectors on projective transformation groupTo track the projective transformation parameter of boundary shape, t is present frame, for the
One frame image, t=1；
Step 2：It is predicted according to following formula, j=1,2 ... .L. L are sampling population；V is state by moment t-
1 moves to the velocity vector of moment t；
；
Step 3：Image-region corresponding to each sampling, calculates the feature basic matrix of corresponding apparent gray matrix,
Then according to formulaCalculate the weights of each sampling particle:
WhereinIt is characterized spaceFeature basic matrix, vectorIndicate t frames with
The target that track arrives.WithIt is two points in Grassmann manifolds, leading role's degree between the two is；
Step 4：Pass through formulaIt calculates in sampling and accumulates mean value, as target is estimated
Meter state；
Step 5：According to the more new strategy in target signature space, feature space is updated；More
New strategy is as follows：
The minimum value of the feature vector of present frame and each feature vector geodesic curve distance of feature space is ds, when ds is big
When given max-thresholds thresmax, illustrate that the frame image is seriously blocked or is distorted, is at this time guarantee feature space letter
The accuracy of breath does not update feature space；
Otherwise template set is updated in two kinds of situation：
（1）In current feature space vectorial number be less than prespecified quantity when, directly by the feature of present frame to
Amount is added in this feature spatial aggregation；
（2）Otherwise, the feature vector with maximum range value in feature space is replaced with the feature vector of present frame；
Step 6：T=t+1, ifOtherwise repetition step 2. tracks process and terminates.
Advantages of the present invention is with effect：
1. the present invention makes full use of the nonlinear characteristic in Grassmann manifolds space, the apparent variation of target is regarded as
The movement put in manifold makes full use of the intrinsic geometry characteristic of state space, designs particle filter algorithm, more acurrate can estimate
The apparent variation of target；
2. the present invention describes the geometric deformation process of target using SL (3) group.Compared with affine transformation, more accurately describe
The deformation process of target more accurately predicts the geometric deformation of target；
3. design effectively target signature spatial update strategy of the present invention, in the apparent feature space on-line study process of target
In, effectively shield exception information, it is ensured that the accuracy of feature space.
Description of the drawings
Fig. 1 shows the video frequency object tracking specific steps based on Grassmann manifolds and projection group；
Fig. 2 shows the results of the algorithm keeps track geometric deformation target；
Fig. 3 shows the result under the algorithm keeps track non-rigid illumination variation；
Fig. 4 shows the result of the algorithm keeps track experience partial occlusion target.
Specific implementation mode
The following describes the present invention in detail with reference to examples.
Embodiment 1：
Step 1：
Geometric deformation sequence of video images 1, totalframes 400 are inputted, original template size is 80*48（Unit：Pixel）.
For first frame image, the target area of manually determined image, 8 dimensional vectors [0.03 on projective transformation group;0.01;0.01;
0.01;0.02;0.02;10;10] be tracking boundary shape projective transformation parameter, t is present frame, for first frame image, t=
1。
Step 2：
It is predicted according to following formula, j=1,2 ... .300. 300 is sampling population；V is state by moment t-1
Move to the velocity vector of moment t.
Step 3：
Image-region corresponding to each sampling, calculates the feature basic matrix of corresponding apparent gray matrix, then root
According to formulaCalculate the weights of each sampling particle:
WhereinIt is characterized spaceFeature basic matrix, vectorIndicate t frames
The target traced into.WithIt is two points in Grassmann manifolds, leading role's degree between the two is。
Step 4：
Pass through formulaIt calculates in sampling and accumulates mean value, the as estimated state of target。
Step 5：
According to the more new strategy in target signature space, feature space is updated.More new strategy is such as
Under：
The minimum value of the feature vector of present frame and each feature vector geodesic curve distance of feature space is ds, when ds is big
In given max-thresholdsWhen, illustrate that the frame image is seriously blocked or is distorted, is at this time guarantee feature-space information
Accuracy do not update feature space.Otherwise template set is updated in two kinds of situation：
（1）When vectorial number is less than 10 in current feature space, the feature vector of present frame is directly added to the spy
It levies in spatial aggregation.
（2）Otherwise, the feature vector with maximum range value in feature space is replaced with the feature vector of present frame.
Step 6：
T=t+1, ifOtherwise repetition step 2. tracks process and terminates.
Attached drawing 2 is the tracking result of the algorithm partial frame.
Embodiment 2：
Step 1：
Illumination variation sequence of video images 2, totalframes 500 are inputted, original template size is 78*62（Unit：Pixel）.
For first frame image, the target area of manually determined image, 8 dimensional vectors [0.01 on projective transformation group;0.001;0.001;
0.03;0.01;0.01;10;10] it is the projective transformation parameter for tracking boundary shape.T is present frame, for first frame image, t=
1。
Step 2：
It is predicted according to following formula, j=1,2 ... .300. 300 is sampling population；V is state by moment t-1
Move to the velocity vector of moment t.
Step 3：
Image-region corresponding to each sampling, calculates the feature basic matrix of corresponding apparent gray matrix, then
According to formulaCalculate the weights of each sampling particle:
WhereinIt is characterized spaceFeature basic matrix, vectorIndicate t frames
The target traced into.WithIt is two points in Grassmann manifolds, leading role's degree between the two is。
Step 4：
Pass through formulaIt calculates in sampling and accumulates mean value, the as estimated state of target。
Step 5：
According to the more new strategy in target signature space, feature space is updated.More new strategy is such as
Under：
The minimum value of the feature vector of present frame and each feature vector geodesic curve distance of feature space is ds, when ds is big
In given max-thresholdsWhen, illustrate that the frame image is seriously blocked or is distorted, is at this time guarantee feature-space information
Accuracy do not update feature space.Otherwise template set is updated in two kinds of situation：
（1）When vectorial number is less than 10 in current feature space, the feature vector of present frame is directly added to the spy
It levies in spatial aggregation.
（2）Otherwise, the feature vector with maximum range value in feature space is replaced with the feature vector of present frame.
Step 6：
T=t+1, ifOtherwise repetition step 2. tracks process and terminates.
Attached drawing 3 is the tracking result of the algorithm partial frame.
Embodiment 3：
Step 1：
Sequence of video images 3, totalframes 100 are blocked in importation, and original template size is 112*52（Unit：Picture
Element）.For first frame image, the target area of manually determined image, 8 dimensional vectors [0.05 on projective transformation group;0.002;
0.001;0.02;0.02;0.02;10;10] it is the projective transformation parameter for tracking boundary shape.T is present frame, for first frame
Image, t=1.
Step 2：
It is predicted according to following formula, j=1,2 ... .300. 300 is sampling population；V is state by moment t-1
Move to the velocity vector of moment t.
Step 3：
Image-region corresponding to each sampling, calculates the feature basic matrix of corresponding apparent gray matrix, then
According to formulaCalculate the weights of each sampling particle:
WhereinIt is characterized spaceFeature basic matrix, vectorIndicate t frames
The target traced into.WithIt is two points in Grassmann manifolds, leading role's degree between the two is。
Step 4：
Pass through formulaIt calculates in sampling and accumulates mean value, the as estimated state of target。
Step 5：
According to the more new strategy in target signature space, feature space is updated.More new strategy
It is as follows：
The minimum value of the feature vector of present frame and each feature vector geodesic curve distance of feature space is ds, when ds is big
In given max-thresholdsWhen, illustrate that the frame image is seriously blocked or is distorted, is at this time guarantee feature-space information
Accuracy do not update feature space.Otherwise template set is updated in two kinds of situation：
（1）When vectorial number is less than 10 in current feature space, the feature vector of present frame is directly added to the spy
It levies in spatial aggregation.
（2）Otherwise, the feature vector with maximum range value in feature space is replaced with the feature vector of present frame.
Step 6：
T=t+1, ifOtherwise repetition step 2. tracks process and terminates.
Attached drawing 4 is the tracking result of the algorithm partial frame.
Claims (1)
1. a kind of video target tracking method based on Grassmann manifolds and projection group, which is characterized in that the method includes
Following procedure：
Step 1：Inputted video image sequence, totalframes k, original template size are m*n；For first frame image, manually really
Determine the target area of image, 8 dimensional vectors on projective transformation group
To track the projective transformation parameter of boundary shape, t is present frame, right
In first frame image, t=1；
Step 2：It is predicted according to following formula, j=1,2 ... L, L are sampling population；V is that state is moved to by moment t-1
The velocity vector of moment t；
；
Step 3：Image-region corresponding to each sampling, calculates the feature basic matrix of corresponding apparent gray matrix, then
According to formulaCalculate the weights of each sampling particle:,
WhereinIt is characterized spaceFeature basic matrix, vectorIndicate the target that t frames trace into；WithLeading role's degree between the two is；WhereinFor proportionality coefficient；
Step 4：Pass through formulaIt calculates in sampling and accumulates mean value, the as estimated state of target；
Step 5：According to the more new strategy in target signature space, feature space is updated；More new strategy is such as
Under：
The minimum value of the feature vector of present frame and each feature vector geodesic curve distance of feature space is ds, is given when ds is more than
When fixed max-thresholds thresmax, illustrate that the frame image is seriously blocked or is distorted, is to ensure feature-space information at this time
Accuracy does not update feature space；
Otherwise template set is updated in two kinds of situation：
（1）When vectorial number is less than prespecified quantity in current feature space, directly the feature vector of present frame is added
Enter into this feature spatial aggregation；
（2）Otherwise, the feature vector with maximum range value in feature space is replaced with the feature vector of present frame；
Step 6：T=t+1, ifStep 2 is repeated, process is otherwise tracked and terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510804824.9A CN105389832B (en) | 2015-11-20 | 2015-11-20 | A kind of video target tracking method based on Grassmann manifolds and projection group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510804824.9A CN105389832B (en) | 2015-11-20 | 2015-11-20 | A kind of video target tracking method based on Grassmann manifolds and projection group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105389832A CN105389832A (en) | 2016-03-09 |
| CN105389832B true CN105389832B (en) | 2018-08-21 |
Family
ID=55422081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510804824.9A Expired - Fee Related CN105389832B (en) | 2015-11-20 | 2015-11-20 | A kind of video target tracking method based on Grassmann manifolds and projection group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105389832B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105761281A (en) * | 2016-03-23 | 2016-07-13 | 沈阳大学 | Particle filter target tracking algorithm and system based on bilateral structure tensor |
| CN111428567B (en) * | 2020-02-26 | 2024-02-02 | 沈阳大学 | Pedestrian tracking system and method based on affine multitask regression |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982556A (en) * | 2012-11-01 | 2013-03-20 | 江苏科技大学 | Video target tracking method based on manifold particle filter algorithm |
| CN103093480A (en) * | 2013-01-15 | 2013-05-08 | 沈阳大学 | Particle filtering video image tracking method based on dual model |
-
2015
- 2015-11-20 CN CN201510804824.9A patent/CN105389832B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982556A (en) * | 2012-11-01 | 2013-03-20 | 江苏科技大学 | Video target tracking method based on manifold particle filter algorithm |
| CN103093480A (en) * | 2013-01-15 | 2013-05-08 | 沈阳大学 | Particle filtering video image tracking method based on dual model |
Non-Patent Citations (4)
| Title |
|---|
| Information Technology in Multi-object Tracking based on Bilateral Structure Tensor Corner Detection for Mutual Occlusion;Yinghong Xie 等;《Advanced Materials Research》;20140623;第977卷;第502-506页 * |
| ONLINE SUBSPACE LEARNING ON GRASSMANN MANIFOLD FOR MOVING OBJECT TRACKING IN VIDEO;Tiesheng Wang 等;《ICASSP 2008》;20081231;第969-972页 * |
| 基于Grassmann流形的仿射不变形状识别;刘云鹏 等;《自动化学报》;20100227;第38卷(第2期);第248-258页 * |
| 基于偏最小二乘分析的双模粒子滤波目标跟踪;谢英红 等;《控制与决策》;20140831;第29卷(第8期);第1372-1378页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105389832A (en) | 2016-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875425A (en) | A kind of multi-target tracking system and implementation method based on deep learning | |
| CN103761737B (en) | Robot motion's method of estimation based on dense optical flow | |
| CN105427308B (en) | A kind of sparse and dense characteristic mates the method for registering images for combining | |
| JP3735344B2 (en) | Calibration apparatus, calibration method, and calibration program | |
| CN107274337B (en) | Image splicing method based on improved optical flow | |
| CN106886748B (en) | TLD-based variable-scale target tracking method applicable to unmanned aerial vehicle | |
| CN110111250A (en) | A kind of automatic panorama unmanned plane image split-joint method and device of robust | |
| EP3186787A1 (en) | Method and device for registering an image to a model | |
| KR20150011938A (en) | Method and apparatus for stabilizing panorama video captured based multi-camera platform | |
| CN105389832B (en) | A kind of video target tracking method based on Grassmann manifolds and projection group | |
| CN110070565A (en) | A kind of ship trajectory predictions method based on image superposition | |
| CN105957097A (en) | Image registration method based on mixed mutual information and improved particle swarm optimization | |
| CN103093480B (en) | Based on the particle filter video image tracking of bimodel | |
| CN115272582A (en) | System and method for body modeling | |
| CN103839280B (en) | A kind of human body attitude tracking of view-based access control model information | |
| CN116152121B (en) | Curved surface screen generating method and correcting method based on distortion parameters | |
| CN109729263A (en) | Video based on fusional movement model removes fluttering method | |
| Zhao et al. | 3D object tracking via boundary constrained region-based model | |
| Modat et al. | Log-Euclidean free-form deformation | |
| Fishbaugh et al. | Acceleration controlled diffeomorphisms for nonparametric image regression | |
| Xu et al. | Optical flow-based video completion in spherical image sequences | |
| CN105427310A (en) | Image registration method of sparse feature matching on the basis of local linear constraint | |
| CN109754412B (en) | Target tracking method, target tracking apparatus, and computer-readable storage medium | |
| CN106886791A (en) | Fat location recognition methods in a kind of two-dimensional ct picture based on condition random field | |
| Pai et al. | Stepwise inverse consistent euler’s scheme for diffeomorphic image registration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20160309 Assignee: Shenyang Hechi Technology Co., Ltd Assignor: Shenyang Univ. Contract record no.: X2019210000010 Denomination of invention: Video object tracking method based on Grassmann manifold and projection group Granted publication date: 20180821 License type: Exclusive License Record date: 20191029 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180821 Termination date: 20191120 |