Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Particle filtering video image tracking method based on dual model

A video image and particle filtering technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as robust algorithms, and achieve stable and robust tracking effects.

Inactive Publication Date: 2013-05-08
SHENYANG UNIV
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no more robust algorithm for objects with obvious geometric deformation, or when the object undergoes strong illumination transformation.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Particle filtering video image tracking method based on dual model
  • Particle filtering video image tracking method based on dual model
  • Particle filtering video image tracking method based on dual model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] The geometrically deformable target is tracked using the algorithm described above.

[0031] Step 1: The video image sequence has a total of 271 frames, and the size of each frame is 320*240. The initial size of the template is 42*42. 8-dimensional vector is the projection transformation parameter of tracking boundary shape, t=1;

[0032] Step 2: Predict according to the following formula , j=1,2….16. 16 is the number of sampled particles; v is the velocity vector of the state transition from time t-1 to time t.

[0033]

[0034] For example to get:

[0035] Step 3: Use the following formula to construct the covariance matrix, and calculate the correlation with each The covariance of the corresponding image patch ;

[0036]

[0037] For a given region R whose size is 42×42, , is the mean vector. . x,y Indicates the abscissa and ordinate of the corresponding pixel. and represent images respectively exist x direction and y The gradient va...

Embodiment 2

[0064] Light transform targets are tracked using the algorithm described above.

[0065] Step 1: The video image sequence has a total of 600 frames, and the size of each frame is 320*240. The initial size of the template is 104*110. 8-dimensional vector is the projection transformation parameter of tracking boundary shape, t=1;

[0066] Step 2: Predict according to the following formula , j=1,2….25. 25 is the number of sampled particles; v is the velocity vector of the state transition from time t-1 to time t.

[0067]

[0068] For example to get:

[0069] Step 3: Use the following formula to construct the covariance matrix, and calculate the correlation with each The covariance of the corresponding image patch ;

[0070]

[0071] For a given region R, its size is 104*110, , is the mean vector. . x,y Indicates the abscissa and ordinate of the corresponding pixel. and represent images respectively exist x direction and y The gradient value in t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a particle filtering video image tracking method based on a dual model, and relates to video image tracking methods. A dual particle filter is built and alternating tracking dynamic models are achieved. One of the particle filters is represented in on-line updating goals of a covariance matrix Riemann flow model and the other one of the particle filters is used for conducting tracking to bounding box parameters of objects in a projection transformation group. Lie algebra and transformation relation of a tangent space of the Lie algebra are adopted by measuring of the filtering parameters, considering the fact that the essence of the process of target-orient imaging is the process of projection transformation, when the particle filtering video image tracking method builds a tracking algorithm based on the particle filtering, a covariance flow model and a projection transformation group (SL (3) group) are combined simultaneously. The particle filtering video image tracking method based on the dual model has the advantages of achieving stable tracking to object with obvious geometric transformation, achieving stable tracking under the condition that changing of light is large, and being good in effectiveness and robustness.

Description

technical field [0001] The invention relates to a video image tracking method, in particular to a dual model-based particle filter video image tracking method. Background technique [0002] In recent years, many algorithms use the feature covariance matrix as the regional characteristics to describe the image, and use the particle filter method to use a group of random samples with weights to represent the current density of the state to achieve target tracking. And affine transformation is used to describe the apparent change of the target. However, there is no more robust algorithm for objects with obvious geometric deformation, or when the object undergoes strong illumination changes. Contents of the invention [0003] The object of the present invention is to provide a particle filter video image tracking method based on dual models. This method not only achieves stable tracking for targets with obvious geometric deformation, but also can achieve stable tracking unde...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/20
Inventor 谢英红韩晓微何友国
Owner SHENYANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com