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

A Robust Target Tracking Method Based on Local Sparse Representation and Particle Swarm Optimization

A particle swarm optimization and target tracking technology, applied in the field of robust target tracking, which can solve the problems of occlusion, interference effects of similar objects in moving background, etc.

Active Publication Date: 2020-07-14
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to avoid the deficiencies of the existing technology, the present invention proposes a robust target tracking method based on local sparse representation and particle swarm optimization, which solves the problems of illumination changes, occlusion, deformation, and complex moving background similarities in the process of visual target tracking. Interfering effects of objects, etc.

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
  • A Robust Target Tracking Method Based on Local Sparse Representation and Particle Swarm Optimization
  • A Robust Target Tracking Method Based on Local Sparse Representation and Particle Swarm Optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will now be further described in conjunction with the embodiments and accompanying drawings:

[0045] Based on the determination of the target position in the first frame, the present invention firstly obtains several target templates by sampling near the initial frame target, and constructs a dictionary for sparse representation. Then, candidate target sampling is performed by particle filtering guided by the particle swarm optimization algorithm. Then the candidate target is sparsely represented, and the representation coefficient is obtained by solving. Finally, the optimal candidate target is obtained as the tracking result. The specific steps are as follows, and the process can refer to the accompanying drawings.

[0046] 1) Read the first frame of image data and the parameters [x, y, w, h] of the target in the first frame of image, where x, y represent the center position of the target, and w, h represent the width and height of the target....

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 relates to a local sparse representation and particle swarm optimization-based robust target tracking method. The method comprises the steps of firstly, performing sampling near an initial frame to obtain a plurality of template blocks, and constructing a dictionary used for sparse representation by utilizing local and structure information of a target; secondly, performing particle filtering on each frame after the initial frame to generate a plurality of particles, wherein each particle represents a candidate target; thirdly, performing sparse representation on each candidate target, and representing the fitness of each particle with a sparse representation coefficient obtained by solving; and finally, taking the particle with the highest fitness, namely, the candidate target with the highest fitness obtained by particle swarm optimization solving as a tracking result.

Description

technical field [0001] The invention belongs to a method for using digital images for target identification, and relates to a robust target tracking method based on local sparse representation and particle swarm optimization. Background technique [0002] Object tracking is a fundamental problem in the field of computer vision, and it has a wide range of applications, including video surveillance, behavior analysis, motion temporal analysis, and video retrieval. Target tracking is a challenging subject because targets will face problems such as illumination changes, occlusion, deformation, and complex moving backgrounds during the tracking process, which often lead to target loss and drift. [0003] In the past two years, the target tracking method based on the sparse representation theory has received great attention. This method transforms the target tracking problem into a sparse solution problem, and has achieved good results, providing a new solution idea for the target...

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 Patents(China)
IPC IPC(8): G06T7/246G06T7/277
CPCG06T7/20G06T2207/10016
Inventor 李映薛希哲胡晓华
Owner NORTHWESTERN POLYTECHNICAL 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