A moving target tracking method based on a matrix low-rank representation theory

A moving target, low-rank representation technology, applied in image data processing, image analysis, instruments, etc., can solve problems such as tracking result drift, disappearance, and moving target loss

Inactive Publication Date: 2016-11-23
NANJING UNIV OF SCI & TECH
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to factors such as illumination changes, moving target shape changes, background changes, and moving targets being partially or completely occluded, for a given image sequence, the feature information on the moving target may disappear for a while and then reappear or even completely disappear
[0003] For existing moving target tracking methods, such as IVT method and L1T me

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 moving target tracking method based on a matrix low-rank representation theory
  • A moving target tracking method based on a matrix low-rank representation theory
  • A moving target tracking method based on a matrix low-rank representation theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] One, basic thought of the present invention

[0024] The present invention proposes a moving target tracking method based on matrix low-rank representation theory under the framework of particle filter theory, and its basic principle is:

[0025] First, the moving target observation matrix composed of image sequences is decomposed into a low-rank matrix representing the moving target and a sparse matrix representing the occlusion, the low-rank matrix is ​​used as the moving target model, the sparse matrix is ​​used as the target occlusion model, and the moving target model is used Establish the target observation probability optimization equation with the target occlusion model;

[0026] Then, use the optimization algorithm to solve the moving target model and the target occlusion model respectively;

[0027] Finally, the obtained moving target model and target occlusion model are substituted into the target observation probability optimization equation to calculate th...

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 brings forward a moving target tracking method based on a matrix low-rank representation theory in the framework of a particle filter theory. A moving target observation matrix composed of image sequences is decomposed into a low rank matrix representing a moving target and a sparse matrix representing shields; the low order matrix is used as a moving target model, and the sparse matrix is used as a target shielding model; a target observation probability optimization equation is established by using the moving target model and the target shielding model; the moving target model and the target shielding model are solved separately by using an optimization algorithm; and the moving target model and the target shielding model are substituted into the target observation probability optimization equation to calculate a moving target observation probability required by target tracking so as to achieve the tracking of a moving target. According to the invention, a problem of tracking drift and even target losing after the moving target is shielded is solved, thereby improving the anti-shielding ability of the moving target tracking. The moving target tracking method of the invention has high robustness.

Description

technical field [0001] The invention belongs to the technical field of computer vision processing, and in particular relates to a moving target tracking method based on matrix low-rank representation theory. Background technique [0002] When tracking a moving target, for a given video sequence, the moving target tracking method is to detect, extract, identify and track the moving target to obtain more accurate parameter information such as the position, speed, and acceleration of the target, and pass Further processing can realize the understanding of the behavior of the sports target, and then complete higher-level tasks. It can also be said that the matching of image features such as position, speed, shape, texture, and color is realized between consecutive image frames. Therefore, the key to the moving target tracking method is to establish the corresponding relationship between the candidate target and the reference target in each frame image. However, due to factors ...

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
IPC IPC(8): G06T7/20
Inventor 孔筱芳顾国华丁祺徐富元陈钱
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap