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

Visual object tracking method based on particle filter of triple particles

A technology of particle filtering and target tracking, which is applied in image data processing, instrumentation, computing, etc., and can solve problems such as tracking target loss

Inactive Publication Date: 2012-09-12
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the tracking target is lost when the size of the target image changes in the particle filter target tracking algorithm, and to provide a particle filter visual target tracking method based on triple particles

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
  • Visual object tracking method based on particle filter of triple particles
  • Visual object tracking method based on particle filter of triple particles
  • Visual object tracking method based on particle filter of triple particles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] 1. Determine the target position, determine the target range and target center according to the moving target detection result, and generate the target color histogram Ch_prior as the target prior value. refer to image 3 , the rectangle box in the figure is the determined target (car) range; refer to Figure 4 , the picture shows the target color histogram as the target prior value.

[0060] 2. Generate the initial particle set, according to the prior distribution p(x 0 ), p(x 0 ) is image 3 The position of the rectangular frame containing the target information in , generating three sets of initial particle sets with The total number of particles is n=100, the initial state of the particles is the initial coordinates of the particles, and the initial position coordinates of each particle are consistent with the initial midpoint coordinates of the target, which is (624, 210) in this example, and the initial weight of each particle is The number of particles...

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 present invention belongs to a mobile object visual tracking technology of a mechanical visual field to solve a problem of missing a tracked object resulted from a size change of an object image in an object tracking of a particle filter. Provided is a visual object tracking method based on a particle filter of triple particles. Specifically an improvement reflects in tracking an object using three groups of particles in the particle filter, wherein the differences among the three groups of particles are the difference in the number and the form of contained pixels, and parameters of three groups of particle transfer models are set differently in a process of a state transfer of particles. When a distance between the tracked object and a shooting lens is changed resulting in the size change of the object image, at least one group of the three groups of particles have a larger weight so that the group of particles can describe the tracked object more accurately. Thereby, the method in the invention can reduce a tracking error and enhance a tracking precision.

Description

technical field [0001] The invention belongs to the technical field of robot autonomous navigation and intelligent monitoring of machine vision for visual tracking of moving targets. Background technique [0002] Moving target visual tracking is an important research direction in the field of robot autonomous navigation and intelligent monitoring of machine vision, and has broad potential application prospects. [0003] Moving object tracking has become an important research topic in machine vision. It has been widely used in many fields such as robot navigation, intelligent monitoring, video compression, human-computer interaction, and virtual reality. Many algorithms have been proposed in the field of visual tracking, such as particle filter tracking algorithm, target tracking algorithm based on neural network, and target tracking algorithm based on mean shift. The invention is aimed at the moving target tracking of the particle filter algorithm. [0004] For the partic...

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 孙启湲李刘生马磊刘俊麟
Owner TIANJIN UNIVERSITY OF TECHNOLOGY
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