Method for realizing multi-target tracking by using video segmentation and particle filter

A multi-target tracking and video segmentation technology, applied in the field of control, can solve the problems of high similarity and difficulty in accurately detecting targets, and achieve the effect of slowing down the calculation speed, realizing motion tracking, and fast calculation speed

Inactive Publication Date: 2010-09-22
ZHEJIANG UNIV
View PDF0 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to changes in ambient light brightness and shadows, high similarity between target features and environmental features, mutual occlusion between targets, and crossing of trajectories, it is difficult to accurately detect the tracked target
Secondly, the correlation inference and tracking of multiple target data require real-time performance, which poses a huge challenge to the multi-target tracking technology.

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
  • Method for realizing multi-target tracking by using video segmentation and particle filter
  • Method for realizing multi-target tracking by using video segmentation and particle filter
  • Method for realizing multi-target tracking by using video segmentation and particle filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The principle of this invention using video segmentation and particle filter to realize multi-target tracking method is: input video data carrying target information and target environment information, then use the model to describe the background, shadow and target features in the video, and use the space The potential functions of the domain and time domain describe their respective degrees of correlation in space and time, and segment the background, shadow, and target in the video data. After removing the background and shadow areas, the centers of the remaining limited areas are used as circle points, and the area 1.5 to 2 times the distance from the center to the farthest pixel point is the radius, and a limited search area A is determined i , calculate the predicted position a of object j j with A i The distance from the center, the one with the closest distance is the search area of ​​object j as A i ; If the distances are the same, determine first to predict ...

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 method for realizing multi-target tracking by using video segmentation and particle filter. The method comprises the steps of establishment of a system model, establishment of a target motion model and a color model, video segmentation and the like. The method realizes the multi-target tracking and greatly increases the tracking speed and precision by combining the respective advantages of the video segmentation and the particle filter and realizes the multi-target motion tracking under a shielding condition by fully utilizing the correlation degree between the measurement and the target.

Description

technical field [0001] The invention relates to the field of control technology, in particular to a method for realizing multi-target tracking by using video segmentation and particle filter. Background technique [0002] Multi-target tracking refers to the use of one or more sensors (radar, sonar, video camera) to measure and estimate the motion state of multiple tracked targets, and assign estimated values ​​based on the probability of each moving target. information to realize the tracking of multiple moving targets. [0003] Multi-target tracking mainly includes moving target modeling, tracking filtering and prediction algorithm, formation of tracking gate, data association, tracking maintenance, tracking start and tracking end, etc. [0004] Object tracking is based on the motion model of the object. When establishing a target motion model, it must conform to the actual target motion and be convenient for mathematical processing. If the selection is not accurate, it w...

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): G06T7/20H04N5/14
Inventor 陈宏文钟凡彭群生
Owner ZHEJIANG UNIV
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