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

A Moving Object Tracking and Extraction Algorithm Unaffected by Obstacles

A technology for moving objects and obstacles, applied in the field of computer vision, can solve problems such as interruption of moving object tracking, and achieve good applicability and practicability

Active Publication Date: 2018-04-06
HANGZHOU GUOCE MAP TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional methods such as background difference method and continuous frame difference method can achieve a relatively good tracking effect when the camera is fixed, but under the influence of obstacles, the tracking of moving objects is usually interrupted
[0003] At present, the methods proposed by many researchers for tracking moving objects, such as optical flow method, matching method based on SIFT feature points, Mean-Shift method and particle filter method, cannot solve the problem of encountering obstacles in tracking.

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 Object Tracking and Extraction Algorithm Unaffected by Obstacles
  • A Moving Object Tracking and Extraction Algorithm Unaffected by Obstacles
  • A Moving Object Tracking and Extraction Algorithm Unaffected by Obstacles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In actual operation, the SIFT algorithm is used to extract feature points for each image frame. And the feature points are described by the direction gradient histogram of the pixels around the feature points.

[0034] In actual operation, after the feature histogram of each feature point is obtained, the distance between the feature histograms of two feature points is calculated by the Bhattacharyian distance, that is, the similarity of the two feature points. The formula for calculating the Barrett's distance is as follows:

[0035]

[0036] where p and q represent two normalized histograms respectively.

[0037] Assuming that N feature points with the best stability are retained among the feature points extracted in each frame, the total number of extracted feature points is N×(T+1).

[0038] After calculating the similarity between all the feature points of the current frame and all the feature points of the previous frame, a basic benefit matrix can be establi...

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 moving object extracting and tracking algorithm capable of being not affected by obstacles. The algorithm can provide detailed motion information of every part of a target object when tracking the target object. The algorithm includes extracting feature points of continuous video image frames acquired by a camera, building a matching matrix for the obtained feature points, converting the moving object extracting and tracking into an assignment problem, obtaining the matching relationship of the feature points by solving the assignment problem and achieving the moving object extracting and tracking. According to the moving object extracting and tracking algorithm capable of being not affected by the obstacles, multiple image frames are processed during the matching, so that the tracking is not affected when a moving object is blocked by obstacles.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a moving object tracking and extraction algorithm not affected by obstacles. Background technique [0002] The tracking of moving objects in the video captured by the camera is a hot spot in the field of computer vision research, and has broad application prospects in robot vision, video surveillance and other systems. Traditional methods such as background difference method and continuous frame difference method can achieve a relatively good tracking effect when the camera is fixed, but under the influence of obstacles, the tracking of moving objects is usually interrupted. [0003] At present, the methods proposed by many researchers for tracking moving objects, such as optical flow method, matching method based on SIFT feature points, Mean-Shift method and particle filter method, cannot solve the problem of obstacles encountered in tracking. Moving object tracking and...

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): G06T7/254G06T7/292
CPCG06T7/254G06T7/292G06T2207/10016
Inventor 李竹
Owner HANGZHOU GUOCE MAP TECH
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