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

Anti-interference real-time tracking method for profile of object

A contour tracking and object technology, which is applied to color TV parts, TV system parts, image data processing, etc., can solve the problems of being greatly affected by noise and slow speed, and achieves speed resistance to noise interference and fast speed Effect

Inactive Publication Date: 2009-09-23
ZHEJIANG UNIV +1
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of being greatly affected by noise and slow speed in the process of object contour tracking, the purpose of the present invention is to provide an anti-interference real-time contour tracking method

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
  • Anti-interference real-time tracking method for profile of object
  • Anti-interference real-time tracking method for profile of object
  • Anti-interference real-time tracking method for profile of object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The present invention comprises following two major steps, as shown in accompanying drawing:

[0012] (1) Perform color analysis on the RGB color space and the normalized RGB color space, extract the foreground information of the object, and exclude the influence of shadows, lighting and noise.

[0013] (2) A fast curve evolution method based on level set, so as to track the outline of the target object in real time.

[0014] Specific steps are as follows:

[0015] 1. Extract foreground information, eliminate the influence of shadow, light and noise, and use it in the initialization process to speed up the curve evolution: set F t Indicates the tth frame in the video, F t (x, y) represents the pixel on the (x, y) coordinates in the frame, and B represents the reference frame as the background; due to the change of illumination, the background always changes with time; thus a more reliable Reference frame to overcome this problem; this method uses the first few still ...

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 an anti-interference real-time tracking method for the profile of an object. The real-time profile tracking in video monitoring has two problems, one is slower speed and the other is influence of noise, shadow and the like. Compared with the traditional level set method, the anti-interference real-time tracking method avoids high computational complexity of repeatedly solving partial differential equation. In addition, the information of color is analyzed on an RGB color space, thus eliminating the shadow and noise in the process of foreground extraction. Different from the traditional method, the process does not set a large amount of threshold values by hand. Further, the anti-interference real-time tracking method utilizes the process of foreground extraction to obtain the approximate position of the profile of the tracked object. The step is automatically completed similarly, thus greatly reducing the time consumption of profile evolution in the level set method. Based on the method, the real-time video monitoring system is realized, and good effect is obtained under the indoor monitoring environment.

Description

technical field [0001] The invention relates to real-time computer vision technology, in particular to an anti-interference real-time object contour tracking method. Background technique [0002] Object tracking is one of the key issues in applications such as video surveillance, video conferencing, etc. Some current object-oriented video coding standards, such as MPEG4, MPEG7, etc., also need to extract objects in the video before the coding stage. A large number of researchers are devoting themselves to the study of methods to solve this problem. There are currently many different ways to describe the tracked object, such as curvature, color, texture, contour, etc. Among these methods, contour is one of the most commonly used descriptors. [0003] Tracking contours is more difficult. Early methods such as the active contour method require many manual initialization operations. Recently, level set methods have gained more attention in object tracking. Many methods bas...

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): H04N5/14G06T7/20H04N7/18
Inventor 陈纯洪朝群卜佳俊杨智刘毅
Owner ZHEJIANG 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