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

Anti-shadow and anti-covering method for detecting and tracing multiple moving targets

A multi-moving target and shadow technology, applied in the field of multi-moving target detection and tracking, can solve problems such as impact, achieve the effects of small calculation, overcome noise and shadow problems, and meet real-time requirements

Inactive Publication Date: 2015-04-22
GUIZHOU MODERN LOGISTICS ENG TECH RES
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a multi-moving target detection and tracking method that is resistant to shadows and occlusions. The technical problems it solves are: (1) the influence of shadows and various noises in the moving target detection stage

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-shadow and anti-covering method for detecting and tracing multiple moving targets
  • Anti-shadow and anti-covering method for detecting and tracing multiple moving targets
  • Anti-shadow and anti-covering method for detecting and tracing multiple moving targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Combine below Figure 1-4 , the present invention is further described:

[0021] Such as figure 1 As shown, the three-frame difference processing based on the 8-neighborhood summation is performed on the continuous 3-frame image sequence, and the video image sequence is divided into the target area and the non-target area, and then the mixed Gaussian background is built on the video image using the classification floating update strategy. mold. In the shadow detection stage, the method based on the combination of texture gradient and color feature invariant is adopted, and the classification tracking strategy is adopted in the object tracking stage.

[0022] Such as figure 2 As shown, the target foreground pixel set can be obtained by mixing Gaussian background modeling, the final shadow candidate area can be obtained by chromaticity estimation and brightness estimation, and then the preliminary processing of shadow detection is completed through spatial correction,...

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 an anti-shadow and anti-covering method for detecting and tracing multiple moving targets and belongs to the technical field of image processing. The method comprises the following steps: performing mixed gauss based background modeling by combining a classified floating strategy; segmenting a moving target prospect by using a three-frame difference algorithm combining with an 8 neighborhood summation operation; adopting shadow detection with invariant texture gradient difference and color characteristics to mark a detected shadow to be red; eliminating a red shadow area at a target tracking stage; and performing multi-target tracing by adopting a strategy of combining Camshift and Kalman wave filtering. The anti-shadow and anti-covering method for detecting and tracing the multiple moving targets can be used for effectively detecting shadows of the moving targets, is small in calculated amount and high in real-time property, can effectively improve a 'cavity' phenomenon, has good stability for detecting the moving targets, and meanwhile can realize stable tracing of the moving targets in a shielding scene.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a multi-moving object detection and tracking method which is resistant to shadows and occlusions. Background technique [0002] Moving target tracking is one of the research hotspots of machine vision, and it is also the basis for in-depth analysis of video images. It has been successfully applied in the fields of intelligent security, transportation, and medical image analysis, but there are still many theoretical and application problems that need to be solved urgently. Including moving target occlusion, shadow removal and other issues. Moving target detection is to completely separate the moving foreground from the video image sequence, which is the key to subsequent target tracking. However, the influence of various noises needs to be fully considered during the detection process, and the shadow of the moving target is easily misdetected as the shadow of ...

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): G06T7/20G06T7/246
Inventor 李明涛罗明俊吴道鸿袁永红吴鹏
Owner GUIZHOU MODERN LOGISTICS ENG TECH RES
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