Automatic segmenting and tracking method of multiple-video moving target

A moving target, automatic segmentation technology, applied in image analysis, image data processing, instruments and other directions, can solve the problems of not meeting the real-time requirements of applications, environmental changes and noise sensitivity, poor algorithm versatility, etc., to improve the versatility and adaptability. performance, reduce the amount of calculation, and improve the accuracy

Inactive Publication Date: 2009-09-09
JIANGSU YINHE ELECTRONICS
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Video object tracking is based on the automatic segmentation of video moving objects. At present, the real-time automatic segmentation and tracking methods for multiple video moving objects have the following defects: poor robustness of the algorithm, sensitive to environmental changes and noise; poor versatility of the algorithm, satisfying It does not meet the real-time requirements of the application; when there are multiple moving targets in the video and occlusion, splitting and other behaviors occur, the stability and accuracy of its segmentation and tracking need to be further improved

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
  • Automatic segmenting and tracking method of multiple-video moving target
  • Automatic segmenting and tracking method of multiple-video moving target
  • Automatic segmenting and tracking method of multiple-video moving target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0028] Such as figure 1 Shown, the automatic segmentation and tracking method of multi-video moving target of the present invention, its steps are:

[0029] 1) input video image;

[0030] 2) Adaptive background modeling, the steps are:

[0031] Using the method of analyzing difference and accumulating dynamic matrix to determine whether a certain pixel belongs to the foreground or background, and determine the update model of the background; set M frame video sequence f(x, y, t 1 ), f(x, y, t 2 ),...,f(x,y,t M ), take f(x, y, t 1 ) as the reference image, and then take the k-rth frame image f(x, y, t k-r ) is the reference frame for calculating the difference accumulation image, then the current frame f(x, y, t k ) with the reference frame f(x, y, t k-r ) between the difference image F(x,y,t kr )for

[0032] F ...

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 automatic segmenting and tracking method of a multiple-video moving target, which can realize real-time automatic segmentation and accurate tracking of a plurality of video moving targets under static background and comprises the following steps: firstly, inputting a video image; secondly, performing the self-adaptive background modeling; thirdly, performing the airspace filtering to a background difference image; fourthly, performing the self-adaptive real-time threshold value and extracting the moving target outline; fifthly, getting the moving target mass center and marking the mass center; and sixthly, tracking the moving targets. The automatic segmenting and tracking method is mainly applied to the substrate video processing technique based on the video research and the video monitoring of the content.

Description

technical field [0001] The invention relates to a segmentation and tracking method of video moving objects, in particular to an automatic segmentation and tracking method of multiple video moving objects. Background technique [0002] Moving object tracking refers to calculating the two-dimensional position coordinates of the target on each frame of image by analyzing the image sequence obtained after motion detection and moving object segmentation processing, and according to different eigenvalues, different frames in the image sequence The same motion target is associated to obtain a complete motion track. Moving object tracking can not only provide the trajectory of the monitored object, but also provide a reliable data source for many traffic parameters and traffic events. Therefore, video object tracking has broad application prospects in the military field, intelligent video surveillance, intelligent transportation, medical diagnosis and other fields. [0003] Typica...

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): G06T7/20G06T5/00G06T7/12G06T7/136G06T7/155G06T7/66
Inventor 李银伢吴建明
Owner JIANGSU YINHE ELECTRONICS
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