Video-based moving target detection and tracking method and system

A moving target and video technology, applied in image data processing, instrumentation, computing, etc., can solve the problems of consuming large system resources, unable to distinguish the shadow of moving objects well, and achieve the goal of improving robustness and shadow detection effect. Effect

Pending Publication Date: 2021-01-05
深圳市国鑫恒运信息安全有限公司
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the most commonly used method is the mixed Gaussian background modeling method, and the mixed Gaussian model (GMM) has the following disadvantages for background modeling: (1) All Gaussian models of each frame image remain the same fixed number of Gaussian models, Can consume a lot of system resources while processing
(2) The shadows produced by moving objects cannot be distinguished well

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
  • Video-based moving target detection and tracking method and system
  • Video-based moving target detection and tracking method and system
  • Video-based moving target detection and tracking method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0128] The preferred embodiments of the present invention will be further described in detail below.

[0129] Such as figure 1 As shown, a video-based moving target detection and tracking method, which includes: processing the input video, using an improved Gaussian mixture model to separate the foreground and background of each frame of the image, and first detecting the foreground The image is processed by median filtering to remove noise, and then the morphological expansion operation is performed to remove the holes in the image to improve the accuracy of target detection, and then combined with the meanshift algorithm to realize the tracking of the target.

[0130] The mixed Gaussian background modeling method is a statistical background subtraction method based on parameter estimation. K different Gaussian functions are used to represent the value of each pixel in the video sequence, and then the K Gaussian functions are prioritized. , select the first B Gaussian functi...

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 provides a video-based moving target detection and tracking method and system. The method comprises steps of outputting a video; carrying out foreground and background separation on eachframe of image by using an improved Gaussian mixture model; carrying out median filtering processing on the foreground image obtained after detection, and removing noise; morphological expansion operation being carried out to remove holes generated in the image; and a mean shift algorithm being adopted to track the target. The method is advantaged in that robustness of the environment is improved, the shadow detection effect is improved, the boundary of the foreground pixel region is expanded, the size of the foreground pixel region is increased, and holes are reduced.

Description

technical field [0001] The invention belongs to the technical field of moving target detection, and in particular relates to a video-based moving target detection and tracking method and system. Background technique [0002] In recent years, with the development of image processing technology, the target detection and tracking system based on machine vision has been widely used. To date, many motion and change detection algorithms have been developed that perform well in certain types of video, but most of them are sensitive to sudden lighting changes, environmental conditions, background / camera motion, shadows, etc. There is no current algorithm that can solve all problems of video-based multi-object detection well at the same time. Detecting the actual shape of a moving object becomes difficult due to various challenges such as dynamic scene changes, lighting changes, presence of shadows, etc. Frame difference method, optical flow method, and background subtraction metho...

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): G06T7/215G06T7/194G06T7/13G06T7/136G06T7/66G06T7/90G06T5/30
CPCG06T5/30G06T2207/10016G06T2207/20032G06T2207/20081G06T7/13G06T7/136G06T7/194G06T7/215G06T7/66G06T7/90
Inventor 罗珊
Owner 深圳市国鑫恒运信息安全有限公司
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