A Covariance Matrix Tracking Method Based on Gray Level Constraint

A covariance matrix and grayscale technology, applied in the field of image detection, can solve the problems of inability to obtain tracking results, weak feature description, etc., and achieve the effect of reducing the amount of calculation, high accuracy, and accurate target positioning.

Inactive Publication Date: 2011-12-14
TIANJIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the feature description of the target by the kernel function histogram in the Mean shift method is relatively weak, it is impossible to achieve ideal tracking when tracking the target on a grayscale image or an image with less texture information, especially when the color of the target and the background are similar. result

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 Covariance Matrix Tracking Method Based on Gray Level Constraint
  • A Covariance Matrix Tracking Method Based on Gray Level Constraint
  • A Covariance Matrix Tracking Method Based on Gray Level Constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The invention adds a gray scale constraint method on the basis of covariance matrix tracking to each frame image in the video sequence. Specifically, the present invention uses the covariance matrix to describe the tracking target, and utilizes the gray scale constraints to screen out the candidate targets, and then uses the difference value of the covariance matrix to judge the matching degree between the candidate target and the tracking target, and finally compares the tracking target according to the matching degree. Track the target for positioning.

[0021] The present invention is a covariance matrix tracking method based on gray scale constraints, figure 1 It is an overall flow chart, specifically including the following steps:

[0022] 1. Select the tracking target

[0023] Such as figure 2 Select a target in the image as shown. figure 2 The rectangle area with solid line in the middle is the initial position of the selected tracked target, the length is ...

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 belongs to the technical field of image detection, and relates to a covariance matrix tracking method based on gray scale constraints, comprising the following steps: for an image, a rectangular area is selected as a target model for tracking; Gray value; extract the eigenvector of each point of the target model; calculate the covariance matrix of the target model; in subsequent frames, the length and width of the target model are expanded to obtain the tracking window, and the candidate target is selected to check whether the gray value is satisfied. degree constraint; for a candidate target that satisfies the gray level constraint, calculate the difference value between it and the covariance matrix of the target model, and the candidate target area with the smallest difference value is the position of the tracked target. The invention has the advantages of more accurate target positioning, faster tracking speed and stronger real-time performance.

Description

technical field [0001] The invention belongs to the technical field of image detection and relates to a moving target tracking method which can be used for real-time video monitoring. Background technique [0002] The background technology involved in the present invention has: [0003] (1) Covariance matrix tracking algorithm (see literature [1]): The covariance matrix tracking algorithm finds the characteristics of the target area frame by frame from the input video sequence, and uses the covariance matrix to model the target features, and then according to the covariance matrix to find the best feature-matching region. This method achieves the fusion of multiple features of the target very well, and has strong adaptability to rotation, scaling and brightness changes. [0004] (2) Mean shift algorithm (see literature [2]): Mean shift algorithm is a non-parametric probability density estimation algorithm, which generally uses a histogram to model the target, and then meas...

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): G06T7/00
Inventor 操晓春邓超张炜王秀锦李雪威
Owner TIANJIN UNIV
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