Correlation filtering tracking method based on space-time perception and multi-peak response

A correlation filter and correlation filter technology, applied in the field of target tracking, can solve the problem of poor tracking effect of target tracking algorithm, and achieve the effect of ensuring the diversity of sample information, avoiding error model update, and strong robustness.

Pending Publication Date: 2021-02-05
GUILIN UNIV OF ELECTRONIC TECH
View PDF12 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] What the present invention aims to solve is the problem that existing target tracking algorithms have poor tracking effects, and provides a correlation filter tracking method based on spatio-temporal perception and multi-peak response

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
  • Correlation filtering tracking method based on space-time perception and multi-peak response
  • Correlation filtering tracking method based on space-time perception and multi-peak response
  • Correlation filtering tracking method based on space-time perception and multi-peak response

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific examples.

[0039] A correlation filter tracking method based on spatio-temporal perception and multi-peak response, such as figure 1 As shown, its specific steps are as follows:

[0040] Step 1. Determine the position and size of the tracking target on the first frame image of the tracking video.

[0041] Step 2. Use the position and size of the tracking target determined in the t-1th frame image to train the target prediction model for the tth frame image. t=2,3,....

[0042] Step 2.1. First, based on the position and size of the tracking target determined based on the t-1th frame image, take the tracking target position as the center, and take the tracking target size as the cell size, and select the t-1th frame image containing Candidate regions with more than 2 cells. Then, ...

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 a correlation filtering tracking method based on space-time perception and multi-peak response. The method comprises the following steps: firstly, determining the position andsize of a tracking target on a first frame image of a tracking video; training a target prediction model of the tth frame of image by using the position and size of the tracking target determined by the t-1th frame of image; and finally, determining the position and size of the tracking target on the t-th frame of image by using the target prediction model of the t-th frame of image. According tothe method, illumination change and attitude change can occur around the target, continuous and robust tracking can be achieved, wrong updating of the model cannot be affected due to the fact that thetarget is shielded or disturbed by similar objects, the model is always kept in a good state, and the target tracking accuracy rate is high; and meanwhile, real-time data can be quickly processed inthe tracking process, so that the method can be applied to actual life.

Description

technical field [0001] The invention relates to the technical field of target tracking, in particular to a correlation filter tracking method based on spatio-temporal perception and multi-peak response. Background technique [0002] Object tracking is one of the research hotspots in the field of computer vision, and it has a wide range of applications in the fields of face recognition, robot vision and intelligent monitoring. The target tracking method based on deep learning gradually shows robust tracking performance due to the powerful feature learning ability of the deep neural network, but this kind of method has a large amount of calculation, the algorithm tracking efficiency is reduced, and it cannot meet the real-time requirements, and it requires hardware resources. High, not suitable for application in engineering products, so deep learning can only use part of the network and continuous optimization to achieve real-time results. The discriminative tracking method ...

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): G06K9/34G06K9/46G06K9/62G06N3/04
CPCG06V10/267G06V10/56G06N3/045G06F18/214
Inventor 牛军浩王文胜苏金操骆薇羽许川佩朱爱军陈涛殷贤华张本鑫
Owner GUILIN UNIV OF ELECTRONIC TECH
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