Correlation filtering target tracking method for occlusion

A target tracking and correlation filtering technology, applied in the fields of computer vision and pattern recognition, can solve problems such as deformation and target occlusion, and achieve the effect of less time-consuming

Active Publication Date: 2019-05-21
尚特杰电力科技有限公司
View PDF11 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] The technical problem of the present invention is to overcome the deficiencies of the existing technology, and propose a correlation filter target tracking method for occlusion, which has high tracking accuracy, good robustness, and the tracking speed meets real-time requirements, and can solve problems such as target occlusion and deformation

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 target tracking method for occlusion
  • Correlation filtering target tracking method for occlusion
  • Correlation filtering target tracking method for occlusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0065] like figure 1 As shown, the implementation steps of the present invention are as follows:

[0066] It is preferred to give a video sequence, give the position and size of the tracking target of the t-th frame, and then determine the target search area and extract features;

[0067] Then, in the target search area, the spatial perception weight map P and the color histogram-based target similarity weight map T are calculated respectively, and the weight map W of the t-th frame is obtained. t ;

[0068] Based on the obtained weight map W of the t-th frame t , the correlation filter of the t-th frame is trained;

[0069] According to the trained correlation filter of the t-th frame, the target response map of the t+1-th frame is calculated, and the target position of the t+1-th frame is calculated.

[0070] Find a high-confidence APSR strategy ...

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 a correlation filtering target tracking method for occlusion, which comprises the following steps of: step 1, for a section of tracked video sequence, giving the position andsize of a tracking target of a t-th frame, determining a search area, calculating characteristics, and calculating a weight map of the t-th frame; step 2, based on the obtained weight graph of the t frame, training a related filter of the t frame; step 3, calculating a target response graph of the (t + 1) th frame according to the trained related filter, and calculating a target position of the (t + 1) th frame; and step 4, on the basis of the (t + 1) th frame target position, obtaining a high-confidence APSR strategy, and determining whether the related filter of the t th frameis updated or not.

Description

technical field [0001] The invention relates to a correlation filtering target tracking method for occlusion, belonging to the fields of pattern recognition and computer vision. Background technique [0002] With the increasing development of computer vision, visual tracking has been widely used in many computer vision tasks, such as video surveillance, human-computer interaction, and unmanned perception systems. Given the true location of the object in the first frame, the tracker can locate the object of interest throughout the video sequence. Although visual tracking methods have made great progress, there are still many challenges, such as deformation, occlusion, out-of-view, scale change, in-plane rotation, etc. [1]. [0003] In recent years, discriminative class tracking methods have attracted great attention. The discriminative approach treats object tracking as a binary classification, i.e. the object and the background region in the video. Many discriminative met...

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): G06T7/246
Inventor 凌强汤峰李峰
Owner 尚特杰电力科技有限公司
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