Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An Adaptive Self-Correcting Target Tracking Method

A target tracking, adaptive technology, applied in the field of robust target tracking

Active Publication Date: 2021-04-02
贵州宇鹏科技有限责任公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an adaptive self-correcting target tracking method to solve the problem of tracking loss caused by environment and target changes in the long-term tracking process, and on this basis, a tracking framework capable of self-correction is proposed , can overcome the deficiencies of the existing technology

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
  • An Adaptive Self-Correcting Target Tracking Method
  • An Adaptive Self-Correcting Target Tracking Method
  • An Adaptive Self-Correcting Target Tracking Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] as follows figure 1 As shown, an adaptive self-correcting target tracking method is characterized in that the method divides the interference factors in target tracking into environmental factors and target factors, and proposes a static appearance model and an adaptive self-adaptive model according to the classified interference factors. Appearance model, then denoise the static appearance model and adaptive appearance model and then fuse them, and finally improve the accuracy of tracking through a self-correcting tracking framework, which includes static modules, adaptive modules, denoising modules and target tracking Algorithm module;

[0019] The static module can always retain the initial information of the target, which is a set composed of all matching relationships between the static appearance model of the initial frame target and the static appearance model of the current frame target;

[0020] The adaptive module updates each frame to adapt to the change of ...

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 adaptive and self-correcting target tracking method. In the method, interference factors during target tracking are divided into an environment factor and a target itself factor. According to the classified interference factors, a static appearance model and an adaptive appearance model are provided. Denoising is performed on the static appearance model and the adaptive appearance model and the two models are fused. Finally, through a self-correcting tracking framework, tracking accuracy is increased. A static module, an adaptive module, a denoising module and a target tracking algorithm module are included. By using the method of the invention, a tracking loss problem caused by environment and target changes during a long-term tracking process is solved, and based on that, the self-correcting tracking framework is provided.

Description

technical field [0001] The invention relates to an adaptive self-correcting target tracking method, which belongs to the technical field of robust target tracking. Background technique [0002] Target tracking refers to estimating the trajectory of a specified target in a video image sequence. In 2012, ZdenekK et al. proposed a target tracking algorithm that combines tracking, detection, and learning [1]. During the tracking process, the target The observed data will be used to train a classifier. At the same time, the algorithm uses an optical flow-based tracker to continuously correct the detection results of the classifier. While detecting, TLD (TLD: Training-Learning Detection, training-learning detection ) uses a sample screening strategy based on structural constraints to ensure that the samples in the training phase of the classifier are close enough to the real situation during the tracking process. Although TLD as a single target tracking algorithm can solve the pr...

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): G06T7/207
CPCG06T2207/10016G06T7/207
Inventor 王高峰卫保国高涛
Owner 贵州宇鹏科技有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com