Anchor-frame-free target tracking method based on contour estimation

A target tracking and contouring technology, applied in the field of computer vision, can solve problems such as difficult to deal with target changes and environmental changes

Active Publication Date: 2021-09-10
WUHAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The determination of hyperparameters requires a lot of professional knowledge and continuous tuning, and it is difficult to deal with complex target changes and environmental changes that may occur during the tracking process

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
  • Anchor-frame-free target tracking method based on contour estimation
  • Anchor-frame-free target tracking method based on contour estimation
  • Anchor-frame-free target tracking method based on contour estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention and are not intended to limit it. this invention.

[0046] The main idea of ​​the anchor-free target tracking algorithm based on contour estimation is to use the contour estimation network to output the rough outline of the target. Compared with using a rectangular frame aligned with the coordinate axes to describe the target state, describing the target state by using the outline outline can provide more target state information to meet the needs of different tracking scenarios; the target outline obtained by using the outline estimation network To update the target template features, the background information in the target template features i...

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 anchor-frame-free target tracking method based on contour estimation. According to a contour estimation network provided by the invention, the rough contour of a target object can be directly solved without presetting an anchor frame according to priori knowledge, and compared with a rectangular frame, the target contour can describe the target state more accurately; target template features are updated by using the target contour solved by the contour estimation network, so that background information in the target template features is reduced, and more accurate target information is provided for subsequent information embedding. Under extreme environments such as illumination variation, motion blur, rotation in a plane and target viewing angle exceeding, the method can still keep high precision.

Description

technical field [0001] The invention belongs to the technical field of computer vision, specifically relates to the technical field of digital image target tracking, in particular to an anchor frame-free target tracking method based on outline estimation. Background technique [0002] Object tracking refers to the position and size of any object in the first frame of a given video, and the state information of the object in the subsequent video sequence is solved. The result of target tracking is used as the input of subsequent video target recognition, scene analysis and understanding, and assumes the role of connecting the preceding and the following in the computer vision system. For decades, many excellent algorithms have emerged in the field of target tracking, and more and more researchers have begun to devote themselves to the research of target tracking algorithms, making the performance of target tracking algorithms better and better, and more widely applied to real...

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): G06T7/246G06T7/207G06T7/13G06K9/62G06N3/04
CPCG06T7/246G06T7/207G06T7/13G06T2207/10016G06T2207/20081G06T2207/20084G06N3/045G06F18/241
Inventor 李晶洪燕姚博文马金燕刘天鹏常军
Owner WUHAN 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