Target tracking method based on quality and similarity evaluation online template updating

A technology for target tracking and template updating, applied in character and pattern recognition, biological neural network models, image data processing, etc., can solve problems such as fusion and template update features, and achieve improved robustness, better multi-scale estimation, and reduced information Effect

Pending Publication Date: 2022-04-19
YANSHAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0021] The technical problem to be solved by the present invention is to provide a target tracking method for online template update based on quality and similarity evaluation, so as to overcome the existing problems of template update and feature fusion

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
  • Target tracking method based on quality and similarity evaluation online template updating
  • Target tracking method based on quality and similarity evaluation online template updating
  • Target tracking method based on quality and similarity evaluation online template updating

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Below in conjunction with embodiment the present invention is described in further detail:

[0055] Such as image 3 As shown, the present invention provides a kind of object tracking method based on quality and similarity assessment online template update, comprising the following steps:

[0056] S1. Augment the initial template frame to generate N incremental templates Create a template pool of size M, as follows:

[0057] Present hardware can adopt GPU (graphics processing unit) to carry out accelerated calculation, what the present invention uses is that computer hardware devices such as GPU process image, and initial moment t is processed by target tracking module 0 Carry out data augmentation on the video images at each moment, perform rotation, translation, scale transformation, and inversion operations on a given target according to the target tracking task, obtain templates of different poses of the target, and then store the templates in a template pool 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 a target tracking method based on quality and similarity evaluation online template updating. The target tracking method comprises the following steps that S1, an initial template frame is augmented to generate N incremental templates, and a template pool with the size being M is established; s2, performing feature extraction on the template frame and the search frame through a target tracking module, performing convolution response to obtain a response score chart, and performing quality evaluation on a current new template according to a quality evaluation index; s3, judging the similarity between the template passing the quality evaluation and the template in the template pool through the cosine similarity, and judging whether a new template needs to be added into the template pool or not; s4, fusing the templates in the template pool through different weights of the templates to obtain a final template at the moment ti; and S5, carrying out convolution on a feature map obtained through feature extraction of the template frame and the search frame and a cavity convolution layer with different synchronization lengths and length-width ratios, and then carrying out feature fusion.

Description

technical field [0001] The invention relates to a video image processing technology, in particular to a target tracking method for online template update based on quality and similarity evaluation. Background technique [0002] At present, the application range of artificial intelligence technology is getting wider and wider, and it has attracted wide attention from all walks of life. As one of the most important branches of artificial intelligence technology, target tracking is also developing very rapidly. The main task of target tracking is to detect the initial position and size of the target position and lock the target so that it does not get lost in the field of view. With the continuous development of the field of computer vision, higher requirements are put forward for video processing technology, and the target tracking technology is also highly valued. Target tracking has a wide application prospect. [0003] Target tracking refers to the position and size inform...

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): G06T7/246G06V10/75G06K9/62G06N3/04
CPCG06T7/251G06N3/045
Inventor 李雅倩赵明肖存军李海滨张文明
Owner YANSHAN 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