Twin candidate region generation network target tracking method based on attention mechanism

A candidate area, twin network technology, applied in the field of image processing, can solve the problems of tracking results deviating from the real target, weak discrimination ability, target drift, etc., to alleviate the target drift problem, high accuracy and robustness, and improve the discrimination ability. Effect

Active Publication Date: 2019-10-15
DALIAN UNIV OF TECH
View PDF5 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the tracking method based on the Siamese candidate region generation network is weak in discriminating the target foreground and the semantic

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
  • Twin candidate region generation network target tracking method based on attention mechanism
  • Twin candidate region generation network target tracking method based on attention mechanism
  • Twin candidate region generation network target tracking method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The specific implementation manners of the present invention will be further described below in conjunction with the technical solutions and accompanying drawings.

[0016] A network target tracking method based on twin candidate region generation based on attention mechanism, including the following steps:

[0017] In the first step, the Siamese network is used to extract the initial target template features and target search area features.

[0018] The Siamese neural network (Siamese network) is used to extract the convolutional features of the initial target template and the convolutional features of the target search area. The Siamese network mainly contains two branches with the same structure, that is, the two branches are the same convolutional neural network model, which has the characteristic of weight sharing. The initial target template and the target search area are simultaneously fed into the Siamese network to obtain the corresponding convolutional featur...

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 twin candidate region generation network target tracking method based on an attention mechanism, and belongs to the technical field of image processing. The twin candidate region generation network target tracking method comprises the following specific steps: 1, extracting initial target template features and target search region features by using a twin network; 2, constructing a spatial attention network to enhance a target template foreground and suppress a semantic background; 3, constructing a channel attention network to activate strong correlation characteristics of the target template, and eliminating redundancy; and 4, constructing a candidate region generation network to realize multi-scale target tracking. The twin candidate region generation networktarget tracking method has the advantages that the attention mechanism is used for constructing the adaptive target appearance feature model; the target foreground is enhanced; the semantic backgroundis inhibited; and the difference features of the target foreground and the interference background are highlighted; redundant information is removed, so that the efficient appearance feature expression capacity is obtained, and the target drifting problem is effectively relieved.

Description

technical field [0001] The invention relates to a network target tracking method for generating twin candidate regions based on an attention mechanism, and belongs to the technical field of image processing. Background technique [0002] With the improvement of computer hardware capabilities and the advent of the era of artificial intelligence, deep neural networks are widely used in the field of target tracking due to their efficient data computing capabilities and feature extraction capabilities. The tracking method based on the convolutional neural network can significantly improve the accuracy and success rate of the tracking results, showing the good performance of the target tracking method. However, the online update process and candidate sample generation process of convolutional neural network consume a lot of time, which greatly limits the running speed of tracking methods. In order to achieve real-time tracking speed, the twin network abandons the online update p...

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
IPC IPC(8): G06T7/246G06T7/194G06T5/00G06K9/62
CPCG06T7/246G06T5/001G06T7/194G06T2207/10016G06T2207/20081G06T2207/20084G06F18/24
Inventor 王凡胡小鹏徐丽娟李婧婷
Owner DALIAN UNIV OF 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