Hierarchical Attention Siamese Network for Thermal Infrared Target Tracking

Thermal infrared (TIR) target tracking is an important topic in the computer vision area. The TIR images are not affected by ambient light and have strong environmental adaptability, making them widely used in battlefield perception, video surveillance, and assisted driving. However, TIR target trac...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement 2024, Vol.73, p.1-11
Main Authors: Yuan, Di, Liao, Donghai, Huang, Feng, Qiu, Zhaobing, Shu, Xiu, Tian, Chunwei, Liu, Qiao
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Attention
Attention mechanism
Computer vision
Convolution
Feature extraction
feature fusion
Image reconstruction
Infrared imagery
Infrared tracking
Interference
Multilayers
Siamese network
Support vector machines
Target tracking
thermal infrared (TIR) target tracking
Training
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Thermal infrared (TIR) target tracking is an important topic in the computer vision area. The TIR images are not affected by ambient light and have strong environmental adaptability, making them widely used in battlefield perception, video surveillance, and assisted driving. However, TIR target tracking faces problems such as relatively insufficient information and lack of target texture information, which significantly affects the tracking accuracy of the TIR tracking methods. To solve the above problems, we propose a TIR target tracking method based on a Siamese network with a hierarchical attention mechanism (called: SiamHAN). Specifically, the CIoU Loss is introduced to make full use of the regression box information to calculate the loss function more accurately. The global context network (GCNet) attention mechanism is introduced to reconstruct the feature extraction structure of fine-grained information for the fine-grained information of TIR images. Meanwhile, for the feature information of the hierarchical backbone network of the Siamese network, the ECANet attention mechanism is used for hierarchical feature fusion, so that it can fully utilize the feature information of the multilayer backbone network to represent the target. On the LSOTB-TIR, the hierarchical attention Siamese network achieved a 2.9% increase in success rate and a 4.3% increase in precision relative to the baseline tracker. Experiments show that the proposed SiamHAN method has achieved competitive tracking results on the TIR testing datasets.
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2024.3462973