Loading [MathJax]/extensions/MathMenu.js
Hierarchical Attention Siamese Network for Thermal Infrared Target Tracking | IEEE Journals & Magazine | IEEE Xplore

Hierarchical Attention Siamese Network for Thermal Infrared Target Tracking


Abstract:

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 a...Show More

Abstract:

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.
Article Sequence Number: 5032411
Date of Publication: 18 September 2024

ISSN Information:

Funding Agency:

Author image of Di Yuan
Guangzhou Institute of Technology, Xidian University, Guangzhou, China
Di Yuan (Member, IEEE) received the Ph.D. degree in computer applied technology from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at Guangzhou Institute of Technology, Xidian University, Guangzhou, China. He was sponsored by the China Scholarship Council as a Visiting Ph.D. Student at the Faculty of Information Technology, Monash University, Melbourne, VIC, Australia, from 2019 to 202...Show More
Di Yuan (Member, IEEE) received the Ph.D. degree in computer applied technology from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at Guangzhou Institute of Technology, Xidian University, Guangzhou, China. He was sponsored by the China Scholarship Council as a Visiting Ph.D. Student at the Faculty of Information Technology, Monash University, Melbourne, VIC, Australia, from 2019 to 202...View more
Author image of Donghai Liao
Guangzhou Institute of Technology, Xidian University, Guangzhou, China
Donghai Liao received the B.Eng. degree from Guilin University of Electronic Technology, Guilin, China, in 2023. He is currently pursuing the master’s degree with the School of Artificial Intelligence, Xidian University, Guangzhou, China.
His research interests include thermal infrared target tracking, object detection, and image processing.
Donghai Liao received the B.Eng. degree from Guilin University of Electronic Technology, Guilin, China, in 2023. He is currently pursuing the master’s degree with the School of Artificial Intelligence, Xidian University, Guangzhou, China.
His research interests include thermal infrared target tracking, object detection, and image processing.View more
Author image of Feng Huang
School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China
Feng Huang received the M.S. and Ph.D. degrees in optical engineering from Beihang University, Beijing, China, in 2004 and 2010, respectively.
He is currently a Professor with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are photoelectric detection and imaging.
Feng Huang received the M.S. and Ph.D. degrees in optical engineering from Beihang University, Beijing, China, in 2004 and 2010, respectively.
He is currently a Professor with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are photoelectric detection and imaging.View more
Author image of Zhaobing Qiu
School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China
Zhaobing Qiu received the M.S. and Ph.D. degrees from the School of Electronic Information, Wuhan University, Wuhan, China, in 2019 and 2023, respectively.
He is currently a Lecturer with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are small target detection and image processing.
Zhaobing Qiu received the M.S. and Ph.D. degrees from the School of Electronic Information, Wuhan University, Wuhan, China, in 2019 and 2023, respectively.
He is currently a Lecturer with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are small target detection and image processing.View more
Author image of Xiu Shu
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China
Xiu Shu received the M.S. and Ph.D. degrees from the School of Science from Harbin Institute of Technology, Shenzhen, China, in 2018 and 2023, respectively.
She is currently a Lecturer with the School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China. Her current research interests include image processing, image segmentation, level-set method, and deep learning.
Xiu Shu received the M.S. and Ph.D. degrees from the School of Science from Harbin Institute of Technology, Shenzhen, China, in 2018 and 2023, respectively.
She is currently a Lecturer with the School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China. Her current research interests include image processing, image segmentation, level-set method, and deep learning.View more
Author image of Chunwei Tian
School of Software, Northwestern Polytechnical University, Xi’an, Shaanxi, China
Yangtze River Delta Research Institute, Northwestern Polytechnical University, Taicang, Jiangsu, China
Chunwei Tian (Member, IEEE) received the Ph.D. degree in computer application technique from Harbin Institute of Technology, Harbin, China, in 2021.
He is currently an Associate Professor with the School of Software, Northwestern Polytechnical University, Xi’an, China, where he is also a member of the National Engineering Laboratory for Integrated Aerospace Ground-Ocean Big Data Application Technology. He has authored or c...Show More
Chunwei Tian (Member, IEEE) received the Ph.D. degree in computer application technique from Harbin Institute of Technology, Harbin, China, in 2021.
He is currently an Associate Professor with the School of Software, Northwestern Polytechnical University, Xi’an, China, where he is also a member of the National Engineering Laboratory for Integrated Aerospace Ground-Ocean Big Data Application Technology. He has authored or c...View more
Author image of Qiao Liu
National Center for Applied Mathematics, Chongqing Normal University, Chongqing, China
Qiao Liu received the Ph.D. degree in computer science from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at the National Center for Applied Mathematics, Chongqing Normal University, Chongqing, China. His research interests include thermal infrared object tracking, infrared image processing, and machine learning.
Qiao Liu received the Ph.D. degree in computer science from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at the National Center for Applied Mathematics, Chongqing Normal University, Chongqing, China. His research interests include thermal infrared object tracking, infrared image processing, and machine learning.View more

Author image of Di Yuan
Guangzhou Institute of Technology, Xidian University, Guangzhou, China
Di Yuan (Member, IEEE) received the Ph.D. degree in computer applied technology from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at Guangzhou Institute of Technology, Xidian University, Guangzhou, China. He was sponsored by the China Scholarship Council as a Visiting Ph.D. Student at the Faculty of Information Technology, Monash University, Melbourne, VIC, Australia, from 2019 to 2021, working with Prof. Xiaojun Chang. His current research interests include computer vision, object tracking, machine learning, self-supervised learning, and active learning.
Di Yuan (Member, IEEE) received the Ph.D. degree in computer applied technology from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at Guangzhou Institute of Technology, Xidian University, Guangzhou, China. He was sponsored by the China Scholarship Council as a Visiting Ph.D. Student at the Faculty of Information Technology, Monash University, Melbourne, VIC, Australia, from 2019 to 2021, working with Prof. Xiaojun Chang. His current research interests include computer vision, object tracking, machine learning, self-supervised learning, and active learning.View more
Author image of Donghai Liao
Guangzhou Institute of Technology, Xidian University, Guangzhou, China
Donghai Liao received the B.Eng. degree from Guilin University of Electronic Technology, Guilin, China, in 2023. He is currently pursuing the master’s degree with the School of Artificial Intelligence, Xidian University, Guangzhou, China.
His research interests include thermal infrared target tracking, object detection, and image processing.
Donghai Liao received the B.Eng. degree from Guilin University of Electronic Technology, Guilin, China, in 2023. He is currently pursuing the master’s degree with the School of Artificial Intelligence, Xidian University, Guangzhou, China.
His research interests include thermal infrared target tracking, object detection, and image processing.View more
Author image of Feng Huang
School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China
Feng Huang received the M.S. and Ph.D. degrees in optical engineering from Beihang University, Beijing, China, in 2004 and 2010, respectively.
He is currently a Professor with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are photoelectric detection and imaging.
Feng Huang received the M.S. and Ph.D. degrees in optical engineering from Beihang University, Beijing, China, in 2004 and 2010, respectively.
He is currently a Professor with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are photoelectric detection and imaging.View more
Author image of Zhaobing Qiu
School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China
Zhaobing Qiu received the M.S. and Ph.D. degrees from the School of Electronic Information, Wuhan University, Wuhan, China, in 2019 and 2023, respectively.
He is currently a Lecturer with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are small target detection and image processing.
Zhaobing Qiu received the M.S. and Ph.D. degrees from the School of Electronic Information, Wuhan University, Wuhan, China, in 2019 and 2023, respectively.
He is currently a Lecturer with the College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China. His current research interests are small target detection and image processing.View more
Author image of Xiu Shu
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China
Xiu Shu received the M.S. and Ph.D. degrees from the School of Science from Harbin Institute of Technology, Shenzhen, China, in 2018 and 2023, respectively.
She is currently a Lecturer with the School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China. Her current research interests include image processing, image segmentation, level-set method, and deep learning.
Xiu Shu received the M.S. and Ph.D. degrees from the School of Science from Harbin Institute of Technology, Shenzhen, China, in 2018 and 2023, respectively.
She is currently a Lecturer with the School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China. Her current research interests include image processing, image segmentation, level-set method, and deep learning.View more
Author image of Chunwei Tian
School of Software, Northwestern Polytechnical University, Xi’an, Shaanxi, China
Yangtze River Delta Research Institute, Northwestern Polytechnical University, Taicang, Jiangsu, China
Chunwei Tian (Member, IEEE) received the Ph.D. degree in computer application technique from Harbin Institute of Technology, Harbin, China, in 2021.
He is currently an Associate Professor with the School of Software, Northwestern Polytechnical University, Xi’an, China, where he is also a member of the National Engineering Laboratory for Integrated Aerospace Ground-Ocean Big Data Application Technology. He has authored or co-authored over 50 papers in academic journals and conferences, including the IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Multimedia, IEEE Transactions on Systems, Man, and Cybernetics, Pattern Recognition, Neural Networks, Information Sciences, and International Conference on Acoustics, Speech, and Signal Processing. His research interests include image restoration, image recognition, and deep learning.
Chunwei Tian (Member, IEEE) received the Ph.D. degree in computer application technique from Harbin Institute of Technology, Harbin, China, in 2021.
He is currently an Associate Professor with the School of Software, Northwestern Polytechnical University, Xi’an, China, where he is also a member of the National Engineering Laboratory for Integrated Aerospace Ground-Ocean Big Data Application Technology. He has authored or co-authored over 50 papers in academic journals and conferences, including the IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Multimedia, IEEE Transactions on Systems, Man, and Cybernetics, Pattern Recognition, Neural Networks, Information Sciences, and International Conference on Acoustics, Speech, and Signal Processing. His research interests include image restoration, image recognition, and deep learning.View more
Author image of Qiao Liu
National Center for Applied Mathematics, Chongqing Normal University, Chongqing, China
Qiao Liu received the Ph.D. degree in computer science from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at the National Center for Applied Mathematics, Chongqing Normal University, Chongqing, China. His research interests include thermal infrared object tracking, infrared image processing, and machine learning.
Qiao Liu received the Ph.D. degree in computer science from Harbin Institute of Technology, Harbin, China, in 2021.
Currently, he is a Lecturer at the National Center for Applied Mathematics, Chongqing Normal University, Chongqing, China. His research interests include thermal infrared object tracking, infrared image processing, and machine learning.View more
Contact IEEE to Subscribe

References

References is not available for this document.