Target tracking algorithm based on attention mechanism

Guoqiang Wang; Guangyu Hui; Xi Luo; Yunong Xiong

doi:10.1117/12.2674797

2 May 2023 Target tracking algorithm based on attention mechanism

Guoqiang Wang, Guangyu Hui, Xi Luo, Yunong Xiong

Proceedings Volume 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023); 126421R (2023) https://doi.org/10.1117/12.2674797
Event: Second International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT 2023), 2023, Xishuangbanna, China

Abstract

Inspired by Transformer, this paper proposes a new attention-based feature fusion network, which effectively combines template features and search region features using attention alone. Specifically, the method includes a contextual enhancement module based on multi-headed self-attention and a cross-feature enhancement module based on crossattention, and finally the two features are combined using the residual structure to effectively enhance the features. Experiments show that our tracker achieves very good results on the GOT-10k benchmark. It runs at approximately 45fps on the GPU, which achieves the real-time requirement.

Citation Download Citation

Guoqiang Wang, Guangyu Hui, Xi Luo, and Yunong Xiong "Target tracking algorithm based on attention mechanism", Proc. SPIE 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023), 126421R (2 May 2023); https://doi.org/10.1117/12.2674797

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available