Refined attention Siamese network for real-time object tracking

Jiaqi Xi; Yi Wang; Huaiyu Cai; Xiaodong Chen

doi:10.1117/12.2615556

8 July 2022 Refined attention Siamese network for real-time object tracking

Jiaqi Xi, Yi Wang, Huaiyu Cai, Xiaodong Chen

Proceedings Volume 12282, 2021 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems; 122820C (2022) https://doi.org/10.1117/12.2615556
Event: 2021 International Conference on Optical Instruments and Technology, 2022, Online Only

Abstract

The Siamese tracker shows great potential in achieving a balance between accuracy and speed, but the twin structure of the Siamese network makes the tracker vulnerable to background interference in the tracking scene. To deal with this problem, a tracking algorithm based on the attention mechanism is proposed. The algorithm introduces the channel attention module based on the Siamese network and dynamically enhances the robust channel feature response by modeling the context relationship between channels. This paper also verified the network performance on the OTB and VOT benchmark. Experimental results show that the proposed algorithm can achieve robust tracking results on challenging datasets, and achieves the goal of improving network performance with a slight increase in computational cost.

Citation Download Citation

Jiaqi Xi, Yi Wang, Huaiyu Cai, and Xiaodong Chen "Refined attention Siamese network for real-time object tracking", Proc. SPIE 12282, 2021 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems, 122820C (8 July 2022); https://doi.org/10.1117/12.2615556

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