Dual efficient self-attention network for multi-target detection in aerial imagery

Sikui Wang; Yunpeng Liu; Zhiyuan Lin; Zhongyu Zhang

doi:10.1117/12.2549196

31 January 2020 Dual efficient self-attention network for multi-target detection in aerial imagery

Sikui Wang, Yunpeng Liu, Zhiyuan Lin, Zhongyu Zhang

Proceedings Volume 11427, Second Target Recognition and Artificial Intelligence Summit Forum; 114270D (2020) https://doi.org/10.1117/12.2549196
Event: Second Target Recognition and Artificial Intelligence Summit Forum, 2019, Changchun, China

Abstract

Aerial imagery target detection has been widely used in the military and economic fields. However, it still faces a variety of challenges. In this paper, we proposed several efficiency improvements based on YOLO v3 framework for getting a better small target detection precision. Firstly, a dual self-attention (DAN) block is embedded in Darknet-53’s ResNet units to refine the feature map adaptively. Furthermore, the deep semantic features are cascaded with the shallow outline features in a feedforward deconvolutional module to obtain context details of small targets. Finally, introducing online hard examples mining and combining Focal Loss to enhance the discriminating ability between classes. The experimental results on the VEDAI aerial dataset show that the proposed algorithm is significantly improved in accuracy compared to the original network and achieves better performance than two-stage algorithms.

Citation Download Citation

Sikui Wang, Yunpeng Liu, Zhiyuan Lin, and Zhongyu Zhang "Dual efficient self-attention network for multi-target detection in aerial imagery", Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114270D (31 January 2020); https://doi.org/10.1117/12.2549196

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