A context-aware anchor-free tiny object detector for aerial images

Li-Syuan Chen; Der-Lor Way; Zen-Chung Shih

doi:10.1117/12.2624186

30 April 2022 A context-aware anchor-free tiny object detector for aerial images

Li-Syuan Chen, Der-Lor Way, Zen-Chung Shih

Proceedings Volume 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022; 121770Y (2022) https://doi.org/10.1117/12.2624186
Event: International Workshop on Advanced Imaging Technology 2022 (IWAIT 2022), 2022, Hong Kong, China

Abstract

Object detection in aerial images is a task of predicting the target categories while locating the objects. Since the different categories of objects may have similar shapes and textures in aerial images, we propose context-aware layer to provide global and robust features for classification and regression branch. In addition, we propose the CentraBox to reduce unnecessary training samples during the training phase. We also propose the instance-level normalization to balance the contributions among the instances. Finally, we compare our method with other methods in terms of accuracy, speed and parameters usage. Moreover, we also compare our own method with different hyper-parameter settings.

Citation Download Citation

Li-Syuan Chen, Der-Lor Way, and Zen-Chung Shih "A context-aware anchor-free tiny object detector for aerial images", Proc. SPIE 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022, 121770Y (30 April 2022); https://doi.org/10.1117/12.2624186

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