Paper
4 December 2024 Dual alignment interactive network for infrared small target detection
Author Affiliations +
Proceedings Volume 13283, Conference on Spectral Technology and Applications (CSTA 2024); 1328315 (2024) https://doi.org/10.1117/12.3034584
Event: Conference on Spectral Technology and Applications (CSTA 2024), 2024, Dalian, China
Abstract
To integrate the relationship between small targets and high-intensity structured backgrounds in infrared images, we propose a dual alignment interactive network (DAINet) for infrared small target detection. DAINet treats the low-rank background features of infrared images as complementary data, guiding the network to consistently focus and localize infrared small targets. First, the dual interactive block is built by receiving an infrared image and a background image, which interactively combines the target and background attention for better detection performance. Then, a multi-level feature fusion strategy is designed to get the final robust result. Experimental results on two public datasets reveal that DAINet can process images with high detection accuracy compared to various state-of-the-art (SOTA) methods.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Fan Hao, Feng Zhou, Pengfei Lu, and Zhipeng Wang "Dual alignment interactive network for infrared small target detection", Proc. SPIE 13283, Conference on Spectral Technology and Applications (CSTA 2024), 1328315 (4 December 2024); https://doi.org/10.1117/12.3034584
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Infrared radiation

Infrared imaging

Target detection

Small targets

Infrared detectors

Feature extraction

Image fusion

Back to Top