Physics informed network improves detection of small infrared targets
PICANet: Physics-Informed Cascaded Asymmetric Network for Infrared Small Target Detection
Computer Vision and Pattern Recognition
Summary
Detecting small objects in infrared images is challenging because of background noise and fading target details. The authors developed a new method called PICANet that uses physics knowledge to better separate targets from the background. Their approach improves how low-level and high-level features are combined so that small targets become clearer. Tests show PICANet works better than earlier methods, especially in complex scenes.
What this means in practice
- •For defense imaging teams: Improve infrared surveillance systems to accurately detect small targets against cluttered backgrounds using physics-informed feature extraction.
- •For autonomous vehicle engineers: Enhance infrared sensing modules to detect distant or small thermal objects more reliably in complex environments.
Authors
Jingjing Liu, Yinchao Han, Xianchao Xiu, Jianhua Zhang, Wanquan Liu
Abstract
Infrared small target detection (ISTD) is an important research direction in image processing. However, existing methods are limited by severe background noise propagation and target degradation in high-level semantic features. To address these limitations, this paper proposes a plug-and-play physics-informed cascaded asymmetric network, named PICANet. Specifically, we construct a hierarchical prior decoupling module to explicitly extract low-level and high-level physical information, thereby characterizing target features at different levels rather than relying solely on convolutional extraction. Furthermore, a dual-prior interactive fusion module is developed to dynamically refine target representations while suppressing complex background clutter. Unlike previous work, a multi-level cross-feature attention module with the cascaded asymmetric mechanism is introduced to achieve precise alignment between high-level semantics and low-level spatial details. Extensive experiments demonstrate that the proposed PICANet outperforms state-of-the-art ISTD methods, showing satisfactory detection accuracy even against complex backgrounds. Our code is available at https://github.com/xianchaoxiu/PICANet.