Physics informed network improves infrared small target detection accuracy
PICANet: Physics-Informed Cascaded Asymmetric Network for Infrared Small Target Detection
Computer Vision and Pattern Recognition
Summary
Detecting tiny targets in infrared images is challenging because background noise and loss of important details often confuse the detection methods. The authors developed a new approach called PICANet that uses physical knowledge about the targets to better separate them from the background. Their method combines different types of information in a step-by-step way to keep details clear and remove background clutter. Tests showed PICANet can find small targets more accurately even in complicated scenes. This helps improve tasks like surveillance or remote sensing where small objects need to be detected.
infrared small target detectionbackground noisehigh-level semantic featuresphysical information extractionconvolutional neural networksfeature fusionattention mechanismhierarchical prior decouplingtarget representation
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.