LapMDNet: Remote Sensing Object Detection Under Foggy Conditions via Physics-Guided Laplacian Prior and Masked Feature Distillation

Abstract

For object detection in remote sensing images, foggy conditions tend to degrade image quality by scattering light and obscuring critical details, thereby compromising the performance of the involved detection models. To address this challenge, we first analyze the feature response of the Laplacian operation based on the atmospheric scattering model (ASM) and design two complementary Laplacian templates for bidirectional edge extraction and fuse them into a customized convolution kernel to enhance fog-degraded features. A rotated object detection method based on masked clean feature distillation is proposed, which leverages clean image features to facilitate the learning of fog-degraded image features. A dual-stream feature attention fusion module is then adopted to integrate the original yet blurred predistillation features with the clear but potentially noisy postdistillation features generated by the feature adjustment module, thus rendering the features for more effective object detection. Finally, a bidirectional attention-based feature pyramid network (BI-AFPN) is employed to enhance multilevel feature fusion. Extensive experiments on the dataset for object detection In optical remote-sensing images (DIOR)-Foggy, dataset for object detection in aerial images (DOTA)-Foggy, and real-world RDDTS fog datasets demonstrate that the proposed model outperforms other state-of-the-art methods.