SAR-EdgeYOLO: Robust Bridge Detection in Low-Resolution SAR via Edge Enhancement

Abstract

Bridge detection using Synthetic Aperture Radar (SAR) is important for infrastructure management, disaster prevention, and navigation automation. Although high-resolution SAR is becoming increasingly accessible, exploiting Sentinel-1 remains advantageous due to its global coverage and accessibility. However, the low spatial resolution of 20 m in Sentinel-1 products poses challenges for detecting small and indistinct bridges. To enhance bridge detection in low-resolution Sentinel-1 imagery, we propose a novel architecture that incorporates CycleGAN as an edge detector. CycleGAN generates detailed boundaries using 5 m land use maps, with enhanced bridge saliency. Since bridges often connect distinct edges like riverbanks and roads, this edge information assists Poly-YOLOv8, our chosen detector, in accurately localizing bridges. Our approach then integrates edge information through feature fusion module and feature alignment loss. Accordingly, the proposed SAR-EdgeYOLO achieves a precision of 98.2%, recall of 91.7%, and mAP of 94.8% at IoU 0.5, marking improvements of 3.9, 3.8, and 3.1 percentage points respectively over the baseline. The results demonstrate that CycleGAN-aided edge extraction effectively addresses the limitations of low-resolution remote sensing data, improving bridge detection accuracy and multi-class localization. This research can further contribute to the advancement of time series infrastructure monitoring with wide applicability and higher accuracy.

Keywords

• Bridge detection
• deep learning
• edge extraction
• feature fusion