Bridge Detection in High-Resolution X-Band Sar Images by Combined Statistical and Topological Approach

Abstract

This article takes account of the radiation feature of rivers in high-resolution airborne Xband synthetic aperture radar (SAR) images and proposes a novel automatic approach to detect highway bridges by combining statistical and topology features. The proposed method consists of two steps. In the river-extraction stage, the classification techniques are applied to water extraction according to the statistical and gray-leveled features. In the bridge-extraction stage, bridges are then detected in this binary image by using a topology-based approach. Experiments, undertaken on high-resolution X-band SAR images, confirm that the proposed method can be implemented with high-precision highway-bridge extraction, feature analysis, and bridge recognition.

Detection of Collapsed Bridges from Multi-Temporal SAR Intensity Images by Machine Learning Techniques

“…Cadario et al [24] discussed the possibilities of extracting bridge features using SAR simulators, as well as airborne and satellite SAR images. Yang and Jian [25] proposed a topography-based method to extract bridges automatically from highresolution airborne SAR imagery. Chen et al [26] proposed a new deep learning-based network to identify bridges from SAR images.…”