Water Body Automated Extraction in Polarization SAR Images With Dense-Coordinate-Feature-Concatenate Network
Weibao Xue, Hui Yang, Yanlan Wu, Kong Peng, Hao Xu, Penghai Wu, Xiaoshuang Ma
Abstract
Synthetic aperture radar (SAR) water body extraction is of great significance for many applications, such as flood disaster monitoring, coastline change detection, and water resources management. However, the previous research has mainly focused on single band SAR images, and the dual-polarization information has not been comprehensively utilized, resulting in the problem of incomplete water body extraction. In this article, we propose a model called dense-coordinate-feature-concatenate network (DCFNet) to extract and fuse the water features of dual-polarization SAR images, overcome the influence of ground interferences, and improved the accuracy and generalization of the model. In this model, the improved dense block module is used to extract and transfer the water features in the dual-polarization data, a coordinate attention module is used to reduce the loss of water body boundary, and a feature concatenate module is proposed to avoid information redundancy. Experimental results show that our proposed model cannot only overcome the influence of roads and hill shades and achieve 98.4%, 84.62%, and 91.67% water body extraction accuracy in overall accuracy, intersection over union, and F1, respectively, on Gaofen-3 SAR images but can also be directly applied to the water body extraction of Sentinel-1 SAR images.