Water Body Segmentation of SAR Images Based on SAR Image Reconstruction and an Improved UNet

Water body segmentation utilizing synthetic aperture radar (SAR) images plays a crucial role in water resource and flood monitoring. However, the existing SAR water segmentation methods often underutilize the information present in the multiple bands of SAR images. Moreover, U-shaped semantic segmentation algorithms based on convolutional neural networks (CNNs) often suffer from the loss of valuable feature information and the neglection of global and local correlations caused by the inclusion of pooling layers. To address these challenges, this letter first generates two novel bands from the VV and VH bands of the SAR images and combines them with the VV band to create a new SAR image as the input for the model. Then, to enhance the model’s capacity for feature learning and minimize the risk of overlooking small-target water bodies, this letter proposed a water body segmentation model for SAR images that improves upon the UNet model by integrating coordinate attention mechanisms, convolutional block attention module (CBAM), and PVTv2. Finally, to tackle the issue of high-computational complexity associated with the model, traditional convolutions are substituted with depthwise separable convolutions. The experimental results demonstrate that the proposed method achieves a 1.68% increase in accuracy, a 4.21% increase in mean intersection-over-union (MIOU), and a 3.51% increase in F score when compared with the widely adopted UNet algorithm. Consequently, the proposed model surpasses other algorithms in the domain of water segmentation.