The proliferation of massive polarimetric Synthetic Aperture Radar (SAR) data helps promote the development of SAR image interpretation. Due to the advantages of powerful feature extraction capability and strong adaptability for different tasks, deep learning has been adopted in the work of SAR image interpretation and has achieved good results. However, most deep learning methods only employ single-polarization SAR images and ignore the water features embedded in multi-polarization SAR images. To fully exploit the dual-polarization SAR data and multi-scale features of SAR images, an effective flood detection method for SAR images is proposed in this paper. In the proposed flood detection method, a powerful Multi-Scale Deeplab (MS-Deeplab) model is constructed based on the dual-channel MobileNetV2 backbone and the classic DeeplabV3+ architecture to improve the ability of water feature extraction in SAR images. Firstly, the dual-channel feature extraction backbone based on the lightweight MobileNetV2 separately trains the dual-polarization SAR images, and the obtained training parameters are merged with the linear weighting to fuse dual-polarization water features. Given the multi-scale space information in SAR images, then, a multi-scale feature fusion module is introduced to effectively utilize multi-layer features and contextual information, which enhances the representation of water features. Finally, a joint loss function is constructed based on cross-entropy and a dice coefficient to deal with the imbalanced categorical distribution in the training dataset. The experimental results on the time series of Sentinel-1A SAR images show that the proposed method for flood detection has a strong ability to locate water boundaries and tiny water bodies in complex scenes. In terms of quantitative assessment, MS-Deeplab can achieve a better performance compared with other mainstream semantic segmentation models, including PSPNet, Unet and the original DeeplabV3+ model, with a 3.27% intersection over union (IoU) and 1.69% pixel accuracy (PA) improvement than the original DeeplabV3+ model.

Urban water plays a significant role in the urban ecosystem, but urban water extraction is still a challenging task in automatic interpretation of synthetic aperture radar (SAR) images. The influence of radar shadows and strong scatters in urban areas may lead to misclassification in urban water extraction. Nevertheless, the local features captured by convolutional layers in Convolutional Neural Networks (CNNs) are generally redundant and cannot make effective use of global information to guide the prediction of water pixels. To effectively emphasize the identifiable water characteristics and fully exploit the global information of SAR images, a modified Unet based on hybrid attention mechanism is proposed to improve the performance of urban water extraction in this paper. Considering the feature extraction ability and the global modeling capability in SAR image segmentation, the Channel and Spatial Attention Module (CSAM) and the Multi-head Self-Attention Block (MSAB) are both introduced into the proposed Hybrid Attention Unet (HA-Unet). In this work, Resnet50 is adopted as the backbone of HA-Unet to extract multi-level features of SAR images. During the feature extraction process, CSAM based on local attention is adopted to enhance the meaningful water features and ignore unnecessary features adaptively in feature maps of two shallow layers. In the last two layers of the backbone, MSAB is introduced to capture the global information of SAR images to generate global attention. In addition, two global attention maps generated by MSAB are aggregated together to reconstruct the spatial feature relationship of SAR images from high-resolution feature maps. The experimental results on Sentinel-1A SAR images show that the proposed urban water extraction method has a strong ability to extract water bodies in the complex urban areas. The ablation experiment and visualization results vividly indicate that both CSAM and MSAB contribute significantly to extracting urban water accurately and effectively.

Distributed scatterer (DS) interferometric synthetic aperture can retrieve maximum available information by jointly processing persistent scatterers (PSs) and DSs. Unlike PSs, DSs are vulnerable to temporal, geometrical, and volumetric decorrelation. The phase optimization of DSs is essential for reliable parameter estimation. However, the preprocessing of DSs is very computationally expensive, and this drawback limits its engineering application to some degree. To improve computational efficiency, a fast scheme for reliable phase optimization of DSs is proposed based on the coherence-weighted model in this letter. The Gauss–Seidel iteration, having the advantages of fast convergence rate and small data memory, is introduced to solve the adopted phase optimization model. Experiments both on simulated data and real data are used to verify the reliability and efficiency of the presented method in this letter.

Synthetic aperture radar (SAR) is crucial for water resource detection and monitoring due to its all-weather, all-day capabilities. Most water body extraction methods only obtain the water information from single polarization SAR images, ignoring various water features captured in SAR images with different polarization modes. To make full use of different polarization information, an efficient water body extraction approach is proposed for dual-polarization SAR data in this work. In preprocessing stage, A-law companding technique is introduced to improve the interpretability of SAR images by adaptively adjusting the dynamic ranges of the amplitudes at different levels, which makes subtle features more distinguishable. Considering both the Dual-polarization feature fusion and the effective extraction of various water bodies, a powerful DFMU-net is constructed based on the framework of Unet and a hybrid MLP network. An adaptive fusion module is firstly developed to capture polarization information of SAR images and generate adaptive weight matrices, effectively integrating dual-polarization water body features in pixel-level and suppressing background noise a little. Then to balance extraction accuracy and inference speed, a hybrid encoder–decoder structure based on CNN and Token-MLP is set up to capture local features and establish long-range dependencies of SAR images. In the part of skip connection, a multi-scale soft thresholding attention is introduced to refine water body features in both channel and spatial dimensions. In the experiment of Sentinel-1 data, the proposed method outperforms known models such as Unet, SegNet, DeeplabV3+, TransUnet and SwinUnet in terms of both extraction accuracy and inference speed.

Unsynchronization of the separate transmit-receive beams makes it a challenging task to obtain high-quality images for nonparallel-track bistatic synthetic aperture radar (NP-BiSAR). To accommodate this issue, we propose an imaging configuration where the receiver's beam follows the transmitter's one actively by adjusting the squint angle of receiver. And a frequency extended nonlinear chirp scaling (FENLCS) algorithm is modified to cope with new effects introduced by the innovative configuration, which is based on an improved quadratic ellipse model. Based on the new model, some innovative improvements on image formation are made, including a residual azimuth-dependent high-order range cell migration correction (ADH-RCMC) and a rederived FENLCS that takes highly varying Doppler centroid into consideration, which contribute to better imaging quality. Simulation results validate the effectiveness of the proposed configuration and algorithm.

Synthetic aperture radar (SAR) change detection is an essential yet challenging task in the field of ground surface observation. Existing transformer-based methods have promising context modeling capabilities for change detection tasks, yet they struggle to preserve change-related details in high-resolution data. To deal with this limitation, a directional-aware dual-branch fusion network (DAFNet) is proposed based on dual-branch backbone and gated cross-fusion module (GCFM) for SAR image change detection. First, an enhanced difference image is developed by integrating log-ratio operator and A-law companding for high-quality training data generation. In the dual-branch backbone, a multi-directional convolution module (MDCM) is then constructed to extract high-frequency features comprehensively via multi-gradient Sobel operators with eight directions, which selectively captures details and contexts of images in a parallel manner with vision transformer. Finally, the GCFM based on GeLU activation and cross-attention is designed to fuse different dimensional features, enhancing related information against irrelevant interference. Experimental evaluations across three real SAR datasets verify the effectiveness of the proposed DAFNet in terms of visualization and quantitative indicators in change detection.