Deep SAR Tomography: A Model-Inspired Approach With Learned Sparse Regularizer

Abstract

Synthetic aperture radar tomography (TomoSAR) can acquire high resolution in height direction by forming a large synthetic aperture along the tomographic direction. Compressed sensing (CS) is widely utilized in TomoSAR imaging to reduce the costs of data sensing. Nevertheless, traditional CS-based algorithms are limited to computational complexity and the nontrivial parameters' tuning. To address such problems, an efficient unfolded deep shrinkage-thresholding network is proposed for TomoSAR imaging in this article. The proposed method adopts convolutional neural network module to learn a generalized nonlinear sparse transformation operator, showing great benefits in exploring the optimal prior. Besides, the hyperparameters of the optimization framework are learned by end-to-end learning mechanism instead of manual-defined, which obviously improves the efficiency of imaging process. Inspired by residual network, the residual learning is introduced to reconstruction blocks of the proposed imaging network, improving the robustness of the network. In addition, the training dataset is constructed from point cloud data based on TomoSAR imaging principles, enhancing the network's ability to extract structural information. Finally, extensive simulation and measured experimental results show the effectiveness of the proposed method, obtaining high-quality imaging results while maintaining high computational efficiency.

Keywords

• Compressed sensing (CS)
• synthetic aperture radar tomography (TomoSAR)
• shrinkage thresholding
• unfolded deep neural work