Sparsity-Driven ISAR Imaging via Hierarchical Channel-Mixed Framework

Sparsity-driven inverse synthetic aperture radar (ISAR) imaging can obtain a high-resolution image of non-cooperative targets using compressive sensing (CS)-based methods. However, traditional CS-based imaging methods generally require extensive computational complexity, and some fixed parameters need to be manually tuned to be optimal for better imaging quality. Iterative-thresholding methods are typical CS-based algorithms with representative framework and efficient performance. This paper proposes a general structure of hierarchical channel-mixed framework (HCMF) for sparsity-driven ISAR imaging. Specifically, HCMF is constructed by unrolling the iterative-thresholding methods, and each phase of HCMF is mapped from one iteration in traditional iterative-thresholding methods, maintaining the hierarchical framework. HCMF also involves mixed channels that flow separately and together at different processes, to process complex data properly. Besides, the parameters in each phase are set to be learnable and self-adapted optimal, contributing to greater robustness. Without loss of generality, we take approximate message-passing (AMP) for demonstration, dubbed as HCM-AMP-Net (HCM-AMPN). HCM-AMPN has the almost same computational complexity as traditional AMP, but the high-parallelization of deep network accelerates computational efficiency dramatically. Experimental results based on simulated and measured data demonstrate that HCM-AMPN has higher efficiency and superior performance compared with some state-of-the-art methods. In our experiments, HCM-AMPN is more than 100 times faster than traditional AMP, and tens of times faster than other network-based methods.