Sparse SAR Imaging Method for Ground Moving Target via GMTSI-Net

Ground moving targets (GMT), due to the existence of velocity in range and azimuth direction, will lead deviation from their true position defocus direction during synthetic aperture radar (SAR) imaging process. To address this problem compress amount echo data, a sparse SAR method for ground is proposed. Specifically, we first constructed two-dimensional observation model GMT based on matched filter operators. Then, was solved by deep network, network (GMTSI-Net), which mainly obtained unfolding an iterative soft threshold algorithm (ISTA)-based solution. Furthermore, designed adaptive module improve adaptability input data with different sampling ratios. The proposed can achieve faster more accurate images under low ratio signal-to-noise (SNR). Simulated measured experiments were conducted demonstrate performance quality method.