Adatomo-Net: a Novel Deep Learning Approach for SAR Tomography Imaging and Autofocusing

Tomographic Synthetic aperture radar (TomoSAR) imaging algorithms for urban areas based on Compressed Sensing (CS) often have high time complexity due to many times iterations. Moreover, the phase error (PE) that exists will defocus TomoSAR imaging results. To reduce PE in the TomoSAR process, researchers use methods such as PS-InSAR, phase gradient autofocusing (PGA), etc. However, these methods are computationally expensive, which hinders the application of fast high-resolution TomoSAR imaging. In this paper, we merge the PE compensation into FISTA framework and proposed a novel deep learning approach for TomoSAR imaging. The network is based on Ada-LFISTA architecture, dubbed as AdaTomo-Net. Experiment results show that AdaTomo-Net has higher imaging accuracy and considerable computational efficiency compared with typical CS algorithms and learning-based algorithms such as LISTA in the presence of PE.