ISAR High-Resolution Imaging Method With Joint FISTA and VGGNet

With regard to inverse synthetic aperture radar (ISAR) imaging, traditional range-Doppler (RD) algorithm is inapplicable sparse aperture. Although compressive sensing (CS) can overcome this problem, the imaging resolution not high enough. When deep learning (DL) applied ISAR some problems may also occur, such as network complexity, selection of labels in training, influence noise and aperture, loss weak scattering points test. In order solve above problems, a joint fast iterative shrinkage-thresholding (FISTA) Visual Geometry Group Network (VGGNet) high-resolution method proposed paper. method, FISTA presented reduce impact The processing (HRPN) built based on VGGNet. Then, combined with peak extraction technology, random ideal are utilized construct training/validation set. Meanwhile, training process HRPN analyzed theoretically, test strategy designed by differences between set Extensive experiments both simulated measured data demonstrate that has good performance small complexity.