Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization

The ground moving target (GMT) is defocused due to unknown motion parameters in synthetic aperture radar (SAR) imaging. Although the conventional Omega-K algorithm (Omega-KA) has been proven be applicable for GMT imaging, its disadvantages are slow imaging speed, obvious sidelobe interference, and high computational complexity. To solve above problems, a SAR-GMT network proposed based on trainable Omega-KA sparse optimization. Specifically, we propose two-dimensional (2-D) model deducted from focusing process. Then, recurrent neural (RNN) an iterative optimization built learn of by off-line supervised training method, solving process mapped each layer RNN. (Omega-KA-net) forms new method that can applied high-quality under down-sampling low signal noise ratio (SNR) while saving time substantially. experiments simulation data measured demonstrate Omega-KA-net superior algorithms terms quality time.