Time-Frequency Analysis for Incomplete Radar Data of Micromotion Targets via Multiframe Parallel Recovery Approach

Conventional time-frequency (TF) analysis methods deteriorate under the condition of data missing and low signal-to-noise ratio (SNR). Sparse signal processing (SSP) method is an effective solution for recovering TF images from incomplete data, but it is burdened by significant computational and storage requirements. To address these challenges, this study proposed a TF image recovery method called multiframe parallel recovery (MFPR) deep unfolded segmentation network. First, the TF recovery optimization problem solved by the proximal gradient (PG) method is constructed based on the MFPR signal model, which can simultaneously recover TF images from all frames. This can eliminate the need for vectorization and thereby reduce computational and storage costs. Then, the MFPR deep unfolded segmentation network (MDUS-Net), which contains two subnetworks, is proposed to obtain a complete TF image from incomplete data. The first subnetwork is a deep unfolded network of MFPR, which achieves high-quality TF recovery from incomplete data. The second subnetwork is a segmentation network, which achieves TF curves skeleton extraction via image segmentation technique. The experimental results on both simulated and measured data demonstrate that the proposed method can generate high-quality TF images even under conditions of incomplete data and low SNR.