Randomized Stepped Frequency Radar Extended Target HRRP-Velocity Joint Estimation Based on SBL-DGAMP-Net

• Published in: IEEE geoscience and remote sensing letters Vol. 21; pp. 1 - 5
• Main Authors: Wang, Yiding, Li, Yuanhao, Song, Jiongda, Zhao, Guanghui
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Approximate message passing; Artificial neural networks; Bayes methods; Bayesian analysis; Computer applications; Damping; Deep learning; deep unfolding network; Estimation; extended target; Fragility; Frequency modulation; High resolution; joint high-resolution range profile (HRRP)-velocity estimation; Machine learning; Message passing; Neural networks; Probability theory; Radar; randomized stepped frequency radar (RSFR); Reconstruction; Scattering; sparse Bayesian learning (SBL); Sparsity; Task complexity; Vectors; Velocity
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2024.3407950

Randomized stepped frequency radar (RSFR) is suitable for handling tasks in complex electromagnetic environments. Because the target typically occupies a series of range cells in the high-resolution range profiles (HRRPs) synthesized by RSFR, it is referred to as an extended target. However, current joint reconstruction methods based on sparsity theory are still limited by the length of the extended target, resulting in block mismatch and high computational complexity. How to adaptively determine the size of the extended target remains a challenge. In this letter, a novel deep unfolding network is proposed for the reconstruction of the extended target with block-sparse property, called Sparse Bayesian Learning (SBL)-damped generalized approximate message passing (DGAMP)-Net. The network proposed in the letter can learn block sparsity information from data without block partition information. Particularly, in each layer of SBL-DGAMP-Net, we replace the M-step of pattern-coupled SBL (PC-SBL) with a convolutional neural network, thus overcoming the fragility of PC-SBL parameter selection. The E-step of the network is an unfolding of DGAMP, with the damping factor optimized by deep learning. Furthermore, the architecture of SBL-DGAMP-Net can accept measurement matrices as inputs to the network, thus avoiding the need for retraining. The simulation results indicate that this method exhibits superior reconstruction accuracy and computational efficiency compared to existing high-resolution range-velocity joint reconstruction algorithms for RSFR.