In this article, we consider a sub-Nyquist sampled multiple-input multiple-output (MIMO) radar scenario where the observations are contaminated by impulsive non-Gaussian clutter, which introduces outliers. To recover the missing data, we propose a robust matrix completion (MC) method with a regularizer that acts on outliers. This regularizer, whose solution is unbiased, sparse, and continuous, is generated by the hybrid ordinary-Welsch (HOW) function, aiming to classify each measurement as normal, semicontaminated, or contaminated, and then handle it appropriately. Then proximal block coordinate descent (BCD) is leveraged to tackle the HOW-based MC problem and the convergence property and computational cost of the developed algorithm are analyzed. Experimental results validate the superior performance of our method compared to existing approaches in terms of MC and direction-of-arrival estimation accuracies as well as runtime in the presence of Gaussian mixture noise and K-distributed clutter.
Hybrid Ordinary-Welsch Function-Based Robust Matrix Completion for MIMO Radar
IEEE Transactions on Aerospace and Electronic Systems ; 61 , 2 ; 3950-3962
2025-04-01
2179804 byte
Article (Journal)
Electronic Resource
English
Anomaly detection method and device based onPSO-Welsch-Ridge
European Patent Office | 2021
|