Robust Detection in Distributed MIMO Radar

We consider the case where there are outliers in the observations and evaluate two robust detectors, namely the Clipped Log-Likelihood Ratio Detector inspired by Huber’s ratio test, and a $\alpha$–Trimmed Sum Detector. The detector’s robustness and performance in the presence of outliers are analyzed. We show these detectors provide reasonably good performance despite the presence of outliers in the observations. We also analyze the detectors breakdown points where the detectors can not yield any meaningful results.