Modified Polar Mapping Classifier for SAR Automatic Target Recognition

Abstract

In this study, we propose a modified polar mapping classifier (M-PMC) with an efficient preprocessing scheme to classify synthetic aperture radar (SAR) targets from the public release database for moving and stationary target acquisition and recognition. M-PMC is evaluated under various SAR extended operating conditions (EOCs), which are designed to reflect real-world battlefield scenarios. Experimental outcomes from various EOCs show that M-PMC has good generalization capabilities and outperforms conventional classifiers.