Recognition of Airplanes Using Merged Subspace Classifiers

International audienceAir-traffic controllers cannot identify airplanes flying with a defective or non-existent transponder. Primary radars do not help since they cannot classify airplanes from echoes. Passive radars offer a potential solution, the main difficulty lying in the analysis of the data. In this paper, we present an automatic target recognition system capable of recognizing airplanes observed with a passive radar. The recognition system relies on the variation of radar cross-section (RCS) of airplanes. Airplanes are recognized by merging the outputs of a grid of parallel classifiers based on subspace methods. The recognition experiments we performed give a correct recognition rate of about 88%