A Framework for Using Radar Measurements of Unknown Targets in Hierarchical Classification

Real-life target recognition often requires appropriate processing of unknown targets. Such targets are the ones that the automatic target recognition system has not been trained to identify. These targets may, however, be interesting whereupon they should be further analyzed. In this paper, we propose a novel framework for analyzing radar measurements of unknown targets in order to incorporate them into a hierarchical target class taxonomy for the target recognition. Besides the preliminary information, a vital part in the analysis of the radar measurement is the comparison between the measured signature and the signatures of the known target types and categories. We use the results of such analysis to indicate potential spots in the class taxonomy where to add the unknown target. The framework allows identification of unknown target types that have been previously observed, when they are encountered again. We demonstrate the proposed framework through an experiment using the real data of a multi-radar system. In the experiments, we show the feasibility of our approach by examining target recognition in two cases: using our framework and without it. We find that the proposed framework enables enhanced processing of unknown targets in radar target recognition.