Maritime automatic target recognition using high range resolution radar range profiles and classifier combination

A maritime Automatic Target Recognition (ATR) system is developed that performs ship classification using 1-D high resolution range profiles. Three dimensional models for six small ship targets are developed and range profiles are computed using the shooting and bouncing ray technique. Five physically based features are defined and are extracted from both VV and HH polarizations resulting in a ten dimensional feature vector. A nonlinear classifier combination approach involving a neural network combiner along with three individual classifiers (Bayes, nearest neighbor and neural network) is proposed and correct classification results of greater than 90% are obtained. A decision confidence measure based on the classifier discriminants is developed using a nonparametric estimation approach. The confidence measure enables the system to reject samples that have a low decision confidence. The performance of the proposed neural network based combination is compared to individual classifiers and a number of other combination rules. The results show that this combination can provide high recognition accuracy along with high probability of declaration. The performance in the presence of samples from not-before-seen classes is also investigated. A new nearest neighbor confidence thresholding approach is developed to aid the neural network combiner in rejecting these samples.