Abstract
In this paper, a new 1-D hybrid Automatic Target Recognition (ATR) algorithm is developed for sequential High Range Resolution (HRR) radar signatures. The proposed hybrid algorithm combines Eigen-Template based Matched Filtering (ETMF) and Hidden Markov modeling (HMM) techniques to achieve superior HRR-ATR performance. In the proposed hybrid approach, each HRR test profile is first scored by ETMF that is followed by independent HMM scoring. The first ETMF scoring step produces a limited number of “most likely” models that are subsequently used for improved HMM scoring in the second step. The individual scores of ETMF and HMM are combined using Maximal Ratio Combining to render the final classification decision. The weights assigned to combine the discriminant scores of ETMF and HMM are determined from the training data. Finally, the hybrid approach is extended to a time-recursive sequential or multi-look HRR-ATR framework that is appropriate for simultaneous recognition and tracking of moving targets, where recognition at previous steps or other look angles are combined in a multiple-hypotheses sense. Classification results are presented using the MSTAR data set and the performance effectiveness of the algorithms is compared using ROC curves.