Hidden Markov models for multiaspect target classification

This correspondence presents a new approach for target identification, in w hich we fuse scattering data from multiple target-sensor orientations. The multiaspect data is processed via hidden Markov model (HMM) classifiers, bu ttressed by physics-based feature extraction. This approach explicitly acco unts for the fact that the target-sensor orientation is generally unknown o r "hidden." Discrimination results are presented for measured scattering da ta.