Incremental model-based discrimination of articulated movement from motion features

Discrimination of articulated movement is a central problem in perception. We present a model-based system designed to discriminate articulated movements and demonstrate its capabilities in distinguishing three human gaits. Recognition proceeds directly from uninterpreted visual motion features. The adaptive model of movement, the scenario, is based on discrete parameterized events separated by parameterized time intervals. Experimental results are shown for real data derived from moving light displays, demonstrating the effectiveness of the structured connectionist approach.<
>