Key feature extraction for probabilistic categorization of human motion patterns

Mimesis is a hypothesis that human intelligence originated where motion recognition and motion generation interact through imitation. We previously proposed the mathematical model of mimesis using hidden Markov models (HMM) and constructed the proto symbol space from parameters of each HMM. The proto symbol space included only 10 motion patterns. No attention was paid on the relationship between behavior pattern and parts of body. It is common that a human observer pays an attention to the relationship between the parts of body and the behaviors recognizing performer´s behavior pattern. In this paper, we discuss key feature extraction from a rich database of behavior patterns based on probabilistic categorization among HMMs. The method is also applied to extract body parts that characterize behavior patterns