Recognizing Human Behavior Using Hidden Markov Models

Abstract

This chapter describes a new human behavior recognition method based on Hidden Markov Models (HMM). We use a feature-based bottom-up approach using HMM, which can provide a learning capability and time-scale invariability. To apply HMM to our aim, time sequential images are transformed to an image feature vector sequence, and the sequence is converted to a symbol sequence by Vector Quantization. In learning human behavior categories, the model parameters of HMM are optimized so as to best describe training sequences. For recognition, the model that best matches the observed sequence is chosen. A new VQ method and HMM configuration for behavior recognition is proposed and evaluated. Experimental results of real time-sequential images of sports scenes show a higher than 90% recognition rate. We also describe an example application of this behavior recognition method to content-based video database retrieval.