In recent years there has been an increased interest in the modelling and recognition of human activities involving highly structured and semantically rich behaviour such as dance, aerobics, and sign language. A novel approach is presented for automatically acquiring stochastic models of the high-level structure of an activity without the assumption of any prior knowledge. The process involves temporal segmentation into plausible atomic behaviour components and the use of variable length Markov models for the efficient representation of behaviours. Experimental results are presented which demonstrate the generation of realistic sample behaviours and evaluate the performance of models for long-term temporal prediction.
Learning structured behaviour models using variable length Markov models
1999-01-01
2126175 byte
Conference paper
Electronic Resource
English
Learning Structured Behaviour Models using Variable Length Markov Models
British Library Conference Proceedings | 1999
|Learning Variable-Length Markov Models of Behavior
British Library Online Contents | 2001
|A real-time hand tracker using variable-length Markov models of behaviour
British Library Online Contents | 2007
|Design of a Linguistic Postprocessor Using Variable Memory Length Markov Models
British Library Conference Proceedings | 1995
|