Learning structured behaviour models using variable length Markov models
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- Language modeling with stochastic automataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Action recognition using probabilistic parsingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- ASL recognition based on a coupling between HMMs and 3D motion analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The acquisition and use of interaction behaviour modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning and recognizing human dynamics in video sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Recognition of human body motion using phase space constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The Visual Analysis of Human Movement: A SurveyComputer Vision and Image Understanding, 1999
- Movement, activity and action: the role of knowledge in the perception of motionPhilosophical Transactions Of The Royal Society B-Biological Sciences, 1997
- Learning the distribution of object trajectories for event recognitionImage and Vision Computing, 1996
- Dynamic programming algorithm optimization for spoken word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978