Unsupervised trajectory pattern classification using hierarchical Dirichlet Process Mixture hidden Markov model
Vahid Bastani, Lucio Marcenaro, Carlo S. Regazzoni · 2014
In this paper we present a trajectory clustering method based on nonparametric Bayesian approach proposed for analyzing dynamic systems. Our method uses a modified hierarchical Dirichlet process-hidden Markov model in order to learn trajectory patterns into its parameter variables in an unsupervised way. Due to inherited Bayesian structure, this model resolves some limitations in trajectory clustering problem such as sequential analysis, incremental learning and non-uniform sampling. In this paper we introduce this model and its learning algorithm and finally we evaluate its performance.