Title :
Tracking nonstationary targets using a dynamical system with Markov-modulated parameters
Author :
Ramsay, Gordon ; Deng, Li
Author_Institution :
Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
Abstract :
Tracking moving targets from partial measurements is an important problem with applications in control theory and pattern recognition. This letter presents a statistical framework for modeling target motion as the output of a linear dynamical system driven by a random step function representing sequences of idealized target positions. Target trajectories are observed through a noisy nonlinear measurement function, whereas system parameters are modulated by a semi-Markov chain representing changes in target regime. An algorithm is presented for maximum-likelihood parameter estimation from a corpus of observations, and potential applications to articulatory speech recognition are discussed.<>
Keywords :
Markov processes; maximum likelihood estimation; pattern recognition; speech recognition; target tracking; Markov-modulated parameters; articulatory speech recognition; control theory; linear dynamical system; maximum-likelihood parameter estimation; moving target tracking; noisy nonlinear measurement function; nonstationary targets; pattern recognition; random step function; semi-Markov chain; statistical framework; system parameters; target trajectories; Control systems; Control theory; Extraterrestrial measurements; Linear systems; Noise measurement; Parameter estimation; Pattern recognition; Position measurement; Target tracking; Trajectory;
Journal_Title :
Signal Processing Letters, IEEE
