Title :
Shape tracking based on switched dynamical models
Author :
Marques, Jorge S. ; Lemos, Joao M.
Author_Institution :
IST/ISR, Lisbon, Portugal
Abstract :
Object tracking based on multipole models has been previously advocated as a way to tackle sudden changes of shape or motion parameters. The paper addresses the estimation of time-varying parameters described by a bank of stochastic models switched according to a probabilistic mechanism (Markov chain). A state estimation algorithm is proposed, based on the propagation of Gaussian mixtures in a multi-model framework.
Keywords :
Gaussian processes; Markov processes; image sequences; motion estimation; tracking; video signal processing; Gaussian mixtures propagation; Markov chain; motion parameters; multi-model framework; multipole models; object tracking; probabilistic mechanism; shape parameters; shape tracking; state estimation algorithm; stochastic models; switched dynamical models; time-varying parameters estimation; video sequences; Density functional theory; Equations; Filters; Gaussian distribution; Image analysis; Integrated circuit modeling; Shape; Stochastic processes; Target tracking; Yttrium;
Conference_Titel :
Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-5467-2
DOI :
10.1109/ICIP.1999.823039
