Skip to Main content Skip to Navigation
Reports

Learning Switching Dynamic Models for Objects Tracking

Gilles Celeux 1 Jorge Marques 1 Jacinto Nascimento 1
1 IS2 - Statistical Inference for Industry and Health
Inria Grenoble - Rhône-Alpes, LBBE - Laboratoire de Biométrie et Biologie Evolutive - UMR 5558
Abstract : Many recent tracking algorithms rely on model learning methods. A promising approach consists of modelling the object motion with switching autoregressive models. This article is involved with parametric switching dynamical models governed by an hidden Markov chain. The maximum likelihood estimation of the parameters of those models is described. The formulas of the EM algorithm are detailed. Moreover, the problem of choosing a good and parsimonious model with BIC criterion is considered. Emphasis is put on choosing a reasonable number of hidden states. Numerical experiments on both simulated and real data sets highlight the ability of this approach to describe properly object motions with sudden changes. The two appplications on real data concern object and heart tracking.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00071720
Contributor : Rapport de Recherche Inria <>
Submitted on : Tuesday, May 23, 2006 - 6:36:17 PM
Last modification on : Monday, February 10, 2020 - 4:36:45 PM
Long-term archiving on: : Sunday, April 4, 2010 - 10:34:58 PM

Identifiers

  • HAL Id : inria-00071720, version 1

Collections

Citation

Gilles Celeux, Jorge Marques, Jacinto Nascimento. Learning Switching Dynamic Models for Objects Tracking. [Research Report] RR-4863, INRIA. 2003. ⟨inria-00071720⟩

Share

Metrics

Record views

220

Files downloads

499