HAL: inria-00306723, version 1

See detailed view

BibTeX,EndNote,... BibTeX - EndNote - TEI - RefWorks -

IEEE international conference on image processing, Genes : Italie (2005)

An efficient Rao-Blackwellized particle filter for object tracking

Elise Arnaud 1, Etienne Memin 1

(2005)

In this paper we present a technique for the tracking of textured almost planar object. The target is modeled as a noisy planar cloud of points. The tracking is led with an appropriate non linear stochastic filter. The particular system that we devised is conditionally Gaussian and can be efficiently implemented through variance reduction principle known as Rao-Blackwellisation. Our model allows also to melt a correlation measurements with dynamic model estimated from the images. Such a cooperation within a stochastic filtering framework allows the tracker to be robust to occlusions and target's unpredictable changes of speed and direction. We demonstrate the efficiency of the tracker on different types of real world sequences

1:	VISTA (INRIA - IRISA)
	CNRS : UMR6074 – INRIA – Université de Rennes 1 – Institut National des Sciences Appliquées (INSA)

Domain

:

Computer Science/Image Processing

inria-00306723, version 1

http://hal.inria.fr/inria-00306723

oai:hal.inria.fr:inria-00306723

From: Elise Arnaud <>

Submitted on: Friday, 3 April 2009 14:12:33

Updated on: Monday, 19 March 2012 10:13:54