Using Visual Saliency for Object Tracking with Particle Filters

Désiré Sidibé (1) , David Fofi (1) , Fabrice Mériaudeau (1)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]

This paper presents a robust tracking method based on the integration of visual saliency information into the particle filter framework. While particle filter has been successfully used for tracking non-rigid objects, it shows poor performances in the presence of large illumination variation, occlusions and when the target object and background have similar color distributions. We show that considering saliency information significantly improves the performance of particle filter based tracking. In particular, the proposed method is robust against occlusion and large illumination variation while requiring a reduced number of particles. Experimental results demonstrate the efficiency and effectiveness of our approach.

Mots clés: visual saliency; tracking; particle filters

Domaines: Informatique [cs]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Désiré Sidibé, David Fofi, Fabrice Mériaudeau. Using Visual Saliency for Object Tracking with Particle Filters. EUSIPCO 2010. 18th European Signal Processing Conference, Jul 2010, Aalborg, Denmark. pp.1776-1780. ⟨hal-00584682⟩