Region tracking through image sequences

Bénédicte Bascle 1 Rachid Deriche
1 ROBOTVIS - Computer Vision and Robotics
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This paper describes a new approach to the tracking of complex shapes through image sequences, that combines deformable region models and deformable contours. A new deformable region model is presented: its optimisation is based on texture correlation and is constrained by the use of a motion model, such as rigid, affine or homographic. The use of texture information (versus edge information) noticeably improves the tracking performances of deformable models in the presence of texture. Then the region contour is refined using an edge-based deformable model, in order to better deal with specularities and non planar objects. The method is illustrated and validated by experimental results on real images.
Type de document :
RR-2439, INRIA. 1994
Liste complète des métadonnées
Contributeur : Rapport de Recherche Inria <>
Soumis le : mercredi 24 mai 2006 - 14:50:08
Dernière modification le : samedi 27 janvier 2018 - 01:31:05
Document(s) archivé(s) le : mardi 12 avril 2011 - 16:15:13



  • HAL Id : inria-00074236, version 1



Bénédicte Bascle, Rachid Deriche. Region tracking through image sequences. RR-2439, INRIA. 1994. 〈inria-00074236〉



Consultations de la notice


Téléchargements de fichiers