Robust real-time visual tracking: Comparison, theoretical analysis and performance evaluation

Andrew Comport 1 D. Kragic 2 E. Marchand 1 François Chaumette 1
1 Lagadic - Visual servoing in robotics, computer vision, and augmented reality
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 KTH - Royal Institute of Technology [Stockholm]
Abstract : In this paper, two real-time pose tracking algorithms of rigid objects are compared. Both methods are 3D-model based and are capable of calculating the pose between the camera and an object with a monocular vision system. Here, special consideration has been put on defining and evaluating different performance criteria such as computational efficiency, accuracy and robustness. Both methods are described and a unifying framework is derived. The main advantage of both algorithms lie in their real-time capabilities (on standard hardware) whilst being robust to miss-tracking, occlusion and changes in illumination.
Type de document :
Communication dans un congrès
IEEE Int. Conf. on Robotics and Automation, ICRA'05, 2005, Barcelona, Spain, France. pp.2852-2857, 2005
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/inria-00351885
Contributeur : Eric Marchand <>
Soumis le : lundi 12 janvier 2009 - 10:23:02
Dernière modification le : mercredi 16 mai 2018 - 11:23:03
Document(s) archivé(s) le : mardi 8 juin 2010 - 17:39:23

Fichier

2005_icra_comport.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : inria-00351885, version 1

Collections

INRIA | IRISA | IRISA-D5 | UR1-UFR-ISTIC | UNIV-RENNES

Citation

Andrew Comport, D. Kragic, E. Marchand, François Chaumette. Robust real-time visual tracking: Comparison, theoretical analysis and performance evaluation. IEEE Int. Conf. on Robotics and Automation, ICRA'05, 2005, Barcelona, Spain, France. pp.2852-2857, 2005. 〈inria-00351885〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

358

Téléchargements de fichiers

141

Contact


archive-ouverte@inria.fr