Combining Odometry and Visual Loop-Closure Detection for Consistent Topo-Metrical Mapping - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Combining Odometry and Visual Loop-Closure Detection for Consistent Topo-Metrical Mapping

Résumé

We address the problem of simultaneous localization and mapping (SLAM) by combining visual loop-closure detection with metrical information given by a robot odometry. The proposed algorithm extends a purely appearance-based loopclosure detection method based on bags of visual words which is able to detect when the robot has returned back to a previously visited place. An efficient optimization algorithm is used to integrate odometry information in this method to generate a consistent topo-metrical map. The resulting algorithm which only requires a monocular camera and odometry data and is simple, and robust without requiring any a priori information on the environment.
Fichier principal
Vignette du fichier
Bazeille_COGIS09.pdf (472.71 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00652602 , version 1 (15-12-2011)

Identifiants

Citer

Stéphane Bazeille, David Filliat. Combining Odometry and Visual Loop-Closure Detection for Consistent Topo-Metrical Mapping. Conference on COGnitive systems with Interactive Sensors (COGIS2009), 2009, France. pp.1, ⟨10.1051/ro/2010021⟩. ⟨hal-00652602⟩

Collections

ENSTA ENSTA_U2IS
107 Consultations
442 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More