Scene structure registration for localization and mapping - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Robotics and Autonomous Systems Année : 2016

Scene structure registration for localization and mapping

Résumé

Image registration, and more generally scene registration, needs to be solved in mobile robotics for a number of tasks including localization, mapping, object recognition, visual odometry and loop-closure. This paper presents a flexible strategy to register scenes based on its planar structure, which can be used with different sensors that acquire 3D data like LIDAR, time-of-flight cameras, RGB-D sensors and stereo vision. The proposed strategy is based on the segmentation of the planar surfaces from the scene, and its representation using a graph which stores the geometric relationships between neighbouring planar patches. Uncertainty information from the planar patches is exploited in a hierarchical fashion to improve both the robustness and the efficiency of registration. Quick registration is achieved in indoor structured scenarios, offering advantages like a compact representation, and flexibility to adapt to different environments and sensors. Our method is validated with different sensors: a hand-held RGB-D camera and an omni-directional RGB-D sensor; and for different applications: from visual-range odometry to loop closure and SLAM.
Fichier principal
Vignette du fichier
Registration of scene structure for SLAM.pdf (3.39 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01237845 , version 1 (03-12-2015)

Identifiants

Citer

Eduardo Fernández-Moral, Patrick Rives, Vicente Arévalo, Javier González-Jiménez. Scene structure registration for localization and mapping. Robotics and Autonomous Systems, 2016, 75 (B), pp.649-660. ⟨10.1016/j.robot.2015.09.009⟩. ⟨hal-01237845⟩
390 Consultations
460 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More