Recovering the Shape of Objects in 3D Point Clouds with Partial Occlusions

Rudolph Triebel 1, 2 Wolfram Burgard 1
1 Department of Computer Science [Freiburg]
2 ASL - Autonomous Systems Lab
Abstract : In this paper we present an approach to label data points in 3d range scans and to use these labels to learn prototypical representations of objects. Our approach uses associative Markov networks (AMNs) to calculate the labels and a clustering operation to determine the prototypes of homogeneously labeled regions. These prototypes are then used to replace the original regions. In this way, we obtain more accurate models and additionally are able to recover the structure of partially occluded objects. Our approach has been implemented and evaluated on 3d data of a building acquired with a mobile robot. The experimental results demonstrate that our algorithm can robustly identify objects with the same shape and can use the prototypes of these objects for highly accurate mesh completion in case of occlusions.
Type de document :
Communication dans un congrès
6th International Conference on Field and Service Robotics - FSR 2007, Jul 2007, Chamonix, France. Springer, 42, 2007, Springer Tracts in Advanced Robotics
Liste complète des métadonnées
https://hal.inria.fr/inria-00270411
Contributeur : Inria Rhône-Alpes Documentation <>
Soumis le : vendredi 4 avril 2008 - 16:07:23
Dernière modification le : vendredi 4 avril 2008 - 16:14:47
Document(s) archivé(s) le : vendredi 21 mai 2010 - 01:21:59

Fichier

fsr_22.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00270411, version 1

Collections

FSR2007

Citation

Rudolph Triebel, Wolfram Burgard. Recovering the Shape of Objects in 3D Point Clouds with Partial Occlusions. 6th International Conference on Field and Service Robotics - FSR 2007, Jul 2007, Chamonix, France. Springer, 42, 2007, Springer Tracts in Advanced Robotics. 〈inria-00270411〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

54

Téléchargements de fichiers

103

Contact


archive-ouverte@inria.fr