Dense Accurate Urban Mapping from Spherical RGB-D Images

Renato Martins 1 Eduardo Fernandez-Moral 1 Patrick Rives 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
Abstract : — This paper presents a methodology to combine information from a sequence of RGB-D spherical views acquired by a home-made multi-stereo device in order to improve the computed depth images both in terms of accuracy and completeness. This methodology is embedded in a larger visual mapping framework aiming to produce accurate and dense topometric urban maps. Our method is based on two main filtering stages. Firstly, we perform a segmentation process considering both geometric and photometric image constraints, followed by a regularization step (spatial-integration). We then proceed to a fusion stage where the geometric information is further refined by considering the depth images of nearby frames (temporal integration). This methodology can be applied to other projective models, such as perspective stereo images. Our approach is evaluated within the frameworks of image registration, localization and mapping, demonstrating higher accuracy and larger convergence domains over different datasets.
Type de document :
Communication dans un congrès
IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS'15, Sep 2015, Hamburg, Germany. 2015
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01237848
Contributeur : Eric Marchand <>
Soumis le : jeudi 3 décembre 2015 - 18:18:48
Dernière modification le : mercredi 16 mai 2018 - 11:23:03
Document(s) archivé(s) le : vendredi 4 mars 2016 - 15:00:15

Fichier

2015_iros_martin.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01237848, version 1

Citation

Renato Martins, Eduardo Fernandez-Moral, Patrick Rives. Dense Accurate Urban Mapping from Spherical RGB-D Images. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS'15, Sep 2015, Hamburg, Germany. 2015. 〈hal-01237848〉

Partager

Métriques

Consultations de la notice

570

Téléchargements de fichiers

149