Segmentation of Façades from Urban 3D Point Clouds using Geometrical and Morphological Attribute-based Operators

Abstract : 3D building segmentation is an important research issue in the remote sensing community with relevant applications to urban modeling, cloud-to-cloud and cloud-to-model registration, 3D cartography, virtual reality, cultural heritage documentation, among others. In this paper, we propose automatic, parametric and robust approaches to segment façades from 3D point clouds. Processing is carried out using elevation images and 3D decomposition, and the final result can be reprojected onto the 3D point cloud for visualization or evaluation purposes. Our methods are based on geometrical and geodesic constraints. Parameters are related to urban and architectural constraints. Thus, they can be set up to manage façades of any height, length and elongation. We propose two methods based on façade marker extraction and a third method without markers based on the maximal elongation image. This work is developed in the framework of TerraMobilita project [1]. The performance of our methods is proved in our experiments on TerraMobilita databases using 2D and 3D ground truth annotations.
Type de document :
Article dans une revue
ISPRS International Journal of Geo-Information, MDPI, 2016, ISPRS International Journal of Geo-Information, 5 (1), <http://www.mdpi.com/2220-9964/5/1/6>. <10.3390/ijgi5010006>
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-01254284
Contributeur : Beatriz Marcotegui <>
Soumis le : mardi 3 janvier 2017 - 17:36:01
Dernière modification le : mardi 12 septembre 2017 - 11:41:31
Document(s) archivé(s) le : mardi 4 avril 2017 - 12:02:16

Fichier

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

Identifiants

Collections

Citation

Andrés Serna, Beatriz Marcotegui, Jorge Hernández. Segmentation of Façades from Urban 3D Point Clouds using Geometrical and Morphological Attribute-based Operators. ISPRS International Journal of Geo-Information, MDPI, 2016, ISPRS International Journal of Geo-Information, 5 (1), <http://www.mdpi.com/2220-9964/5/1/6>. <10.3390/ijgi5010006>. <hal-01254284>

Partager

Métriques

Consultations de
la notice

57

Téléchargements du document

35