Indoor Scene Reconstruction using Feature Sensitive Primitive Extraction and Graph-cut - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue ISPRS Journal of Photogrammetry and Remote Sensing Année : 2014

Indoor Scene Reconstruction using Feature Sensitive Primitive Extraction and Graph-cut

Sven Oesau
  • Fonction : Auteur
  • PersonId : 941905
Florent Lafarge
  • Fonction : Auteur
  • PersonId : 833647
Pierre Alliez

Résumé

We present a method for automatic reconstruction of permanent structures, such as walls, doors and ceilings, given a raw point cloud of an indoor scene. The main idea behind our approach is a graph-cut formulation to solve an inside/outside labeling of a space partitioning. We rst partition the space in order to align the reconstructed models with permanent structures. The horizontal structures are located through analysis of the vertical point distribution, while vertical wall structures are detected through feature preserving multi-scale line tting, followed by clustering in a Hough transform space. The nal surface is extracted through a graph-cut formulation that trades faithfulness to measurement data for geometric complexity. A series of experiments show watertight surface meshes reconstructed from point clouds measured on multi-level buildings.
Fichier principal
Vignette du fichier
journal.pdf (1.97 Mo) Télécharger le fichier
Vignette du fichier
eulerResult2.png (1017.02 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-00980804 , version 1 (18-04-2014)

Identifiants

Citer

Sven Oesau, Florent Lafarge, Pierre Alliez. Indoor Scene Reconstruction using Feature Sensitive Primitive Extraction and Graph-cut. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 90, pp.68-82. ⟨10.1016/j.isprsjprs.2014.02.004⟩. ⟨hal-00980804⟩

Collections

INRIA INRIA2
602 Consultations
3954 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More