Building reconstruction from a single DEM - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Building reconstruction from a single DEM

Florent Lafarge
  • Fonction : Auteur
  • PersonId : 833647
Xavier Descombes
Josiane Zerubia
  • Fonction : Auteur
  • PersonId : 833424

Résumé

We present a new approach for building reconstruction from a single Digital Elevation Model (DEM). It treats buildings as an assemblage of simple urban structures extracted from a library of 3D parametric blocks (like a LEGO set). This method works on various data resolutions such as 0.7 m satellite and 0.1 m aerial DEMs and allows us to obtain 3D representations with various levels of detail. First, the 2D supports of the urban structures are extracted either interactively or automatically. Then, 3D blocks are placed on the 2D supports using a Gibbs model. A Bayesian decision finds the optimal configuration of 3D blocks using a RJMCMC sampler. Experimental results on complex buildings and dense urban areas are presented using data at various resolutions
Fichier principal
Vignette du fichier
2008_lafarge_cvpr08.pdf (2.95 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00781733 , version 1 (28-01-2013)

Identifiants

  • HAL Id : hal-00781733 , version 1

Citer

Florent Lafarge, Xavier Descombes, Josiane Zerubia, Marc Pierrot-Deseilligny. Building reconstruction from a single DEM. Computer Vision and Pattern Recognition (CVPR), Jun 2008, Anchorage, United States. ⟨hal-00781733⟩
237 Consultations
358 Téléchargements

Partager

Gmail Facebook X LinkedIn More