Skip to Main content Skip to Navigation
Conference papers

Reconstruction of the 3D Structure of a Building from the 2D Drawings of its Floors

Philippe Dosch 1 Gérald Masini 1
1 ISA - Models, algorithms and geometry for computer graphics and vision
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This article presents our first results in reconstructing the 3D structure of a building using primitives delivered by the analysis of the 2D architectural drawings of its floors. A set of features is extracted from the set of architectural symbols available for each floor. A graph of matching hypothesis between the most pertinent features of two consecutive floors is then constructed. A maximal clique detection algorithm supplies the best set of matches. The geometrical transformation allowing each floor to be aligned with respect to its lower floor is computed from the pairs of matching features. The final 3D model of the building is obtained by heaping the 3D models of the consecutive floors. || Cet article présente nos premiers résultats dans la reconstruction de la structure 3D d'un bâtiment en utilisant les primitives issues de l'analyse des plans architecturaux 2D de ses niveaux. Un ensemble d'indices est extrait à partir de l'ensemble des sy
Document type :
Conference papers
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/inria-00098758
Contributor : Publications Loria <>
Submitted on : Tuesday, September 26, 2006 - 8:33:37 AM
Last modification on : Friday, February 26, 2021 - 3:28:04 PM
Long-term archiving on: : Wednesday, March 29, 2017 - 12:35:34 PM

Identifiers

  • HAL Id : inria-00098758, version 1

Collections

Citation

Philippe Dosch, Gérald Masini. Reconstruction of the 3D Structure of a Building from the 2D Drawings of its Floors. Fifth International Conference on Document Analysis & Recognition, International Association for Pattern Recognition, 1999, Bangalore, Inde, pp.487-490. ⟨inria-00098758⟩

Share

Metrics

Record views

174

Files downloads

439