Reconstruction of the 3D structure of a building from the 2D drawings of its floors

Author

Dosch, Philippe ; Masini, Gérald

Author_Institution

LORIA, CNRS, Vandoeuvre-les-Nancy, France

fYear

1999

fDate

20-22 Sep 1999

Firstpage

487

Lastpage

490

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 hypotheses 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

Keywords

architectural CAD; document image processing; engineering graphics; feature extraction; image matching; image reconstruction; stereo image processing; 2D architectural drawings; 3D model heaping; 3D structure reconstruction; architectural symbols; building; feature extraction; floor alignment; floors; geometrical transformation; matching features; matching hypothesis graph; maximal clique detection algorithm; primitives; Buildings; Electrical capacitance tomography; Floors; Graphics; Image reconstruction; Image segmentation; Libraries; Read only memory; Software systems; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on

Conference_Location

Bangalore

Print_ISBN

0-7695-0318-7

Type

conf

DOI

10.1109/ICDAR.1999.791831

Filename

791831