Cost-effective reconstruction of BIM from 2D scanned plan : experiments on existing buildings

Lucile Gimenez (1) , Sylvain Robert (1) , Frédéric Suard (1) , Khaldoun Zreik (2)

1 LADIS - Laboratoire d'analyse des données et d'intelligence des systèmes
2 PARAGRAPHE - Laboratoire Paragraphe

The overall energy efficiency of existing buildings has to be significantly improved to comply with emerging regulations and to contribute to overcoming current environmental challenges. The effectiveness of renovation actions could be significantly enhanced through the systematic use of Information and Communication Technologies (ICT) tools and Building Information Modeling (BIM). But these solutions rely on full-fledged digital models, which, for most buildings, are not available. This paper gives an overview of the semi-automatic generation process of 3D models from existing buildings developed by combining 2D scanned plan recognition with assisted human interventions. The implemented process is able to extract information from 2D plans and to generate IFC (Industry Foundation Classes)-compliant 3D models that include the main components of the building: walls, openings, and spaces. This paper also highlights the extension of the methodology to cope with additional drawing conventions and to allow for more genericity. The results obtained with experiments on plans of existing buildings are encouraging and suggest that the mix of software assistance and focused human interventions may be a good trade-off for the quality of the resulting models.

Keywords: Building Information Modeling (BIM); Image processing; 3D building models; 3D reconstruction; model checking

Domains: Library and information sciences; Artificial Intelligence [cs.AI]; Modeling and Simulation

Lucile Gimenez, Sylvain Robert, Frédéric Suard, Khaldoun Zreik. Cost-effective reconstruction of BIM from 2D scanned plan : experiments on existing buildings. Sustainable Places 2015, Sep 2015, Savona, Italy. pp.68-77. ⟨hal-02109541⟩