• search hit 6 of 54
Back to Result List

Towards automated digital building model generation from floorplans and on-site images

  • Digitalization of buildings has become increasingly relevant for processes such as construction or refurbishing. However, the lack of availability of digital building models is a common problem. In many cases, only printed floorplans and photos of the interior of a building are available. We propose a system to automatically generate enriched digital models from this data, consisting of two AI modules: one for 3D model reconstruction from 2D plans and one for 6D localization of images taken within a building in the corresponding 3D model. Such a model can facilitate tasks such as monitoring of the condition of a building or defects of its components. We demonstrate this pipeline using a real-world building, from which a plan and pictures of a floor are available, and show that good results can be achieved, with potential to greatly reduce the human effort normally required to create digital twins of buildings.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Niklas GardGND, Aleixo Cambeiro BarreiroGND
URN:urn:nbn:de:hbz:294-101322
DOI:https://doi.org/10.13154/294-10132
Parent Title (English):34th Forum Bauinformatik / 34. Forum Bauinformatik (Bochum, 06. - 08.09.2023)
Document Type:Part of a Book
Language:English
Date of Publication (online):2023/09/07
Date of first Publication:2023/09/07
Publishing Institution:Ruhr-Universität Bochum, Universitätsbibliothek
Tag:BIM
Floorplan Analysis; Localization; Pose Estimation
GND-Keyword:Deep learning
First Page:414
Last Page:422
Institutes/Facilities:Lehrstuhl für Informatik im Bauwesen
Dewey Decimal Classification:Technik, Medizin, angewandte Wissenschaften / Ingenieurbau, Umwelttechnik
open_access (DINI-Set):open_access
faculties:Fakultät für Bau- und Umweltingenieurwissenschaften
Konferenz-/Sammelbände:34th Forum Bauinformatik / 34. Forum Bauinformatik (Bochum, 06. - 08.09.2023)
Licence (German):License LogoCreative Commons - CC BY 4.0 - Namensnennung 4.0 International