AUTHOR=Schatz Yohann , Domer Bernd 

TITLE=Semi-automated creation of IFC bridge models from point clouds for maintenance applications

JOURNAL=Frontiers in Built Environment

VOLUME=Volume 10 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/built-environment/articles/10.3389/fbuil.2024.1375873

DOI=10.3389/fbuil.2024.1375873

ISSN=2297-3362

ABSTRACT=Bridge maintenance activities benefit from digital models, provided in the interoperable IFC format. Such a model, enriched with up-to-date information, is an enabler for a wide range of applications. It opens new perspectives in asset information management. However, the manual creation of a digital replica, representing the actual state of the asset from point cloud data, is timeconsuming. Consequently, process automation is of particular interest. This paper proposes a systematic, semi-automatic approach for creating IFC bridge models from point clouds. It introduces new methods for semantic segmentation and 3D shape modeling. A case study demonstrates the feasibility of the process in practice. Compared to other solutions, proposed methods are robust when dealing with incomplete point clouds.Essentially, a digital twin refers to a Building Information Modeling (BIM) model that accurately represents the physical asset and includes up-to-date information. Creating DT from archived construction documentation is labor-intensive, as not only the as-built situation but also information about modifications applied during the lifecycle of a bridge as well as inspection reports must be considered. In addition, available documents might be incomplete or incorrect and should be validated with the asset on site. It is obvious that a DT should be established based on the current state of the structure. Point Cloud Data (PCD), generated through laser scanning and photogrammetry, are good candidates. Point clouds accurately reflect the actual geometrical and topological conditions of an asset (Vilgertshofer et al., 2023). Consequently, generating a DT from PCD ensures it has a true geometry (Vilgertshofer et al., 2023;Tang et al., 2010). Additionally, PCD can be used to highlight movements and deformations by comparing point clouds created at different times. Furthermore, when combined with images, PCD enable automated detection and analysis of defects (