Digitalization of bridge inventory via automated analysis of point clouds for generation of BIM models

Building Information Modelling (BIM) is becoming increasingly prevalent in infrastructure asset management, as it facilitates current management practices. This includes the construction of BIM models for roads, rails, bridges, tunnels etc. Bridges are particularly challenging to digitalize due to their complex geometry. The manual construction of bridge BIM models based on 2D plans is hardly feasible due to the related workload. Given the recent advancements in the field of 3D surveying and artificial intelligence, new possibilities emerge for an automated generation of as‐is bridge BIM models.

This paper presents a novel, modular framework for the automatic processing of point clouds into as‐is BIM models, based on a fusion of artificial intelligence and heuristic algorithms. Representative bridge element datasets were provided to train neural network. Trained neural network can identify elements of a bridge, which are further processed using geometric algorithms into surface and solid bridge elements. This result can be additionally enriched with semantic information from existing databases. The final BIM models are exported in the standardized vendor‐free Industry Foundation Classes (IFC) format.