Quantitative investigation on the accuracy and precision of Scan-to-BIM under different modelling scenarios

Accurate as-built information is required to operate, maintain, and adapt existing buildings. Scan-to-BIM has become a feasible approach for collecting and modelling 3D as-built information and has three phases: (1) scanning, (2) registration, and (3) modelling. This paper focuses on the modelling phase, which can currently be conducted either manually or semi-automatically. As-built conditions of a building are surveyed, and the geometry is modeled in a series of modelling scenarios. For each trial, geometric dimensions of the BIMs are compared to ground truth dimensions. This paper assesses the impact of levels of automation and modeller training on the accuracy and precision of generated BIMs. Quantitative models are developed for modelling scenarios using empirical datasets. Lastly, the impacts of degrees of accuracy are discussed. This study provides insight into the dimensional certainty of BIMs generated by Scan-to-BIM and helps decision-makers assess the risk of decisions made based on this information. •Accuracy and precision of scan-to-BIM is investigated for manual vs. automated techniques•Quantitative models are used to estimate the level of dimensional certainty for generated BIMs•Modeller training (i.e., standardizing the modelling approach) can improve accuracy by up to 260%•Primary building objects (e.g., walls) can yield larger errors in scan-to-BIM than for secondary objects (e.g., pipes)•The industry needs a unified system for certifying the level of accuracy in scan-to-BIM