Semantic as-built 3D modeling of buildings under construction from laser-scan data based on local convexity without an as-planned model

Abstract

As-built building information models (BIMs) need to be represented with the composing building elements having their own functional semantic information. In order to generate such as-built BIMs with composing building elements, it is necessary to recognize each of the semantic elements and separate them from each other. In addition, the as-built BIM needs to be generated and updated during or after each major construction activity because most of the structural elements and nonstructural elements (especially for mechanical, electrical, and plumbing (MEP) components) are covered by other objects as the construction phase progresses. This study aims to propose a method for generating a semantic as-built BIM from laser-scan data acquired during the construction phase, especially for structural works. A field experiment was performed to validate the proposed method by acquiring and processing laserscan data from the construction site. The experimental result shows that the proposed method can be used for semantic as-built BIMs without any prior information from as-planned models.