Automatic As-is 3D Building Models Creation from Unorganized Point Clouds

Building information models (BIMs) increasingly are applied throughout a building's life cycle for various applications, such as building renovation, energy simulation, and performance analysis in the architecture, engineering construction, and facility management (AEC/FM) domain. In a traditional approach, as-is BIM is primarily manually created from point clouds, which is labor intensive, costly, and time consuming. This paper introduces a method to create as-is 3D building models automatically from an unorganized point cloud collected by a 3D laser scanner. The collected raw data are downsized and segmented to individual plane segments. Then, boundary estimation method and building component recognition methods are applied to recognize all building components as individual objects and visualize them as polygons. The proposed method was tested on outdoor point cloud data to validate its feasibility and evaluate its performance. The analyzed results showed that the proposed method would simplify and accelerate the as-is building model creation process.