From Point Clouds to Definitions of Architectural Space: Potentials of Automated Extraction of Semantic Information from Point Clouds for the Building Profession

Regarding interior building topology as an important aspect in building design and management, several approaches to indoor point cloud structuring have been introduced recently. Apart from a high-level semantic segmentation of the formerly unstructured point clouds into stories and rooms, these methods additionally allow the extraction of attributed graphs in which nodes represent rooms (including room properties like area or height), and edges represent connections between rooms (doors or staircases) or indicate neighborhood relationships (separation by walls). In this paper, we investigate possible applications of these approaches in architectural design and building management and comment on the possible benefits for the building profession. While contemporary practice of spatial arrangement is predominantly based on the manual iteration of spatial topologies, we show that the segmentation of buildings in spaces along with the untraditional more abstract graph-based representations can be used for design, management and navigation within building structures.