Semantic decomposition and recognition of indoor spaces with structural constraints for 3D indoor modelling

Recent developments in laser scanning systems have inspired substantial interest in indoor modelling. Considering the cellular nature (i.e., rooms) of indoor spaces, recent studies have often reconstructed 3D indoor models from point clouds in heavily occluded environments by room space decomposition. However, recent space decomposition methods have excluded connection spaces (e.g., doors) and neglected the fact that room spaces are connected by connection spaces. These methods have thus failed to determine the correct room spaces in the case of unclear wall constraints from point clouds. Difficulties also arise from modelling stair connection spaces when the method is extended to a multi-storey environment. In this study, the semantic structural constraints of architectural components are defined. Three-dimensional indoor modelling from point clouds is cast as indoor space decomposition and recognition with structural constraints. The room space decomposition method is improved using wall structural constraints to effectively decompose the room space. The connection spaces, including wall connection spaces and stair connection spaces, are recognized from point clouds to generate a unified 3D indoor model. The proposed method is verified with two synthetic and four real-world datasets. The results indicate that the proposed method is reliable and accurate, especially for complex and large-scale indoor scenes.