BIM reconstruction from 3D point clouds: A semantic registration approach based on multimodal optimization and architectural design knowledge

Abstract

Reconstructing semantically rich building information model (BIM) from 2D images or 3D point clouds represents a research realm that is gaining increasing popularity in architecture, engineering, and construction. Researchers have found that architectural design knowledge, such as symmetry, planarity, parallelism, and orthogonality, can be utilized to improve the effectiveness of such BIM reconstruction. Following this line of enquiry, this paper aims to develop a novel semantic registration approach for complicated scenes with repetitive, irregular-shaped objects. The approach first formulates the architectural repetition as the multimodality in mathematics. Thus, the reconstruction of repetitive objects becomes a multimodal optimization (MMO) problem of registering BIM components which have accurate geometries and rich semantics. Then, the topological information about repetition and symmetry in the reconstructed BIM is recognized and regularized for BIM semantic enrichment. A university lecture hall case, consisting of 1.9 million noisy points of 293 chairs, was selected for an experiment to validate the proposed approach. Experimental results showed that a BIM was satisfactorily created (achieving about 90% precision and recall) automatically in 926.6 s; and an even more satisfactory BIM achieved 99.3% precision and 98.0% recall with detected semantic and topological information under the minimal effort of human intervention in 228.4 s. The multimodality model of repetitive objects, the repetition detection and regularization for BIM, and satisfactory reconstruction results in the presented approach can contribute to methodologies and practices in multiple disciplines related to BIM and smart city.