Urban GeoBIM Construction by Integrating Semantic LiDAR Point Clouds With as-Designed BIM Models

Developments in 3-D real worlds promote the integration of geoinformation and building information models (BIMs) known as GeoBIM. Light detection and ranging (LiDAR) integrated with global navigation satellite systems (GNSSs) can provide geo-referenced information at the urban scale. However, constructing detailed urban GeoBIM poses challenges in terms of LiDAR data quality. BIM models designed from software are fine on geometrical information but are often located in local coordinates and limited at an individual building level. In this study, we propose a complementary strategy to solve the contradiction between fine and large-scale construction of GeoBIM in urban scenes. A deep learning framework and graph theory are combined for LiDAR point cloud segmentation. Then, a coarse-to-fine matching program is developed to integrate building point clouds with corresponding BIM models. Results show that the overall segmentation accuracy of LiDAR datasets reaches up to 90%, and average positioning accuracies of building BIM models are 0.156 m, demonstrating the effectiveness of the method in segmentation and matching processes. This work offers a practical solution for rapid and accurate urban GeoBIM construction.