ABSTRACT
Updating point cloud data into a building information model (BIM) is a new, efficient and fine management method for monitoring construction and operation status. The accurate segmentation, modelling method and implementation process of the unit point cloud based on the BIM model are proposed. First, we use a clustering algorithm to cluster point clouds based on the geometric information of building elements in the BIM model and give them different semantic information; Then, the coarse extraction of various planes is realized by the region growth algorithm, and the fine segmentation of adjacent planes is realized by combining the distance algorithm of boundary points; Finally, ABM indoor is used to model the segmented data based on the three-dimensional triangle algorithm and associate it with the component semantic information in BIM, so as to achieve a high degree of coordination between the two types of data. Taking a substation project under construction as an example, the proposed method is used to scan, segment and model the substation structure under construction. The engineering application results show that this method can automatically segment and model the plane according to the BIM model element information. The segmentation accuracy is higher than that of the traditional method, which has strong practical value.
