PriSeg: IFC-supported Primitive Instance Geometry Segmentation with Unsupervised Clustering

Abstract

One of the societal problems for current building construction projects is the lack of timely progress monitoring and quality control, causing over-budget costs, inefficient productivity, and poor performance. This paper addresses the challenge of high-accuracy primitive instance segmentation from point clouds with the support of IFC model as a core stage to facilitate maintaining a geometric digital twin during the construction stage. Keeping the geometry of a building digital twin dynamic and up-to-date will help monitor and control the progress and quality timely and efficiently. We propose a novel automatic method named Priseg to detect and segment the entire points corresponding to the as-designed instance by developing an IFC-based instance descriptor and unsupervised clustering algorithm. The proposed solution is robust in real complex environments, such as point clouds are noisy with high occlusions and clutter, the as-built status deviates from the as-designed model in terms of position, orientation, and scale.