Publications / 2004 Proceedings of the 21st ISARC, Jeju, South Korea

Human-Assisted 3D Spatial Modeling of Construction Sites Using Sparse Range-Point Clouds

Changwan Kim, Carl T. Haas, Katherine A. Liapi

3D spatial-modeling can be used in various safety-enhancement applications and for as-built data acquisition in project-control systems. The objective of the research reported herein was to provide spatialmodeling methods that represent construction sites in an efficient manner and to validate the proposed methods by testing them in an actual construction environment. Algorithms to construct construction-site scenes and to carry out coordinate transformations in order to merge data from different acquisition locations are presented. Field experiments were conducted to establish performance parameters and validation for the proposed methods and models. Initial experimental work has demonstrated the feasibility of this approach.

Keywords: Sparse range-point cloud, 3D spatial-modeling, convex hull, workspace partitioning