Space Classification from Point Clouds of Indoor Environments Based on Reconstructed Topology

Abstract

Reconstruction of as-built building models from point cloud data is a challenging problem with promising applications in the con-struction industry. In this paper, we outline the general concept of a da-ta processing pipeline that produces fully three-dimensional, semanti-cally rich and topologically valid as-built building models. Point cloud data is processed with a combination of histogram, voxel-based and RANSAC-based methods to detect surfaces of spaces and building components. Topological relations between building components (walls, slabs) are derived from a space partitioning that is generated from detected surfaces. The output from topology reconstruction is used as input for a space classification procedure which involves assigning functional properties to spaces. Each step in the data processing pipe-line is illustrated with examples. Limitations of the proposed approach are discussed and an outlook of future development in this area is given.

Reconstruction of as-built building models from point cloud data is a challenging problem with promising applications in the con-struction industry. In this paper, we outline the general concept of a da-ta processing pipeline that produces fully three-dimensional, semanti-cally rich and topologically valid as-built building models. Point cloud data is processed with a combination of histogram, voxel-based and RANSAC-based methods to detect surfaces of spaces and building components. Topological relations between building components (walls, slabs) are derived from a space partitioning that is generated from detected surfaces. The output from topology reconstruction is used as input for a space classification procedure which involves assigning functional properties to spaces. Each step in the data processing pipe-line is illustrated with examples. Limitations of the proposed approach are discussed and an outlook of future development in this area is given.