Automatic extraction of 3d building meshes from LiDAR data

Abstract

Terrestrial laser scanning and drone-based scanning are often combined to gain a complete picture of the external envelopes of buildings. While the resulting data sets are easy to understand for humans, extracting any semantical information from the data is a challenging task. Creating a BIM model for large cities is desirable, especially for planning and inventory purposes. Nowadays, engineers manually separate buildings and draw corresponding floor plans or any other required entities, making creating such a model nearly impossible for the whole city.
In this contribution, we present the design and concept of a C++ library that provides fundamental algorithmic tools for automated detection of the ground points, separation of buildings into individual point clouds, and segmentation of walls and roofs. The buildings’ 3D model (both volumetric and surface mesh) can be constructed using the data. Furthermore, the building area and volume calculation can be performed on such a model, which can then be compared with the existing city plan.