Automatic extraction of building features from terrestrial laser scanning

Abstract

Realistic 3D city models are required for many purposes such as urban planning and safety analysis. The traditional modeling methods are mainly based on manual or semi-automatic reconstruction from close-range images, which are rather time-consuming. The lack of fully automatic reconstruction is mainly due to the difficulty to recover building structures from close-range images. The terrestrially scanned laser points usually contain useful information, and it can be a valuable data source for reconstructing 3D city models. This paper presents our approach to automatically extract building features from terrestrial laser scanned data. This is done by first processing the terrestrial laser points with various segmentation algorithms, then retrieving several important properties (size, position, direction, topology, etc.) from the segments, and finally recognizing potential building features (walls, windows and doors, etc.) with feature constraints, which are based on the properties of segments. The recognized features will form the basis for an automatic 3D building model reconstruction framework. 1