Building Detection and Structure Line Extraction from Airborne Lidar Data

The development of LIDAR (Light Detection and Ranging) system makes the acquisition of 3D surface information more convenient and immediate than other geomatics technologies. However, the 3D coordinates of the surface features, such as the corners, edges and planes of buildings, cannot be obtained directly from the LIDAR data because of its blind characteristics. How to detect the feature locations effectively and further to reconstruct the building from the LIDAR point clouds becomes one of the most important applications and study issues. For this reason, an approach for building detection and feature lines extraction from airborne LiDAR data is proposed in this paper. The building detection is based on wavelet transform and geometric properties of buildings, and the extraction of feature lines is based on Hough transform and image processing. For data-driven building reconstruction, the feature lines are essential to reconstruct the roof models. The basic idea of the proposed approach is to detect the location of each single building in the raw LiDAR data firstly. Then, the initial feature lines which are divided into external contour lines and internal structure lines are extracted respectively. These structure lines could be provided as the features for data-driven building reconstruction. The experiment results showed that the feature lines of regular and simple roofs such as rectangle roofs, gabled roofs and L-type roofs could be extracted successfully. * Corresponding author.