A greyscale voxel model for airborne lidar data applied to building detection

The existing binary voxel model algorithm for 3D building detection (3BD) from airborne lidar cannot distinguish between connected buildings and non-buildings. As a result, a greyscale voxel structure model, using the discretised mean intensity of lidar points, is presented to support subsequent building detection in areas where buildings are adjacent to non-buildings but with different greyscales. The resulting 3BD algorithm first detects a building roof by selecting voxels characterised by a jump in elevation as seeds, labelling them and their 3D connected regions as rooftop voxels. Then voxels which fall into buffers and possess similar greyscales to that of the corresponding building outline are assigned as building facades. The results for detected buildings are evaluated using lidar data with different densities and demonstrate a high rate of success.