Extraction of Building Ground Plans from Lidar Data

The goal of this research is to extract and delineate building ground plans from LIDAR data. Our approach consists of three steps: first of all, the raw point cloud has to be classified into terrain points and off-terrain points. Secondly, the off-terrain points (the potential buildings) have to be aggregated to form connected building blobs. Those blobs that exceed a certain size and have certain characteristics (e.g. consisting of planes) are supposed to be building candidates. For them, in a third step the outline is simplified. This is a generalization task, which has to take the characteristics of buildings into account to produce a meaningful 2D building shape. In the paper, these steps are described in detail. The focus lies on the different possibilities to generalize the building ground plans.