Target Graph Matching for Building Reconstruction

We present a building reconstruction approach, which is based on a target graph matching algorithm to relate laser data with building models. Establishing this relation is important for adding building knowledge to the data. Our targets are topological representations of the most common roof structures which are stored in a database. Laser data is segmented into planar patches. Topological relations between segments, in terms of intersection lines and height jumps, are represented in a building roof graph. This graph is matched with the graphs from the database. Segments and intersection lines that do not fit to an existing target roof topology will be removed from the automated reconstruction approach. For the geometric reconstruction our approach is flexible to use information from data and/or model. For specific object parts it might be better to use model constraints as the data might not appropriately represent the object. As our approach combines data and model driven techniques, we speak of an object driven reconstruction approach. We present our algorithm using airborne laser scanner data with about 15 pts/m. Existing 2D map data with scale 1:1000 has been used for selection of building segments, for outlining flat building roofs and to reconstruct walls.