Semi-automatic interpretation of buildings and settlement areas in user-generated spatial data

In recent times the amount of spatial data being collected by voluntary users, e.g. as part of the OpenStreetMap project, is rapidly increasing. Due to the fact, that everyone can participate in this social collaboration, the completeness and accuracy of the data is very heterogeneous. Although a object catalogue exists as part of the OSM project, users are not restricted which attributes they set and to which detail. Therefore the geometry of a feature is more reliable than its attributes. However, in order to use the data for analysis purposes, knowledge about the semantic contents is of importance. In our work, we propose an approach to classify spatial data solely based on geometric and topologic characteristics. We use both building outlines and road network information. In the first step, topology errors are fixed in order to create a consistent dataset. In the second step, we use unsupervised classification to separate buildings into clusters sharing the same characteristics. Including expert knowledge by visual inspection and interaction, some of these clusters are grouped together and semantically enriched. In the third step, we transfer the derived information from individual buildings to city blocks that are enclosed by edges of the road network. We evaluate our approach with test datasets from OSM and available authoritative datasets. Our results show, that enrichment of user-generated data is possible based on geometric and topologic feature characteristics.