Intuitive and Natural Interfaces for Geospatial Data Classification

Falko Schmid, Oliver Kutz, Lutz Frommberger, Till Mossakowski, Tomi Kauppinen, Cunyuan Cai

In: Maria Vasardani , Stephan Winter , Kai-Florian Richter , Krzysztof Janowicz , William Mackaness (Hrsg.). Proceedings of the International Workshop on Place-related Knowledge Acquisition Research. International Workshop on Place-Related Knowledge Acquisition Research (P-KAR-12) August 31 Kloster Seeon Germany Seiten 26-32 881 2012.


In the last decade, volunteered and participatory initiatives to create repositories of geo-spatial information gained overwhelming success. The most prominent and successful example of volunteered geographic information (VGI) is OpenStreetMap1 (OSM). In some parts of the world, OSM has a significantly larger data coverage, higher accuracy, and faster response to change than any other geospatial data set produced by public survey- ing agencies or companies. In general, in well-covered regions the quality and coverage of the OSM dataset is coequal to commercially available datasets. Furthermore, OSM offers the opportunity to collect data where no commercial datasets are available for lack of (commercial) interest, such as for example rural areas of developing countries. The great advantage of OSM data is the collection and provision by interested users.This method guarantees the collection not only of rather traditional data such as streets of different types, buildings, or natural features. OSM contains a large variety of particular data such as very fine-grained information about e.g. barriers or surface properties, thus providing information essential for creating assistance for e.g. disabled persons or athletes. This is a great advantage compared to offcial datasets: OSM contributors collect and share the information relevant to them and other users with similar interests. Such possibilities add enormous value to the freely available data, as it does not only map the street network, but potentially every spatial asset and facet of a place which is of interest to someone.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence