Klassifikation von Gebäudetypen - Analyse von Landbedeckungsdaten und Liegenschaftsgrenzen zur Identifikation von Bauweisen

Kristin Kalian

Publikation: AbschlussarbeitMasterarbeit


For questions in the context of spatial planning, urban settlement monitoring using remote sensing data is essential. The location of various building types, reserved areas, and their future demand in urban settlements are integral information for regional policy. Land cover data represent an important basis for the fulfillment of numerous analyses. Austria has a long tradition regarding the application of land use data, however most of the available data sets do not meet today´s requirements and have become outdated. The objective of this study is to develop a method which permits identification of different building types. Eight categories were chosen for the classification: detached house, semi-detached house, terraced house, apartment building, perimeter block development, large storage building (typical for industry/trade), high-rise building, and adjoining building. The methodology relies on integrating location, surface, and height parameters from the buildings of the land cover data with plot boundaries from the cadaster. The combination of these data enables the derivation of building structures, from open to closed coverage types. The differentiation of semi-detached and terraced houses can only be achieved by the integration of plot boundaries. Additional parameters are footprint and number of buildings in each plot boundary, as well as the green-area ratio. Small building objects of less than 35 m² are eliminated from the data set. Implementation in GIS starts with an intersection of land cover data with the plot boundaries and proceeds with a spatial join in order to get information from both data sets. The final classification is based on predefined rules referring to a set of selected parameters for each building type. Applying this rule set to the study area results in a total coverage of over 97,95% leaving less than 2,05% of the buildings unclassified. Accuracy assessment is based on a random sample of 10% of all buildings, indicating that 88,07% of the building objects are classified correctly. The test area covers a part of Klagenfurt, Carinthia, including the quarter Annabichl - Welzenegg - St. Peter. The result of the classification approach is a model, which was implemented in ArcGIS 9.2 and tested on LISA (Land Information System Austria) data.
Gradverleihende Hochschule
  • University of Vienna
Betreuer/-in / Berater/-in
  • Steinnocher, Klaus, Betreuer:in
  • Kainz, W., Betreuer:in, Externe Person
Datum der Bewilligung29 Sept. 2011
PublikationsstatusVeröffentlicht - 2011

Research Field

  • Ehemaliges Research Field - Innovation Systems and Policy

Diese Publikation zitieren