An urban classification approach based on an object-oriented analysis of high resolution satellite imagery for a spatial structuring within urban areas

Classifying the complex structures of urban morphology from high resolution remote sensing imagery comprises difficulties due to their spectral and spatial heterogeneity. This paper presents a methodology allowing derivation of area-wide spatial information meaningful for city planning and management from IKONOS imagery. The initial point is a stable segmentation for an object-oriented approach to derive a thematic land cover classification. The classification methodology – which is predominantly based on shape and neighbourhood related features - is exemplified by the extraction of roads with a region-growing rule base. The approach follows the assumption that objects representing real world structures correspond in any urban area. Finally, the urban land cover classification is used to compute a spatial distribution of built-up densities within the city and to map homogeneous zones or structures of urban morphology. The aim apart from the information on urban morphology is to derive indirectly standard socio-economic data for further support of city management and planning. The result shows an allocation of different urban zones within the city of Istanbul with an accuracy of 82% compared to a digitized layer based on visual classification