Application of VHR Multispectral Data and Height Information for an Object-Based Classification of Urban Structure Types
Voltersen, Michael; Berger, Christian; Hese, Soeren; Schmullius, Christiane
Friedrich-Schiller-University Jena, GERMANY
All over the world, cities have evolved under manifold geographical, economical, historical and cultural criteria resulting in various sizes and shapes. Each city exhibits individual features and unique characteristics, despite that structural similarities appear. The separation into individual patterns, commonly named urban structure types (USTs), supports the characterization of physical, functional and energetic factors of settlement structures, enabling associated environmental and socio-economic investigations as well as the comparison between the patterns of different cities. Remote sensing data and methods provide a source for the effective monitoring of urban environments on different scales. The derivation of up-to-date land cover information for large areas enables a detailed and cost-efficient mapping basis. This study presents an object-based approach to initially identify the land cover for the city of Berlin, utilizing spatially very high resolution aerial images and object height information. Target UST-classes are defined regarding the appearance within the study area, delimited by block boundaries. Afterwards, optimal indicators for the derivation of USTs are generated and structural units are classified by involving rarely used and new land cover based parameters. Comparing the results with manually derived information, high classification accuracies for both, land cover and USTs, indicate the suitability of the proposed method.