Semi-Automated LULC Classification of VHR Optical Satellite Data in the Context of Urban Planning

摘要

One of the major phenomenon of the ongoing globalization is the rapid growing of urban areas. In the end of the 1970~(th), 38% of the world population were living in cities. This number increased up to 50% in 2008 and will steady rise up to two third of the world population in 2030 [1]. Urban sprawl is one of the major environmental and social concerns caused by the development of new and the growing of existing cities. Besides a quantitative reduction of land consumption, sustainable handling of the limited resource land and "smart growth" are acknowledged as key tasks for urban planning [2, 3]. Coping with these tasks requires precise and adaptive planning instruments which will be developed in the project "Gaining additional urban space (GAUS) - Detection and valuation of potential areas for inner urban development with remote sensing and GIS". This research project is dedicated to the development of a multi-criteria decision support system (MDSS) as tool for supporting urban planners and municipal management authorities with regard to urban consolidation and smart growth. The description of the framework for a land use and land cover (LULC) classification of very high resolution (VHR) optical satellite data is in the focus. The results of the object oriented analysis acts as basement for the MCDSS. The main objective is to describe a strategy to retrieve comparable classification results of different investigation areas under the preconditions of transferability and firmness to reach semi-automation.