Per-parcel land use classification in urban areas applying a rule-based technique

Monitoring urban land use requires very high spatial resolution image data, acquired either by airborne or spaceborne sensor systems. The information content of such images is very complex, thus information extraction is currently performed on the basis of visual interpretation. The aim of the research described in this study is to formalise the visual interpretation procedure in order to automate the land use mapping process for urban areas. The assumption underlying this approach is that the land use functions can be distinguished on the basis of the differences in spatial distribution and pattern of land cover forms. IKONOS data covering a part of the metropolitan area of Vienna, Austria, are used in this study.