Building parameters extraction from remote-sensing data and GIS analysis for the derivation of a building taxonomy of settlements – a contribution to flood building susceptibility assessment

Assessment of building susceptibility due to natural hazard such as floods requires information about the building construction, which cannot always be properly collected and characterised in many cities of the world due to lack of reliable data and laborious techniques and high costs involved in field work. To overcome these issues, the paper proposes an approach to infer a building’s taxonomy for the investigation of settlements at the building scale. The approach combines generic methods for building feature extraction, derivation of building parameters, and classification of the parameters using fuzzy clustering. It is implemented in a case study in the city of Dresden.