Automated Object-Identification for Isolated Transient Landforms in Remote-Sensing Data

GeoViz: Linking Geovisualization with Spatial Analysis and Modeling, 10-11 March 2011, Hamburg, Germany

Lucia Tyrallova, Stephan van Gasselt, and Hartmut Asche

“Automated object identification and statistical characterization of morphometric key values are valuable tools in the field of geomorphology in order to identify processes and process-response systems related to climatic boundary conditions. The automated detection of primary climate-related landforms and the assessment of their change throuth time and three decades of remote-sensing observations allow and help to quantify and find predictors for the consequences of climate change. Approaches and concepts for object-catalog based detection of landforms within a commercial GIS suite are discussed and presented for the study cases of two major climate tracers: dunes and thermokarst features.”