Susanne Karg started her M.Sc. thesis on „Burn scar detection using polarimetric ALOS-2 time-series data“ in cooperation with DLR-DFD (Günter Strunz, Sandra Martinis). The aim of this thesis is to develop a change-detection approach using polarimetric SAR (PolSAR) data and, if suitable data is available, interferometric SAR (InSAR) data to detect fire scars. Within this thesis different polarimetric decomposition approaches and pixel-based classifications will be tested for their suitability to detect a recently burned region of interest. The variables which perform best will then be used for an object-based post-classification refinement.
New Publication on Automated building characterization
A new publication by Hannes Taubenböck and colleagues is online about "Automated building characterization for seismic risk assessment using street-level imagery and deep learning". From the abstract: "Accurate seismic risk modeling requires knowledge of key...
