Semi-automated Mapping of Landslide Changes in Taiwan by Means of Object-based Image Analysis

Earth observation (EO) data are of great value for the detection of landslides after triggering events, especially if they occur in remote and hardly accessible terrain. To fully exploit the potential of the wide range of available remote sensing data, innovative and reliable landslide (change) detection methods are needed. To overcome the limitations of pixel-based methods object-based image analysis (OBIA) has recently been employed for EO-based landslide (change) mapping. The presented approach is developed for a sub-area of the Baichi catchment in northern Taiwan. The focus is on themapping oflandslides and debris flows/sediment transport areascaused by the Typhoons Aere in 2004 and Matsa in 2005. For both events, preand post-disaster optical satellite images (SPOT-5 with 2.5 m spatial resolution)were analysed. A digital elevation model (DEM)at 5 m spatial resolution and its derivatives, mainly slope and curvature, were integrated in the analysis to support the semi-automated object-based mapping.The changes were identified by comparing properties of segmentation-derived image objects between preand post-event images. To ensure a certain degree of transferability and robustness of the approach changes were mainly detected using relational features such as the Normalized Difference Vegetation Index (NDVI) and the Green Normalized Difference Vegetation Index (GNDVI).