Mapping of Landslides Under Dense Vegetation Cover Using Object-Oriented Analysis and LiDAR Derivatives Miet Van Den Eeckhaut, Norman Kerle, Javier Herva ´s, and Robert Supper Abstract Light Detection and Ranging (LiDAR) and its wide range of derivative products have become a powerful tool in landslide research, particularly for landslide identification and landslide inventory mapping. In contrast to the many studies that use expert-based analysis of LiDAR derivatives to identify landslides, only few studies, all pixel-based, have attempted to develop computer-aided methods for extracting landslides from LiDAR. So far, it has not been tested whether object-oriented analysis (OOA) could be an alterna- tive. Therefore, this study focuses on the application of OOA using LiDAR derivatives such as slope gradient, curvature, and difference in elevation (2 m resolution). More specifically, the focus is on the possible use for segmentation and classification of slow-moving landslides in densely vegetated areas, where spectral data do not allow accurate landslide inventory mapping. The test areas are the Flemish Ardennes (Belgium) and Vorarlberg (Austria). In a first phase, a relatively qualitative procedure based on expert-knowledge and basic statistical analysis was developed for a test area in the Flemish Ardennes. The procedure was then applied without further modification to a validation area in the same region. The results obtained show that OOA using LiDAR derivatives allows recognition and characterization of profound morphologic properties of deep-seated landslides, because approximately 70 % of the landslides of an expert-based inventory were also included in the object-oriented inventory. For mountain areas with bed rock outcrops like Vorarlberg, on the other hand, it is more difficult to create a transferable model. Keywords Deep-seated landslides  LiDAR  Segmentation  Characterisation  Geomorphometry Introduction Since the availability of Light Detection and Ranging (LiDAR), shaded-relief, slope, surface roughness and con- tour maps, and other derivatives have regained popularity for landslide inventory mapping, especially in forested areas (Schulz 2004; Van Den Eeckhaut et al. 2007, 2011). Many studies have used expert-based analysis of LiDAR derivatives to identify landslides, while only few studies have attempted to develop computer-aided methods for extracting landslides from LiDAR data (McKean and Roering 2004; Booth et al. 2009). Promising results were obtained with M. Van Den Eeckhaut (*)  J. Herva ´s Institute for Environment and Sustainability, Joint Research Centre (JRC), European Commission, 21027 Ispra, Italy e-mail: miet.van-den-eeckhaut@jrc.ec.europa.eu N. Kerle Faculty of Geo-Information Science and Earth Observation, University of Twente, Enschede, The Netherlands R. Supper Geological Survey of Austria, Vienna, Austria C. Margottini et al. (eds.), Landslide Science and Practice, Vol. 1, DOI 10.1007/978-3-642-31325-7_13, # Springer-Verlag Berlin Heidelberg 2013 103