摘要： The main objective of this research was to establish a semiautomated object-based image analysis (OBIA) methodology for locating landslides. We have detected and delineated landslides within a study area in north-western Iran using normalized difference vegetation index (NDVI), brightness, and textural features derived from satellite imagery (IRS-ID and SPOT-5) in combination with slope and ?ow direction derivatives from a digital elevation model (DEM) and topographically oriented gray-level cooccurrence matrices (GLCMs). We utilized particular combinations of these information layers to generate objects by applying multiresolution segmentation in a sequence of feature selection and object classi?cation steps. The results were validated by using a landslide inventory database including 109 landslide events. In this study, a combination of these parameters led to a high accuracy of landslide delineation yielding an overall accuracy of 93.07%. Our results con?rm the potential of OBIA for accurate delineation of landslides from satellite imagery and, in particular, the ability of OBIA to incorporate heterogeneous parameters such as DEM derivatives and surface texture measures directly in a classi?cation process. The study contributes to the establishment of geographic object-based image analysis (GEOBIA) as a paradigm in remote sensing and geographic information science.