Automatic extraction of wind erosion obstacles by integration of GIS data, DSM and stereo images 1

Integrating multiple data sources is a very important strategy to obtain relevant solutions in geo-scientific analysis. This paper mainly deals with the integration of Geographical Information System (GIS) data, stereo aerial imagery and a Digital Surface Model (DSM) to extract wind erosion obstacles (namely tree rows and hedges) in open landscapes. Different approaches, such as image segmentation, edge extraction, linking, grouping and 3-dimensional verification with the DSM, are combined to extract the objects of interest. Experiments show that most wind erosion obstacles can be successfully extracted by the developed system.