Enhanced semi-automatic image classification of high-resolution data

With the launch of KOMPSAT-2 at the end of 2005 the availability of high resolution data should be greatly improved. The use of download facilities in Europe will allow increased coverage without interfering with the original mission of KOMPSAT-2. With platforms currently under development by the European Space Agency such as the service support environment (SSE) and eoPortal larger audiences can be reached with different technical know-how. As these platforms go beyond mere data distribution but allow the implementation of applications this opens new possibilities but also poses new demands on application development. In this paper an object oriented classifier is used to derive basic land cover classes from high-resolution satellite image. The result is then integrated with vector data to identify different land user categories.