Unsupervised river detection in RapidEye-data
Résumé
Remote sensing is a widely-used utility in supporting multilateral environmental treaties such as the Water Framework Directive (WFD). Regarding the WFD most remote sensing applications aim on the assessment of the biochemical status of surface water, while the general detection of water networks is disregarded. Therefore, a methodology for the automatic extraction of river networks from multispectral satellite data is presented. Moreover, a new index called RE-NDWI is introduced, which highlights open water bodies in optical remotely sensed data, using the red edge and green band. The river detection method is tested on RapidEye data from three test sites in Germany and clearly outperforms a regular, supervised SVM-classification.