Tree Species Classification by Fusing of Very Highresoltuion Hyperspectral Images and 3K-DSM

摘要

Tree species information is crucial in sectors such as forest management and nature conservation. It is often required over a large area. In this study, tree species classification was performed using hyperspectral data and the Digital Surface Model generated from DLR-3K aerial borne stereo camera System. In the classification step, pixel-based approach and the patch-based approach with Bag-of-Word (BoW) model were proposed and tested. The two approaches have been performed in the Kranzberg Forest near Munich, Germany. The comparison was taken in a statistical way. By using proper features combination, the pixel-based classification can achieve very high accuracy (Kappa $=0.95)$, while the patch-based method only has accuracy around 60%.