Mapping invasive vegetation using AISA Eagle airborne hyperspectral imagery in the Mid-Ipoly-Valley

摘要

The primary goal of this study was to investigate the utility of high ground (1 m) and spectral (253 bands) resolution airborne hyperspectral imagery and several classification approaches for detecting the most problematic invasive plant species in the Mid-Ipoly-Valley. AISA Eagle II airborne sensor was applied to map a NATURA-2000 site on the Hungarian-Slovak cross-border site. This study focused on mapping of goldenrod (Solidago sp.) and milkweed (Asclepias syriaca) species in two selected study areas. During the image analysis, SAM classification method was used by selected dataset. Further classification methods were applied on MNF dataset. Feature selection (SEATH) tool was used to identify relevant feature from original MNF dataset. Maximum likelihood classification applied on the selected MNF dataset provided more accurate result than other methods. The primary outcome of this study was a comparison of different image classification methods to evaluate invasive species.