Hyperspectral data analysis for subtropical tree species recognition

Hyperspectral data analysis is an important basic research arena for remote sensing. However, tree species in the tropical and subtropical environment are not commonly studied and reported. In this study, hyperspectral data are taken for 6 common tree species using a high spectral resolution spectrometer in the subtropical environment of Hong Kong. Data are taken from 400 to 900 nm. Using linear discriminant analysis reveals that these tree species can be recognized with an overall accuracy of %.