Development of Agricultural Crops Spectral Library and Classification of Crops Using Hyperion Hyperspectral Data

Abstract

The very high effectiveness of hyperspectral sensors in vegetation discrimination increases the applications of crop classification using hyperspectral data. However, for this capability to be exploitable, it is essential that a well-populated spectral library exists and is accessible in a user-friendly way by the user of this technology. To address this issue field hyperspectral measurement using field spectrometer have been collected and spectral library for various crops have been developed in this study. Spectral Angle Mapper (SAM) approach has been used for image classification and accuracy assessment has been carried out to test the end results. The reasonable good overall accuracy shows that the possible integration of field spectra (in-situ hyperspectral measurements) with pixel data (space-borne hyperspectral data).