Comparison of Vegetation Spectral Indices Based on UAV Data : Land Cover Identification Near Small Water Bodies

Abstract

Middle- and low-class unmanned aerial vehicles (UAV) can be used for land cover/land use identification on demand even when equipped only with an RGB camera. UAV is used as a cheap and on-demand available solution for remote data sensing for smaller areas, with respect to legal regulations and weather conditions. The paper is focused on land cover identification near a small water body, which is based on RGB data collected by UAV and on vegetation spectral indices. Various vegetation indices based on calculating with RGB bands are used to process the collected imagery and identify particular land cover types. NGRDI, GLI2 and VARI provided the most accurate results.