MULTI SPECTRALSATELLITE IMAGES AS A TOOL FOR DETECTING HEALTHY TEA PLANTATION

Abstract

Sri Lanka is well known for its rich tea cultivation. Diseases are always injurious to the tea plant’s health which in turn severely affect its growth, yield and quality. So it is always advisable to continuously monitor its growth to ensure minimal losses of tea plant. This study proposes a solution of tea leaf disease detection approach that is simple, time efficient and generic, which can be utilized to assess and monitor tea plantations. In this study, an attempt has been made with the help of Remote Sensing and GIS techniques to monitor the tea plant health by using the spectral responses in the visible and Near Infrared (NIR) regions of the Electromagnetic Spectrum using Landsat-8 OLI\TIRS images. Spectral profiles for the tea patches were generated from the classified images obtained after atmospheric correction. Grey Level Co-occurrence Matrix (GLCM) based texture variations and Normalized Difference Vegetation Index (NDVI) analysis have been used to verify the results