Open AccessGossypium Plant Health Detection from Hyperspectral Data using Various Disease Indices
Author(s) -
Komal Patil,
K. V. Kale
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a1512.109119
Subject(s) - hyperspectral imaging , crop , malvaceae , agriculture , agricultural engineering , vegetation (pathology) , environmental science , agronomy , mathematics , biology , remote sensing , geography , medicine , engineering , ecology , pathology
Cotton is the world's most prevalent beneficial non-food crop, producing revenue for over 250 million people globally and employing nearly 7% of all workers in developing nations. About half of all fabrics are produced with cotton. In such a case if the cotton plant gets affected due to disease can lead to economic and personal loss. These diseases may be one of the reasons that could significantly reduce the supply of cotton to the market, which result in a low agricultural economy. Faster and more accurate prediction of leaf diseases in crops could help to develop an early treatment technique while significantly reducing economic losses. The traditional monitoring system is time-consuming and expensive. In this paper, we have discussed hyperspectral sensor ASD FieldSpec4 which are less time consuming and non-destructive. Spectral Vegetation Indices (SVI) is strongly linked to the chemical composition of the plant leaf such as chlorophyll, nitrogen, carotenoid, and anthocyanin. The linear regression models were developed for the calculation of correlations between spectral indices and plant composition using MATLAB 2018.