Abstract
Crop discrimination is still very challenging issue for researcher because of spectral reflectance similarity captured in non-imaging data. The objective of this research work is to focus on crop discrimination challenge. We have used ASD FieldSpec4 Spectroradiometer for collection of leaf samples of four crops Wheat, Jowar, Bajara and Maize. We used vegetation indices and some spectral reflectance band for featuring our dataset. We applied Principle Component Analysis (PCA) for discrimination and it has been observed that when we use first and second principle component, it will give poor result but if third principle component is used then we get accurate and fine results.
Highlights
INTRODUCTIONLand Cover (LULC), biophysical characteristics, crop yield prediction, crop growth monitoring, etc. requires high dimensional and detailed data
Monitoring crop condition applications like Land UseLand Cover (LULC), biophysical characteristics, crop yield prediction, crop growth monitoring, etc. requires high dimensional and detailed data
Jan Rudolf Karl Lehmann et al [4], have performed on Acacia longifolia (Native Shrub) to spectrally discriminate from other non-native and native species. He used jump correction followed by a first-derivative Savitzky-Golay smoothing with a second polynomial order and a filter width of nine points, PLS regression, Principle Component Analysis (PCA)-LDA and found that better estimation of A. longifolia was achieved by using regions of wavelength between 1360–1450 nm and 1630–1740 nm, and got the accuracy of 98.9%
Summary
Land Cover (LULC), biophysical characteristics, crop yield prediction, crop growth monitoring, etc. requires high dimensional and detailed data. Thenkabail et al [1] performed arduous hyperspectral data analysis for classification of crops based on many technique consisting of principal components analysis (PCA), lambda-lambda models, stepwise Discriminant Analysis (SDA) and vegetation indices. Carlos et al [3] performed hyperspectral data analysis and discriminated soybean plant’s spectral behavior to detect genetic seperability of soybean crop with remote sensor and he used vegetation indices and multivariate statistics to discriminate soyabean varieties. Wilson et al [6], discriminated five cash crops Soybean, Canola, wheat, barley and oat using ViewSpec Pro for extracting text data, Stepwise Discriminant Analysis (SDA) He found hyperspectral bands in the visual and near infrared (NIR) regions (400–900 nm) can be used to excellently differentiate between five crop species under investigation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
