%0 Conference Proceedings
%T Hyperspectral Discrimination and Response Characteristics of Stressed Rice Leaves Caused by Rice Leaf Folder
%+ Hangzhou Normal University
%+ Zhejiang University
%+ National Engineering Research Center for Information Technology in Agriculture [Beijing] (NERCITA)
%A Liu, Zhanyu
%A Cheng, Jia-An
%A Huang, Wenjiang
%A Li, Cunjun
%A Xu, Xingang
%A Ding, Xiaodong
%A Shi, Jingjing
%A Zhou, Bin
%Z Part 1: GIS, GPS, RS and Precision Farming
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 5th Computer and Computing Technologies in Agriculture (CCTA)
%C Beijing, China
%Y Daoliang Li
%Y Yingyi Chen
%I Springer
%3 Computer and Computing Technologies in Agriculture V
%V AICT-369
%P 528-537
%8 2011-10-29
%D 2011
%R 10.1007/978-3-642-27278-3_54
%K Hyperspectral remote sensing
%K Rice crop
%K Rice leaf folder
%K Principal components analysis (PCA)
%K Support vector classification (SVC)
%Z Computer Science [cs]Conference papers
%X Detecting plant health condition plays an important role in controlling disease and insect pest stresses in agricultural crops. In this study, we applied support vector classification machine (SVC) and principal components analysis (PCA) techniques for discriminating and classifying the normal and stressed paddy rice (Oryza sativa L.) leaves caused by rice leaf folder (Cnaphalocrocis medinalis Guen). The hyperspectral reflectance of paddy rice leaves was measured through the full wavelength range from 350 to 2500nm under the laboratory condition. The hyperspectral response characteristic analysis of rice leaves indicated that the stressed leaves presented a higher reflectance in the visible (430~470 nm, 490~610 nm and 610~680 nm) and one shortwave infrared (2080~2350 nm) region, and a lower reflectance in the near infrared (780~890 nm) and the other shortwave infrared (1580~1750 nm) region than the normal leaves. PCA was performed to obtain the principal components (PCs) derived from the raw and first derivative reflectance (FDR) spectra. The nonlinear support vector classification machine (referred to as C-SVC) was employed to differentiate the normal and stressed leaves with the front several PCs as the independent variables of C-SVC model. Classification accuracy was evaluated using overall accuracy (OA) and Kappa coefficient. OA of C-SVC with PCA derived from both the raw and FDR spectra for the testing dataset were 100%, and the corresponding Kappa coefficients were 1. Our results would suggest that it’s capable of discriminating the stressed rice leaves from normal ones using hyperspectral remote sensing data under the laboratory condition.
%G English
%Z TC 5
%Z WG 5.14
%2 https://inria.hal.science/hal-01361026/document
%2 https://inria.hal.science/hal-01361026/file/978-3-642-27278-3_54_Chapter.pdf
%L hal-01361026
%U https://inria.hal.science/hal-01361026
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG5-14
%~ IFIP-CCTA
%~ IFIP-AICT-369