Detection of cotton waterlogging stress based on hyperspectral images and convolutional neural network
作者机构：School of Agricultural Engineering and Food ScienceShandong University of TechnologyZibo 255000ShandongChina Sub-center of National Center for International Collaboration Research on Precision Agricultural Aviation Pesticides Spraying TechnologyShandong University of TechnologyZibo 255000ShandongChina School of Traffic and vehicle engineeringShandong University of TechnologyZibo 255000ShandongChina
出 版 物：《International Journal of Agricultural and Biological Engineering》 (国际农业与生物工程学报（英文）)
年 卷 期：2021年第14卷第2期
页 面：167-174页
核心收录：
学科分类：08[工学] 081501[工学-水文学及水资源] 0815[工学-水利工程]
主 题：cotton waterlogging hyperspectral image convolutional neural network
摘 要：Waterlogging in the early stage of cotton will reduce the number of bolls and do harm to *** detection of waterlogging will help farmers to adjust cotton management and save the *** evaluate the application of deep learning for the detection of early waterlogging,this study applied a convolutional neural network(CNN)to classify different durations of waterlogging stress(0,2,4,6,8,10 d)based on hyperspectral images(HSIs)of cotton *** experiment was designed to simulate the situation of cotton under waterlogging stress and collect HSIs of visible and near-infrared(VNIR 450-950 nm)spectra with 126 bands 66 d after cotton sowing(66 DAS).It was found the spectral curve reflectance of waterlogging cotton was higher than that of non-waterlogging *** near 550 nm and 750 nm,and the spectral curve increased with durations of waterlogging stress and there were‘blue shift’phenomena for the position of the red edge of the *** first principal components of HSIs after band randomly discarding and principal component analysis(PCA)were used to build a *** Inception-v3(GLNI-v3)and VGG-16 models were selected to detect cotton waterlogging stress with the *** results showed that the average time for a round training for GLNI-v3 was 13.337 s,with a classification accuracy of 96.95%and a loss value of *** average time for a round training for VGG-16 was 21.470 s,with a classification accuracy of 97.00%and a loss value of *** these two models had similar classification accuracy and loss value,GLNI-v3 achieved a high accuracy with fewer training *** durations of waterlogging stress of cotton in a short-term can be detected by HSIs of cotton leaves and CNN models are suitable for the classification of HSIs,and this method can provide support for cotton yield estimation and loss assessment after waterlogging.
维普期刊数据库