无人机高光谱遥感的水稻叶瘟病的光谱特征提取与检测方法研究  

Research on Spectral Feature Extraction and Detection Method of Rice Leaf Blast by UAV Hyperspectral Remote Sensing

作　　者：刘子扬 冯帅[1,2] 赵冬雪 李金朋 关强 许童羽 LIU Zi-yang;FENG Shuai;ZHAO Dong-xue;LI Jin-peng;GUAN Qiang;XU Tong-yu(Shenyang Agricultural University,College of Information and Electrical Engineering,Shenyang 110161,China;Shenyang Agricultural University,Liaoning Agricultural Informatization Engineering Technology Center,Shenyang 110161,China)

机构地区：[1]沈阳农业大学信息与电气工程学院,辽宁沈阳110161 [2]沈阳农业大学,辽宁省农业信息化工程技术中心,辽宁沈阳110161

出　　处：《光谱学与光谱分析》2024年第5期1457-1463,共7页Spectroscopy and Spectral Analysis

基　　金：辽宁省重点攻关项目(LSNZD202005);国家重点研发项目(2018YFD0300309)资助。

摘　　要：为了确定最佳的无人机高光谱遥感检测水稻冠层叶瘟病分类模型,以水稻大田试验为研究基础,获取了400~1000 nm波段内的无人机高光谱图像,参照国家标准GBT 15790—2009稻瘟病测报调查规范,按病情指数将叶瘟病划为5个等级,提取了0~4级共227组高光谱数据。采用Savitzky-Golay平滑(SG平滑)、一阶微分光谱(1-Der)和二阶微分光谱(2-Der)对数据进行预处理,并构建SVM模型,对比得出较优的预处理方法。采用主成分分析法(PCA)选取主成分累计贡献率;连续投影法(SPA)和随机青蛙法(RF)筛选光谱特征波段,并将筛选的结果作为模型的输入,分别构建粒子群优化的极限学习机(PSO-ELM)、极限学习机(ELM)、支持向量机(SVM)和决策树(DT)分类模型,并对模型进行对比分析得出最优分类模型。结果表明:相比于1-Der和2-Der,SG平滑方法的去噪效果较好,分类准确率较高,是较优的预处理方法,分类准确率和Kappa系数分别为93.47%、91.85%。PCA的前2个PC的累计贡献率为93.13%,为了模型的有效构建,最终选取了前6个PC,累计贡献率为99.02%。SPA使用RMSE作为最佳光谱特征波段选择标准,共显示了7个最佳光谱特征波段,其中可见光波段为400.8、416.7和426.2 nm,绿光波段为566 nm,红光波段为683.9 nm,近红外波段为830.2和916.4 nm。RF将筛选概率大于0.2的波段选为最佳光谱特征波段,最终筛选了8个光谱特征波段,其中红光波段为663.4和694.2 nm,近红外波段为784.4、787.9、791.4、905.5、927.2和930.9 nm,该方法有效地降低了波段间相关性和冗余性。将3种筛选结果分别构建分类模型,结果显示所有模型的总体分类准确率全部大于92.61%,建模结果较好;其中,以PSO-ELM模型对PCA的分类准确率达到97.77%,Kappa系数为97.22%,在所有模型中分类准确率最高,相比于ELM模型的最高分类准确率和Kappa系数高1.42%和1.56%,相比于SVM模型的最高分类准确率和Kappa系数高2.12%和To determine the optimal classification model for unmanned aerial hyperspectral remote sensing for detection of leaf blast in rice canopies,the research is based on rice field trials,hyperspectral images of unmanned aerial vehicles(UAVs)in the 400~1000 nm band were acquired,referring to the national standard GBT 15790-2009 specification for rice blast detection and survey,leaf blast is categorized into five classes according to the disease index,a total of 227 hyperspectral data sets were extracted for levels 0 to 4.The data were preprocessed using Savitzky-Golay smoothing(SG smoothing),first-order differential spectroscopy(1-Der)and second-order differential spectroscopy(2-Der)methods,and SVM models are constructed and compared to arrive at a better preprocessing method.Principal component analysis(PCA)was used to select the cumulative contribution of the principal components,continuous projection(SPA)and random frog(RF)methods for screening spectral signature bands,and using the results of the screening as inputs to the model,constructing Particle Swarm Optimization for Extreme Learning Machines(PSO-ELM),Extreme Learning Machines(ELM),Support Vector Machines(SVM)and Decision Tree(DT)classification models,respectively.The results show that compared with 1-Der and 2-Der,the SG smoothing method has better denoising effect,higher classification accuracy,and is a better preprocessing method,the classification accuracy and Kappa coefficient were 93.47%and 91.85%,respectively.The cumulative contribution of the first 2 PCs of the PCA was 93.13%,and for the effective construction of the model,the first 6 PCs were finally selected with a cumulative contribution of 99.02%,SPA used RMSE as the criterion for the selection of the best spectral signature bands,showing a total of seven best spectral signature bands,The visible wavelength bands are 400.8,416.7 and 426.2 nm,the green wavelength band is 566nm,the red wavelength band is 683.9nm,and the near-infrared wavelength bands are 830.2 and 916.4 nm,RF selected the bands wit

关 键 词：水稻 叶瘟病 无人机 高光谱 机器学习 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]