[1]芦兵,孙俊,毛罕平,等.高光谱和图像特征相融合的生菜病害识别[J].江苏农业学报,2018,(06):1254-1259.[doi:doi:10.3969/j.issn.1000-4440.2018.06.008]
　LU Bing,SUN Jun,MAO Han-ping,et al.Disease recognition of lettuce with feature fusion based on hyperspectrum and image[J].,2018,(06):1254-1259.[doi:doi:10.3969/j.issn.1000-4440.2018.06.008]
点击复制

高光谱和图像特征相融合的生菜病害识别()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2018年06期
页码:
1254-1259
栏目:
植物保护
出版日期:
2018-12-25

文章信息/Info

Title:
Disease recognition of lettuce with feature fusion based on hyperspectrum and image
作者:
芦兵1; 3; 孙俊1 ; 毛罕平2; 杨宁1; 武小红1
(1.江苏大学电气信息工程学院，江苏镇江212013；2.江苏大学现代农业装备与技术教育部重点实验室，江苏镇江212013；3.江苏大学信息化中心，江苏镇江212013)
Author(s):
LU Bing1; 3; SUN Jun1; MAO Han-ping2; YANG Ning1; WU Xiao-hong1
(1.School of Electrical and Information Engineering， Jiangsu University， Zhenjiang 212013， China;2.Key Laboratory of Modern Agricultural Equipment and Technology， Ministry of Education， Jiangsu University， Zhenjiang 212013， China;3.Information Center， Jiangsu University， Zhenjiang 212013， China)
关键词:
高光谱; 图像特征; 特征融合; 三阶矩; LBP算子; SVR
Keywords:
hyperspectrum; image feature; feature fusion; third-order moments; LBP algorithm; SVR
分类号:
TP391.41
DOI:
doi:10.3969/j.issn.1000-4440.2018.06.008
文献标志码:
A
摘要:
为精准识别生菜的病害类型及所处病害时期，提出了一种结合高光谱技术和图像特征提取技术融合的生菜病害诊断方法。利用高光谱套件分别采集炭疽病、菌核病、白粉病的发病早期、中期和晚期以及健康状态下生菜叶片样本的高光谱信息，利用多项式平滑（Savitzky-Golay,SG）算法对原始光谱数据进行降噪平滑处理，采用连续投影算法（Successive projections algorithm ,SPA）对预处理后的数据进行特征波长的优选，使用一阶到三阶矩和纹理LBP算子分别提取样本图像的颜色特征和纹理特征，最后通过SVR预测模型对颜色、纹理及光谱特征值数据进行训练并对预测集样本进行分类研究。结果表明，基于高光谱和图像融合特征的SVR预测模型性能良好，预测集决定系数为0.895 6，均方根误差为375%。由于决定系数不够理想，通过引入松弛变量的方式降低间隔阈值，最终模型预测集决定系数为0.928 6，均方根误差为0034 2，决定系数提高了368%，均方根误差降低了88%，病害时期判断准确率为9223%。说明该方法能够较有效地诊断生菜的病害类型及所处病害时期，可为农业精准化管理中病害的自动防治提供参考。
Abstract:
In order to identify the disease type and disease period accurately, a method of lettuce disease diagnosis with hyperspectral technology and image feature extraction technology was proposed. Hyperspectral information was collected from the health leaves and the diseased leaves of anthracnose, sclerotia and powdery mildew under different disease cycle including early, medium and late. The polynomial smoothing (Savitzky-Golay, SG) algorithm was used to reduce the noise and smooth the original spectral data, and successive projections algorithm (SPA) was applied to optimize the characteristic wavelengths of the preprocessed data, the color and texture features of the sample image were extracted through first to third-order moments and LBP algorithm, respectively. Finally, the SVR prediction model was used to train the color, texture and spectral feature data and to classify the prediction set samples.The results showed that the SVR prediction model based on hyperspectral and image fusion features had a good performance, the determination coefficient and the root mean square error of the prediction set were 0.895 6 and 375%. The interval threshold was reduced by introducing relaxation variable because the coefficient of determination was not ideal, after optimization, the final prediction coefficient of the model was 0.928 6 and the root mean square error was 342%, the coefficient of determination was increased by 368% and the root mean square error was reduced by 88%, and the accuracy rate of the disease period was 9223%. This method can effectively diagnose the disease type and disease cycle of lettuce, and provide a reference for the automatic control of disease in agricultural precision management.

参考文献/References:

[1]田翠. 生菜三大病害的发生与防治[J]. 农村新技术,2014(10),18-19.
[2]曹入尹,陈云浩,黄文江,等. 面向作物病害识别的高光谱波谱库设计与开发[J]. 自然灾害学报,2008,17(6):73-76.
[3]李子艺，王振锡，岳俊，等．基于BP神经网络的高光谱果树树种识别研究[J]．江苏农业科学，2016,44(5):410-414.
[4]杨赛,朱启兵,黄敏. 基于联合偏度的高光谱图像波段选择对玉米种子分类研究[J]. 光谱学与光谱分析,2017,37(3):990-996.
[5]岳学军,全东平,洪添胜,等. 不同生长期柑橘叶片磷含量的高光谱预测模型[J]. 农业工程学报,2015,31(8):207-213.
[6]曹文涛，康日斐，王集宁，等. 基于高光谱遥感的土壤氯化钠含量监测[J]. 江苏农业学报，2016，32（4）：817-823.
[7]BRAVO C, MOSHOU D, WEST J, et al. Early disease detection in wheat fields using spectral reflectance[J]. Biosystems Engineering, 2003, 84(2):137-145.
[8]王斌,薛建新,张淑娟. 基于高光谱成像技术的腐烂、病害梨枣检测[J]. 农业机械学报,2013，44(1):205-209.
[9]谭峰，马晓丹．基于叶片的植物病虫害识别方法[J]．农机化研究，2009，31(6)：41-43.
[10]ZHANG S W,SHANG Y J,WANG L. Plant disease recognition based on plant leaf image[J]. Journal of Animal & Plant sciences,2015,25(3):42-45.
[11]孙俊,谭文军,毛罕平，等. 基于改进卷积神经网络的多种植物叶片病害识别[J]. 农业工程学报,2017，33(19)：209-215.
[12]JUNCHENG M,KEMING D, LINGXIAN Z,et al. A segmentation method for greenhouse vegetable foliar disease spots images using color information and region growing[J]. Computers and Electronics in Agriculture,2017(142):110-117.
[13]朱文静,毛罕平,周莹，等. 基于高光谱图像技术的番茄叶片氮素营养诊断[J]. 江苏大学学报(自然科学版)，2014,35(3):290-294.
[14]郭志明,黄文倩,彭彦昆，等. 高光谱图像感兴趣区域对苹果糖度模型的影响[J]. 现代食品科技,2014,30(8):59-63，75.
[15]孙林,陈丽娟. 植被叶片生化组分的光谱相应特征分析[J]. 光谱学与光谱分析,2010,30(11):3025-3031
[16]ACHARYA D, RANI A, AGARWAL S, et al. Application of adaptive Savitzky-Golay filter for EEG signal processing[J]. Perspectives in Science, 2016， 8:677-679.
[17]孙俊,丛孙丽,毛罕平，等. 基于高光谱的油麦菜叶片水分CARS-ABC-SVR预测模型[J]. 农业工程学报,2017,33(5):178-184.
[18]RAJATHIAGAM B,MURALI M. Edge detection using G-lets based on matrix factorization by group representations[J]. Pattern Recognition,2017(67):1-15.
[19]庄哲民,章聪友,杨金耀,等. 基于灰度特征和自适应阈值的虚拟背景提取研究[J]. 电子与信息学报,2015,37（2):346-352.
[20]YINGYING Y,ZHENZHOU A,HONG W. Adaptive Targets-detecting Algorithm based on LBP and Background Modeling under Complex Scenes[J]. Procedia Engineering,2011，15:2789-2494.
[21]李春利,沈鲁娟. 基于改进LBP算子的纹理图像分类方法[J]. 计算机工程与设计,2016(1):232-236.
[22]韩丁,武佩,张强,等. 基于颜色矩的典型草原牧草特征提取与图像识别[J]. 农业工程学报,2016,32(23):168-175.
[23]HONORIUS G,LUCIAN M,RAZVAN A. Increment and decremental SVM for Regression[J]. International Journal of Computers Communications & Control,2016(11):195-202.
[24]马允,王晓东,富显祖. 基于GA-SVR模型的无参考立体图像质量评价[J]. 计算机工程,2017,43（5）：234-239.
[25]张艳,孟庆龙,尚静,等. 新型图像技术在农作物病害监测预警中的应用与展望[J]. 激光技术,2017,38（12）：7-13.
[26]冯雪冰. 基于优化SVM的列车转向架故障挖掘模型仿真[J]. 计算机仿真,2015(10):182-185.
[27]熊宁,张魏,黄金海,等. 基于约束松弛变量策略的中心校正内点法[J]. 电力系统保护与控制,2012,40(14):20-25.

相似文献/References:

[1]刘志刚,徐勤超.基质破碎度对光谱法检测基质含水率的影响[J].江苏农业学报,2017,(05):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
　LIU Zhi-gang,XU Qin-chao.Influences of substrate fragmentation degree on substrate water contents detected by hyper-spectral technology[J].,2017,(06):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
[2]王卓卓,何英彬,罗善军,等.基于冠层高光谱数据与马氏距离的马铃薯品种识别[J].江苏农业学报,2018,(05):1036.[doi:doi:10.3969/j.issn.1000-4440.2018.05.010]
　WANG Zhuo-zhuo,HE Ying-bin,LUO Shan-jun,et al.Variety identification of potatoes based on canopy hyperspectral data and Mahalanobis distance[J].,2018,(06):1036.[doi:doi:10.3969/j.issn.1000-4440.2018.05.010]
[3]郑曼迪,熊黑钢,乔娟峰,等.基于综合光谱指数的不同程度人类干扰下土壤有机质含量预测[J].江苏农业学报,2018,(05):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
　ZHENG Man-di,XIONG Hei-gang,QIAO Juan-feng,et al.Prediction of soil organic matter content based on comprehensive spectral index at different levels of human disturbance[J].,2018,(06):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
[4]王婷,刘振华,彭一平,等.华南地区土壤有机质含量高光谱反演[J].江苏农业学报,2020,(02):350.[doi:doi:10.3969/j.issn.1000-4440.2020.02.014]
　WANG Ting,LIU Zhen-hua,PENG Yi-ping,et al.Predicting soil organic matter content in South China based on hyperspectral reflectance[J].,2020,(06):350.[doi:doi:10.3969/j.issn.1000-4440.2020.02.014]
[5]朱淑鑫,杨宸,顾兴健,等.K均值算法结合连续投影算法应用于土壤速效钾含量的高光谱分析[J].江苏农业学报,2020,(02):358.[doi:doi:10.3969/j.issn.1000-4440.2020.02.015]
　ZHU Shu-xin,YANG Chen,GU Xing-jian,et al.K-means algorithm combined with successive projection algorithm for hyperspectral analysis of soil available potassium content[J].,2020,(06):358.[doi:doi:10.3969/j.issn.1000-4440.2020.02.015]
[6]苗梦珂,王宝山,李长春,等.基于连续小波变换的冬小麦叶片最大净光合速率遥感估算[J].江苏农业学报,2020,(03):544.[doi:doi:10.3969/j.issn.1000-4440.2020.03.003]
　MIAO Meng-ke,WANG Bao-shan,LI Chang-chun,et al.Remote sensing estimation of maximum net photosynthetic rate of winter wheat leaves based on continuous wavelet transform[J].,2020,(06):544.[doi:doi:10.3969/j.issn.1000-4440.2020.03.003]
[7]陶惠林,冯海宽,徐良骥,等.基于无人机高光谱遥感数据的冬小麦生物量估算[J].江苏农业学报,2020,(05):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
　TAO Hui-lin,FENG Hai-kuan,XU Liang-ji,et al.Winter wheat biomass estimation based on hyperspectral remote sensing data of unmanned aerial vehicle(UAV)[J].,2020,(06):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
[8]潘月,曹宏鑫,齐家国,等.基于高光谱和数据挖掘的油菜植株含水率定量监测模型[J].江苏农业学报,2022,38(06):1550.[doi:doi:10.3969/j.issn.1000-4440.2022.06.013]
　PAN Yue,CAO Hong-xin,QI Jia-guo,et al.Quantitative monitoring models of plant water content in rapeseed based on hyperspectrum and related data mining[J].,2022,38(06):1550.[doi:doi:10.3969/j.issn.1000-4440.2022.06.013]
[9]樊泳灼,李新国.湖滨绿洲棕漠土有机碳含量高光谱估算[J].江苏农业学报,2023,(06):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]
　FAN Yong-zhuo,LI Xin-guo.Hyperspectral prediction of organic carbon content of brown desert soil in the lakeside oasis[J].,2023,(06):1341.[doi:doi:10.3969/j.issn.1000-4440.2023.06.009]
[10]郑智康,常庆瑞,符欣彤,等.基于变换光谱与光谱指数的夏玉米叶片含水率高光谱估算[J].江苏农业学报,2023,(09):1883.[doi:doi:10.3969/j.issn.1000-4440.2023.09.010]
　ZHENG Zhi-kang,CHANG Qing-rui,FU Xin-tong,et al.Hyperspectral estimation of leaf water content of summer maize based on transformed spectrum and spectral index[J].,2023,(06):1883.[doi:doi:10.3969/j.issn.1000-4440.2023.09.010]

备注/Memo

备注/Memo:
收稿日期：2018-03-26 基金项目：国家自然科学基金项目（31471413）;江苏高校优势学科建设工程资助项目PAPD[苏政办发(2011)6号];江苏省六大人才高峰资助项目（ZBZZ-019） 作者简介：芦兵(1983-),男,江苏镇江人,博士,实验师,主要从事计算机技术在农业工程中的应用研究。(Email)lubing@ujs.edu.cn
更新日期/Last Update: 2018-12-28