基于光学特性参数反演的绿萝叶绿素含量估测研究

王浩云; 曹雪莲; 孙云晓; 闫明壮; 王江波; 徐焕良

基于光学特性参数反演的绿萝叶绿素含量估测研究

1. 南京农业大学人工智能学院;
2. 中国电子科技集团国睿科技股份有限公司;
3. 塔里木大学植物科学学院;
4. 塔里木大学南疆特色果树高效优质栽培与深加工技术国家地方联合工程实验室

基金项目:

南京农业大学-塔里木大学科研合作联合基金项目(NNLH202006)

中央高校基本科研业务费专项资金项目(KYLH202006、KYZ201914)

新疆生产建设兵团南疆重点产业支撑计划项目(2017DB006)

国家自然科学基金项目(31601545)

详细信息

作者简介:
王浩云(1981—),男,副教授,博士,主要从事作物表型参数测量研究,E-mail:wanghy@njau.edu.cn

通讯作者:
徐焕良(1963—),男,教授,博士生导师,主要从事作物表型参数测量研究,E-mail:huanliangxu@njau.edu.cn

中图分类号: S682.36
计量
- 文章访问数: 1
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2020-11-25
- 刊出日期: 2021-03-24

Estimation of Chlorophyll Content of Epipremnum aureum Based on Optical Characteristic Parameter Inversion

1. College of Artificial Intelligence,Nanjing Agricultural University;
2. China Electronics Technology Group Guorui Technology Co.,Ltd.;
3. Faculty of Plant Sciences,Tarim University;
4. The National and Local Joint Engineering Laboratory of High Efficiency and Superior-Quality Cultivation and Fruit Deep Processing Technology of Characteristic Fruit Trees in South Xinjiang,Tarim University

摘要

摘要: 为快速准确检测植物体叶绿素含量,提出一种基于MMD迁移的光学特性参数反演方法。以绿萝叶片为研究对象,仿真光子在基于蒙特卡洛方法的单层平板模型上的运动轨迹,获得12 000幅绿萝叶片仿真光亮度分布图,利用卷积神经网络对模拟光谱数据进行训练,得到预训练模型;基于预训练模型进行迁移学习,在少量实测绿萝叶片光谱数据上对模型进行微调,进行绿萝光学参数反演,得到吸收系数μa反演准确率为84.83%、散射系数μs反演准确率为83.33%;在此基础上引入最大均值差异方法,提升迁移效果。结果表明,与普通的模型迁移方法相比,基于MMD迁移的方法具有更好的反演效果,吸收系数μa反演准确率为87.55%,散射系数μs反演准确率为86.67%。利用MMD迁移得到的全连接层特征建立叶绿素回归模型的决定系数R²为0.931 0,分别比直接使用光学参数和光谱图像建立的模型决定系数R2高0.046 8和0.062 0。研究表明,基于光学特性参数反演方法可以为叶绿素含量无损估测研究提供参考。
- 绿萝 /
- 叶绿素含量 /
- 高光谱图像 /
- 光学特性参数 /
- 蒙特卡洛方法 /
- 迁移学习
Abstract: In order to realize the rapid and accurate detection of chlorophyll content in plants,an inversion method based on MMD migration was proposed. Taking Epipremnum aureum leaves as the research object,the motion trajectory of photons was simulated with the Monte Carlo method based singlelayer flat plate model, totally 12 000 simulated luminance distribution maps were obtained. The convolutional neural network was used to train the simulated spectral data to obtain the pre-training model. Then based on the pre-training model,the model was fine-tuning on the measured spectral data of a small amount of Epipremnum aureum leaves to realize the inversion of the optical parameters. The inversion results were as follows: absorption coefficient μawas 84. 83% and scattering coefficient μswas 83. 33%. On this basis,the maximum mean difference method was added to improve the migration effect. The results showed that the MMD migration method had a better inversion effect with absorption coefficient μawas 87. 55% and scattering coefficient μswas 86. 67% compared with the common model migration method. The chlorophyll regression model was established by using the full connection layer characteristics obtained from MMD migration,and the determination coefficient R~2 of this method was 0. 046 8 and 0. 062 0 higher than that of the model established directly using optical parameters and spectral images,respectively. The experimental results showed that the inversion method based on optical characteristic parameters can provide important reference for the research of chlorophyll nondestructive detection.
- Epipremnum aureum /
- chlorophyll content /
- hyperspectral image /
- optical characteristic parameters /
- Monte Carlo method /
- transfer learning

HTML全文

参考文献(25)

[1]	鲁敏,景荣荣,赵洁,等.苯污染胁迫下室内植物叶绿素含量变化分析研究[J].山东建筑大学学报,2016,31(1):1-6.LU Min,JING Rongrong,ZHAO Jie,et al. Analysis of indoor plant chlorophyll content in benzene pollution stress[J]. Journal of Shandong Jianzhu University,2016,31(1):1-6.(in Chinese)
[2]	GHASEMI M,ARZANI K,YADOLLAHI A,et al. Estimate of leaf chlorophyll and nitrogen content in Asian Pear(Pyrus serotina Rehd.)by CCM-200[J]. Notulae Scientia Biologicae,2011,3(1):91-94.
[3]	邹小波,张小磊,石吉勇,等.基于高光谱图像的黄瓜叶片叶绿素含量分布检测[J].农业工程学报,2014,30(13):169-175.ZOU Xiaobo,ZHANG Xiaolei,SHI Jiyong,et al. Detection of chlorophyll content distribution in cucumber leaves based on hyperspectral imaging[J]. Transactions of the CSAE,2014,30(13):169-175.(in Chinese)
[4]	WELLBURN A R. The spectral determination of chlorophyll a and chlorophyll b,as well as total carotenoids,using various solvents with spectrophotometers of different resolution[J]. Journal of Plant Physiology,1994,144(3):307-313.
[5]	李鹏程,董合林,刘爱忠,等.棉花上部叶片叶绿素SPAD值动态变化研究[J].中国农学通报,2012,28(3):121-126.LI Pengcheng,DONG Helin,LIU Aizhong,et al. A study on dynamic change of chlorophyll SPAD values of upper leaves in main stem of cotton[J]. Chinese Agricultural Science Bulletin,2012,28(3):121-126.(in Chinese)
[6]	徐爽,何建国,马瑜,等.高光谱图像技术在水果品质检测中的研究进展[J].食品研究与开发,2013,34(10):4-8.XU Shuang,HE Jianguo,MA Yu,et al. Research progress of hyperspectral imaging technology for nondestructive detection of fruit quality[J]. Food Research and Development,2013,34(10):4-8.(in Chinese)
[7]	岳学军,全东平,洪添胜,等.柑橘叶片叶绿素含量高光谱无损检测模型[J].农业工程学报,2015,31(1):294-302.YUE Xuejun,QUAN Dongping,HONG Tiansheng,et al. Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves[J]. Transactions of the CSAE,2015,31(1):294-302.(in Chinese)
[8]	岳学军,凌康杰,洪添胜,等.基于高光谱图像的龙眼叶片叶绿素含量分布模型[J/OL].农业机械学报,2018,49(8):25-32.YUE Xuejun,LING Kangjie,HONG Tiansheng,et al. Distribution model of chlorophyll content for Longan leaves based on hyperspectral imaging technology[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(8):25-32. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20180802&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2018. 08. 002.(in Chinese)
[9]	董哲,杨武德,张美俊,等.基于高光谱遥感的玉米叶片SPAD值估算模型研究[J].作物杂志,2019,190(3):126-131.DONG Zhe,YANG Wude,ZHANG Meijun,et al. Estimation models of maize leaf SPAD value based on hyperspectral remote sensing[J]. Crops,2019,190(3):126-131.(in Chinese)
[10]	朱军伟,张彦娥,王晓敏,等.基于图像纹理的玉米叶片叶绿素含量分析研究[J].微计算机信息,2010,26(10):106-108.ZHU Junwei,ZHANG Yane,WANG Xiaomin,et al. Analysis and research of chlorophyll content in maize leaf based on image texture[J]. Microcomputer Information,2010,26(10):106-108.(in Chinese)
[11]	方振欢.用于水果组织光传输特性检测的单积分球系统研制及应用[D].杭州:浙江大学,2015.FANG Zhenhuan. Development and application of a single integrating sphere system for detecting optical properties of fruit tissue[D]. Hangzhou:Zhejiang University,2015.(in Chinese)
[12]	HUANG M,LU R. Apple mealiness detection using hyperspectral scattering technique[J]. Postharvest Biology and Technology,2010,58(3):168-175.
[13]	王爱臣.空间分辨高光谱成像技术测量单/双层农产品组织光学特性的研究[D].杭州:浙江大学,2017.WANG Aichen. Measuring the optical properties of one/two-layer tissue of agro-products using hyperspectral imaging-based spatially-resolved technique[D]. Hangzhou:Zhejiang University,2017.(in Chinese)
[14]	陈荣,陈韶华,刘江海.强散射生物组织光学特性参数的重构[J].湖北大学学报(自然科学版),2006,28(1):45-47.CHEN Rong,CHEN Shaohua,LIU Jianghai. Reconstructing optical properties parameter of highly scattering biological tissue[J]. Journal of Hubei University(Natural Science Edition),2006,28(1):45-47.(in Chinese)
[15]	刘奇.生物组织光学模型的蒙特卡罗模拟研究[D].武汉:武汉理工大学,2013.LIU Qi. Research on biological tissue optical model by Monte Carlo simulation[D]. Wuhan:Wuhan University of Technology,2013.(in Chinese)
[16]	林相泽,朱赛华,张俊媛,等.基于迁移学习和Mask R-CNN的稻飞虱图像分类方法[J/OL].农业机械学报,2019,50(7):201-207.LIN Xiangze,ZHU Saihua,ZHANG Junyuan,et al. Rice planthopper image classification method based on transfer learning and Mask R-CNN[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(7):201-207. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20190721&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2019. 07. 021.(in Chinese)
[17]	郑一力,张露.基于迁移学习的卷积神经网络植物叶片图像识别方法[J/OL].农业机械学报,2018,49(增刊):354-359.ZHENG Yili,ZHANG Lu. Plant leaf image recognition method based on transfer learning with convolutional neural networks[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(Supp.):354-359. http:∥www. j-csam.org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=2018s047&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2018. S0. 047.(in Chinese)
[18]	龙满生,欧阳春娟,刘欢,等.基于卷积神经网络与迁移学习的油茶病害图像识别[J].农业工程学报,2018,34(18):194-201.LONG Mansheng, OUYANG Chunjuan, LIU Huan, et al. Image recognition of camellia oleifera diseases based on convolutional neural network&transfer learning[J]. Transactions of the CSAE,2018,34(18):194-201.(in Chinese)
[19]	许景辉,邵明烨,王一琛,等.基于迁移学习的卷积神经网络玉米病害图像识别[J/OL].农业机械学报,2020,51(2):230-236,253.XU Jinghui,SHAO Mingye,WANG Yichen,et al. Recognition of corn leaf spot and rust based on transfer learning with convolutional neural network[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2020,51(2):230-236,253. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=2002025&journal_id=jcsam.DOI:10. 6041/j. issn. 1000-1298. 2020. 02. 025.(in Chinese)
[20]	徐焕良,周冰清,王浩云,等.基于模型迁移的苹果光学特征参数反演[J/OL].农业机械学报,2020,51(11):264-271.XU Huanliang,ZHOU Bingqing,WANG Haoyun,et al. Inversion of apple optical feature parameters based on model migration[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2020,51(11):264-271. http:∥www. jcsam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20201129&journal_id=jcsam. DOI:10. 6041/j. issn.1000-1298. 2020. 11. 029.(in Chinese)
[21]	郑宗生,胡晨雨,姜晓轶.基于改进的最大均值差异算法的深度迁移适配网络[J].计算机应用,2020,40(11):3107-3112.ZHENG Zongsheng, HU Chenyu, JIANG Xiaoyi. Deep transfer adaptive network based on improved maximum mean discrepancy algorithm[J]. Journal of Computer Applications,2020,40(11):3107-3112.(in Chinese)
[22]	王浩云,李亦白,张煜卓,等.基于光子传输模拟的苹果品质高光谱检测源探位置研究[J].农业工程学报,2019,35(4):281-289.WANG Haoyun,LI Yibai,ZHANG Yuzhuo,et al. Research on hyperspectral light and probe source location on apple for quality detection based on photon transmission simulation[J]. Transactions of the CSAE,2019,35(4):281-289.(in Chinese)
[23]	汪传建,赵庆展,马永建,等.基于卷积神经网络的无人机遥感农作物分类[J/OL].农业机械学报,2019,50(11):161-168.WANG Chuanjian,ZHAO Qingzhan,MA Yongjian,et al. Crop identification of drone remote sensing based on convolutional neural network[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(11):161-168. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20191118&journal_id=jcsam. DOI:10. 6041/j.issn. 1000-1298. 2019. 11. 018.(in Chinese)
[24]	李萍,倪志伟,朱旭辉,等.联合类间及域间分布适配的迁移学习方法[J].模式识别与人工智能,2020,33(1):1-10.LI Ping,NI Zhiwei,ZHU Xuhui,et al. Transfer learning with joint inter-class and inter-domain distributional adaptation[J].Pattern Recognition and Artificial Intelligence,2020,33(1):1-10.(in Chinese)
[25]	闫明壮,王浩云,吴媛媛,等.基于光谱与纹理特征融合的绿萝叶绿素含量检测[J].南京农业大学学报,2020,24(11):1-14.YAN Mingzhuang,WANG Haoyun,WU Yuanyuan,et al. Detection of chlorophyll content of Epipremnum aureum based on fusion of spectrum and texture features[J]. Journal of Nanjing Agricultural University,2020,24(11):1-14.(in Chinese)