基于高光谱深度特征的油菜叶片锌含量检测  

Non-destructive determination of zinc content in oilseed rape leaves based on hyperspectral depth characteristics

作　　者：周鑫[1,4,5] 王坚 赵春江 孙俊 史磊[1] ZHOU Xin;WANG Jian;ZHAO Chunjiang;SUN Jun;SHI Lei(School of Electrical and Information Engineering,Jiangsu University,Zhenjiang 212013,China;Information Technology Research Center,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China;National Engineering Research Center for Information Technology in Agriculture,Beijing 100097,China;Key Laboratory for Theory and Technology of Intelligent Agricultural Machinery and Equipment of Jiangsu University,Zhenjiang 212013,China;Jiangsu Province and Education Ministry Co-sponsored Synergistic Innovation Center of Modern Agricultural Equipment,Zhenjiang 212013,China)

机构地区：[1]江苏大学电气信息工程学院,镇江212013 [2]北京市农林科学院信息技术研究中心,北京100097 [3]国家农业信息化工程技术研究中心,北京100097 [4]江苏大学智能农机装备理论与技术重点实验室,镇江212013 [5]省部共建现代农业装备与技术协同创新中心,镇江212013

出　　处：《农业工程学报》2024年第19期262-271,共10页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金青年基金项目(32201653);中国博士后科学基金项目(2021M701479);江苏大学农业工程学部项目(NGXB20240202);江苏大学大学生科研课题立项项目(Y23A093)。

摘　　要：为了实现油菜叶片锌含量的快速无损检测,该研究采用一种基于高光谱成像技术结合深度迁移学习算法的高精度检测方法,通过无土栽培的方式,设置10个不同胁迫类别(2种不同硅浓度环境结合5个不同锌胁迫梯度),获取无硅环境和有硅环境中重金属锌胁迫下总计4000个油菜叶片样本。利用高光谱成像设备采集油菜叶片样本高光谱图像信息,并将整个叶片作为感兴趣区域获取其平均光谱信息。通过对比不同预处理后光谱对硅作用下油菜叶片锌含量预测性能,确立标准正态变量变换(standard normalized variable,SNV)算法作为最佳预处理方法,并对SNV处理的光谱数据进行进一步分析。利用堆叠自编码器(stacked auto-encoder,SAE)对预处理后的最佳光谱数据进行降维,并与传统的降维算法进行比较。最后,对最优SAE深度学习网络进行迁移学习,得到迁移堆叠自编码器(transfer stacked auto-encoder,TSAE)模型,验证无硅环境和有硅环境中深度学习模型之间的可迁移性。结果表明,基于SAE提取深度特征的支持向量机回归(support vector machine regression,SVR)模型对无硅环境或有硅环境中油菜叶片中锌含量的预测效果较好。无硅环境和有硅环境中所建立的SNV-SAE-SVR模型性能较佳,预测集的决定系数(R_p~2)、均方根误差(RMSEP)和相对分析误差(RPD)分别为0.8507、0.03466 mg/kg和2.607,0.8766、0.02854 mg/kg和2.732。此外,基于T-SAE提取深度特征的SVR模型能有效实现无硅环境和有硅环境中锌含量的预测,最佳SNV-T-SAE-SVR模型预测集的R_p~2、RMSEP和RPD分别为0.8810、0.02748 mg/kg和2.966。研究结果表明,深度迁移学习方法结合高光谱成像无损检测技术能够有效实现油菜叶片锌含量检测。Non-destructive testing can be expected to rapidly and accurately detect the zinc content in oilseed rape leaves.In this study,a high-precision detection was realized to combine with deep transfer learning using hyperspectral imaging technology.Oilseed rape with similar growth shape was divided into two groups(Group Z and Group ZS)by soilless cultivation,each of which included the five types of stress reagents.Therefore,400 oilseed rape leaf samples were selected for each type of stress reagent,while 2000 oilseed rape leaf samples were collected for each group,leading to 4000 oilseed rape leaf samples in total.The hyperspectral image information of oilseed rape leaf samples was obtained by hyperspectral imaging equipment.The whole blade was taken as the region of interest.The average spectral information was obtained in the region of interest after calculation.Firstly,the predictive performance of different pre-treated spectra was compared for the zinc content in oilseed rape leaves under the action of silicon.Standard normalized variable(SNV)was established as the best pre-processing.The spectral data was processed by SNV for further analysis.A stacked auto-encoder(SAE)was used to reduce the dimensionality of the best pre-processed spectral data,compared with the traditional.Finally,transfer stacked auto-encoder(T-SAE)was performed on the optimal SAE deep learning network.The transfer learning model was obtained to verify the portability between the deep learning models in silicon-free and silicon environments.The results showed that the support vector machine regression(SVR)model with SAE extraction depth features shared the best prediction on zinc content in the oilseed rape leaves under silicon-free or silicon environments.The best performance was achieved in the SNV-SAE-SVR model under a silicon-free environment.The coefficient of determination(Rc2)and root mean square error(RMSEC)of the calibration set were 0.9393 and 0.01822 mg/kg,respectively,while the coefficient of determination(Rp2),root mean square er

关 键 词：无损检测 重金属 硅环境 深度学习 迁移学习 高光谱图像 

分 类 号：S126[农业科学—农业基础科学]