摘要
玉米籽粒构成和精细结构与玉米产量及品质直接相关。本文提出一种基于CT图像的玉米籽粒三维结构自动测量方法,快速提取、统计玉米籽粒成分和结构性状,评估不同玉米品种籽粒间性状差异。首先,利用Micro-CT获取批量玉米籽粒CT图像,通过Watershed算法准确分割出单颗籽粒;进而,设计基于注意力机制RAUNet-3D网络准确提取出籽粒胚;最后,建立自动化玉米籽粒表型管道,计算籽粒、胚、胚乳和空腔的共23项性状,用于玉米籽粒性状分析和品种鉴定。选取4个玉米品种籽粒(登海605、京科968、先正达408和农华5号)共120颗籽粒进行验证,结果表明籽粒CT扫描成像效率提高到1 min/粒,籽粒表型提取效率为10 s/粒,胚分割精度可达93.4%,粒长、粒宽和粒厚的R^(2)分别为0.902、0.926和0.904,籽粒品种分类精度达90.4%。本文方法实现了玉米籽粒及其胚、胚乳、空腔三维结构无损、快速测量,提取的性状能够表征不同玉米品种籽粒间表型差异,为开展大规模玉米籽粒三维表型鉴定奠定了基础。
The composition and fine structure of corn kernel are directly related to yield and quality of maize.An automatic measurement method for three-dimensional structures of corn kernels based on CT images was proposed,which could quickly extract and analyze the components and structural traits of corn kernel,and the differences of traits among different maize varieties were evaluated.Firstly,CT images of batch corn kernels were obtained by Micro-CT,and single kernel was accurately segmented by using Watershed algorithm.Furthermore,the improved RAUNet-3 D network based on attention mechanism was designed to accurately extract kernel embryos.Finally,an automatic phenotype pipeline was established to calculate 23 traits related to corn kernel,embryo,endosperm and cavity,which were used for traits analysis and variety identification of maize kernel.A total of 120 kernels of four corn varieties(Denghai 605,Jingke 968,Syngenta 408 and Nonghua 5)were selected for performance verification.The experimental results showed that the data acquirement efficiency was improved to about 1 min per kernel,and the efficiency of algorithm pipeline was about 10 s per kernel,and the segmentation accuracy of kernel embryos reached 93.4%.The determinant coefficients of kernel length,width and thickness were 0.902,0.926 and 0.904,respectively.The proposed method could quickly and non-destructively measure the three-dimensional structure of corn kernel and its components,and the extracted traits could represent the phenotypic differences among different corn varieties,which laid a foundation for large-scale three-dimensional phenotypic measurement and identification of corn kernels.
作者
杜建军
李大壮
廖生进
卢宪菊
郭新宇
赵春江
DU Jianjun;LI Dazhuang;LIAO Shengjin;LU Xianju;GUO Xinyu;ZHAO Chunjiang(National Engineering Research Center for Information Technology in Agriculture,Beijing 100097,China;Beijing Key Laboratory of Digital Plants,Beijing 100097,China;College of Plant Science and Technology,Huazhong Agricultural University,Wuhan 430070,China)
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2022年第12期244-253,289,共11页
Transactions of the Chinese Society for Agricultural Machinery
基金
北京市农林科学院作物表型协同创新中心项目(KJCX201917)
北京市农林科学院创新能力建设专项(KJCX20180423)
北京市农林科学院改革与发展项目和国家自然科学基金项目(U21A20205)
财政部和农业农村部:国家现代农业产业技术体系专项(CARS-02)