• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于结构光成像的谷物三维点云形状提取和饱满/不饱满籽粒识别方法。

Cereal grain 3D point cloud analysis method for shape extraction and filled/unfilled grain identification based on structured light imaging.

机构信息

College of Engineering, Huazhong Agricultural University, Wuhan, 430070, People's Republic of China.

National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research (Wuhan), Huazhong Agricultural University, Wuhan, 430070, People's Republic of China.

出版信息

Sci Rep. 2022 Feb 24;12(1):3145. doi: 10.1038/s41598-022-07221-4.

DOI:10.1038/s41598-022-07221-4
PMID:35210561
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8873360/
Abstract

Cereals are the main food for mankind. The grain shape extraction and filled/unfilled grain recognition are meaningful for crop breeding and genetic analysis. The conventional measuring method is mainly manual, which is inefficient, labor-intensive and subjective. Therefore, a novel method was proposed to extract the phenotypic traits of cereal grains based on point clouds. First, a structured light scanner was used to obtain the grains point cloud data. Then, the single grain segmentation was accomplished by image preprocessing, plane fitting, region growth clustering. The length, width, thickness, surface area and volume was calculated by the specified analysis algorithms for grain point cloud. To demonstrate this method, experimental materials included rice, wheat and corn were tested. Compared with manual measurement results, the average measurement error of grain length, width and thickness was 2.07%, 0.97%, 1.13%, and the average measurement efficiency was about 9.6 s per grain. In addition, the grain identification model was conducted with 25 grain phenotypic traits, using 6 machine learning methods. The results showed that the best accuracy for filled/unfilled grain classification was 90.184%.The best accuracy for indica and japonica identification was 99.950%, while for different varieties identification was only 47.252%. Therefore, this method was proved to be an efficient and effective way for crop research.

摘要

谷物是人类的主要食物。谷物形状的提取和饱满/不饱满谷物的识别对于作物育种和遗传分析具有重要意义。传统的测量方法主要是手动的，效率低下、劳动强度大且主观。因此，提出了一种基于点云提取谷物表型特征的新方法。首先，使用结构光扫描仪获取谷物点云数据。然后，通过图像预处理、平面拟合、区域生长聚类完成单粒分割。通过指定的谷物点云分析算法计算长度、宽度、厚度、表面积和体积。为了验证该方法，对水稻、小麦和玉米等实验材料进行了测试。与手动测量结果相比，谷物长度、宽度和厚度的平均测量误差分别为 2.07%、0.97%和 1.13%，平均测量效率约为每粒 9.6 秒。此外，使用 6 种机器学习方法对 25 个谷物表型特征进行了谷物识别模型的构建。结果表明，饱满/不饱满谷物分类的最佳准确率为 90.184%。籼稻和粳稻识别的最佳准确率为 99.950%，而不同品种的识别准确率仅为 47.252%。因此，该方法被证明是一种用于作物研究的高效、有效的方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/97997384f3fe/41598_2022_7221_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/eb2c50bf114f/41598_2022_7221_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/807d2880dc31/41598_2022_7221_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/fa3d7e4f950c/41598_2022_7221_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/932fba95157e/41598_2022_7221_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/9e6fa154a64d/41598_2022_7221_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/98d5ac959b2f/41598_2022_7221_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/fd3073a4e8b8/41598_2022_7221_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/b8f6c568941b/41598_2022_7221_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/0a09026d4872/41598_2022_7221_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/56615f62d74b/41598_2022_7221_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/6f161791e0e4/41598_2022_7221_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/97997384f3fe/41598_2022_7221_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/eb2c50bf114f/41598_2022_7221_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/807d2880dc31/41598_2022_7221_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/fa3d7e4f950c/41598_2022_7221_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/932fba95157e/41598_2022_7221_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/9e6fa154a64d/41598_2022_7221_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/98d5ac959b2f/41598_2022_7221_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/fd3073a4e8b8/41598_2022_7221_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/b8f6c568941b/41598_2022_7221_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/0a09026d4872/41598_2022_7221_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/56615f62d74b/41598_2022_7221_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/6f161791e0e4/41598_2022_7221_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/734c/8873360/97997384f3fe/41598_2022_7221_Fig12_HTML.jpg

相似文献

1
Cereal grain 3D point cloud analysis method for shape extraction and filled/unfilled grain identification based on structured light imaging.基于结构光成像的谷物三维点云形状提取和饱满/不饱满籽粒识别方法。
Sci Rep. 2022 Feb 24;12(1):3145. doi: 10.1038/s41598-022-07221-4.
2
A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet+.一种基于结构光成像和改进型PointNet+的填充/未填充谷物分类新方法。
Sensors (Basel). 2023 Jul 12;23(14):6331. doi: 10.3390/s23146331.
3
An Intelligent Analysis Method for 3D Wheat Grain and Ventral Sulcus Traits Based on Structured Light Imaging.基于结构光成像的三维小麦籽粒及腹沟性状智能分析方法
Front Plant Sci. 2022 Apr 13;13:840908. doi: 10.3389/fpls.2022.840908. eCollection 2022.
4
Size measurement and filled/unfilled detection of rice grains using backlight image processing.基于背光图像处理的稻谷尺寸测量与饱满度检测
Front Plant Sci. 2023 Oct 13;14:1213486. doi: 10.3389/fpls.2023.1213486. eCollection 2023.
5
Detection and characterization of spike architecture based on deep learning and X-ray computed tomography in barley.基于深度学习和X射线计算机断层扫描技术对大麦穗形态结构的检测与表征
Plant Methods. 2023 Oct 27;19(1):115. doi: 10.1186/s13007-023-01096-w.
6
High-throughput and separating-free phenotyping method for on-panicle rice grains based on deep learning.基于深度学习的水稻穗上籽粒高通量免分离表型分析方法
Front Plant Sci. 2023 Sep 18;14:1219584. doi: 10.3389/fpls.2023.1219584. eCollection 2023.
7
Nondestructive 3D Image Analysis Pipeline to Extract Rice Grain Traits Using X-Ray Computed Tomography.利用X射线计算机断层扫描技术提取水稻籽粒性状的无损三维图像分析流程
Plant Phenomics. 2020 May 2;2020:3414926. doi: 10.34133/2020/3414926. eCollection 2020.
8
Extraction of soybean plant trait parameters based on SfM-MVS algorithm combined with GRNN.基于结构光运动恢复形状-多视角立体视觉（SfM-MVS）算法与广义回归神经网络（GRNN）的大豆植株性状参数提取
Front Plant Sci. 2023 Jul 25;14:1181322. doi: 10.3389/fpls.2023.1181322. eCollection 2023.
9
Segmentation and counting of wheat spike grains based on deep learning and textural feature.基于深度学习和纹理特征的小麦穗粒分割与计数
Plant Methods. 2023 Aug 1;19(1):77. doi: 10.1186/s13007-023-01062-6.
10
A Low-Cost 3D Phenotype Measurement Method of Leafy Vegetables Using Video Recordings from Smartphones.一种利用智能手机拍摄的视频记录进行叶菜类低成本 3D 表型测量方法。
Sensors (Basel). 2020 Oct 25;20(21):6068. doi: 10.3390/s20216068.

引用本文的文献

1
Large-Scale Rice Mutant Establishment and High-Throughput Mutant Manipulation Help Advance Rice Functional Genomics.大规模水稻突变体构建及高通量突变体操作助力水稻功能基因组学发展
Plants (Basel). 2025 May 16;14(10):1492. doi: 10.3390/plants14101492.
2
Integrative multi-omics analysis reveals genetic and heterotic contributions to male fertility and yield in potato.综合多组学分析揭示了马铃薯雄性育性和产量杂种优势的遗传贡献。
Nat Commun. 2024 Oct 5;15(1):8652. doi: 10.1038/s41467-024-53044-4.
3
An Overview of High-Throughput Crop Phenotyping: Platform, Image Analysis, Data Mining, and Data Management.

本文引用的文献

1
Comparative study of classifiers for human microbiome data.人类微生物组数据分类器的比较研究
Med Microecol. 2020 Jun;4. doi: 10.1016/j.medmic.2020.100013. Epub 2020 May 11.
2
Measurement of Rock Joint Surfaces by Using Smartphone Structure from Motion (SfM) Photogrammetry.利用基于运动结构（SfM）的摄影测量法通过智能手机测量岩石节理面
Sensors (Basel). 2021 Jan 30;21(3):922. doi: 10.3390/s21030922.
3
CRISPR/Cas9-mediated mutation of OsSWEET14 in rice cv. Zhonghua11 confers resistance to Xanthomonas oryzae pv. oryzae without yield penalty.
高通量作物表型分析概述：平台、图像分析、数据挖掘和数据管理。
Methods Mol Biol. 2024;2787:3-38. doi: 10.1007/978-1-0716-3778-4_1.
4
A three-dimensional vision measurement method based on double-line combined structured light.一种基于双线组合结构光的三维视觉测量方法。
Sci Rep. 2023 Oct 31;13(1):18660. doi: 10.1038/s41598-023-46176-y.
5
A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet+.一种基于结构光成像和改进型PointNet+的填充/未填充谷物分类新方法。
Sensors (Basel). 2023 Jul 12;23(14):6331. doi: 10.3390/s23146331.
CRISPR/Cas9 介导的水稻品种中花 11 中 OsSWEET14 的突变赋予了对稻白叶枯病菌的抗性而不降低产量。
BMC Plant Biol. 2020 Jul 3;20(1):313. doi: 10.1186/s12870-020-02524-y.
4
High throughput phenotyping dataset related to seed and seedling traits of sugar beet genotypes.与甜菜基因型种子和幼苗性状相关的高通量表型数据集。
Data Brief. 2020 Jan 27;29:105201. doi: 10.1016/j.dib.2020.105201. eCollection 2020 Apr.
5
Crop Phenomics and High-Throughput Phenotyping: Past Decades, Current Challenges, and Future Perspectives.作物表型组学和高通量表型分析：过去几十年、当前挑战和未来展望。
Mol Plant. 2020 Feb 3;13(2):187-214. doi: 10.1016/j.molp.2020.01.008. Epub 2020 Jan 22.
6
Measuring crops in 3D: using geometry for plant phenotyping.三维测量作物：利用几何学进行植物表型分析。
Plant Methods. 2019 Sep 3;15:103. doi: 10.1186/s13007-019-0490-0. eCollection 2019.
7
Use of X-ray micro computed tomography imaging to analyze the morphology of wheat grain through its development.利用X射线显微计算机断层扫描成像技术分析小麦籽粒在其发育过程中的形态。
Plant Methods. 2019 Jul 31;15:84. doi: 10.1186/s13007-019-0468-y. eCollection 2019.
8
Detection and correction of assembly errors of rice Nipponbare reference sequence.检测和校正水稻日本晴参考序列的组装错误。
Plant Biol (Stuttg). 2014 May;16(3):643-50. doi: 10.1111/plb.12090. Epub 2013 Nov 8.
9
Plant phenomics and high-throughput phenotyping: accelerating rice functional genomics using multidisciplinary technologies.植物表型组学和高通量表型分析：利用多学科技术加速水稻功能基因组学研究。
Curr Opin Plant Biol. 2013 May;16(2):180-7. doi: 10.1016/j.pbi.2013.03.005. Epub 2013 Apr 8.
10
SmartGrain: high-throughput phenotyping software for measuring seed shape through image analysis.SmartGrain：高通量表型分析软件，通过图像分析测量种子形状。
Plant Physiol. 2012 Dec;160(4):1871-80. doi: 10.1104/pp.112.205120. Epub 2012 Oct 10.