基于人工智能的苗木质量无损检测研究进展

编号 lyqk008617

中文标题 基于人工智能的苗木质量无损检测研究进展

作者 李玉荣  刘英  汪力  费叶琦 

作者单位 南京林业大学机械电子工程学院, 南京 210037

期刊名称 世界林业研究 

年份 2020 

卷号 33

期号 6

栏目编号 1

栏目名称 专题论述 

中文摘要 我国森林面积广域，人工林面积居世界首位。为了确保质优量足的苗木进一步提升苗木造林效果，苗木质量的无损检测成为苗木质量精准快速评价的关键。文中概述人工智能理论与算法在苗木质量的形态、生理和活力指标3个方面的无损检测应用现状；针对传统检测指标单一、效率低和主观误差大的问题，指出综合应用图像采集、数字图像处理和机器学习技术的人工智能算法与理论在苗木质量评价指标检测领域具有明显优势，并从检测技术融合、提升检测算法和多源数据融合等方面进行展望，旨在为苗木质量快速精准评价提供参考。

关键词 苗木质量  数字图像处理  无损检测  机器学习 

基金项目 国家自然科学基金面上项目“基于多信息融合的马尾松苗木活力快速精准预测模型研究”（31570714）；江苏省重点研发计划（产业前瞻与关键核心技术）项目（BE2019112）。

英文标题 Research Progress in Non-destructive Testing of Seedling Quality Based on Artificial Intelligence

作者英文名 Li Yurong, Liu Ying, Wang Li, Fei Yeqi

单位英文名 College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China

英文摘要 China boasts large forest area, and her artificial forest tops the world in area. In order to ensure the quality and quantity of seedling production and further improve the effect of afforestation with seedlings, the non-destructive testing of seedling is the key to the accurate and rapid evaluation of seedling quality. This paper reviews the application of artificial intelligent theory and algorithm to the non-destructive testing of morphological index, physiological index and vitality index of seedlings. In order to solve the problems of the traditional testing including unitary index, low efficiency and more subjective errors, the artificial intelligent theory and algorithm that integrates image acquisition, digital image processing and machine learning technology has obvious advantages in the field of seedling quality evaluation index testing. The paper also prospects the testing technology fusion, improvement of the testing algorithm and multi-source data fusion, with the expectation to provide references for rapid and accurate evaluation of seedling quality.

英文关键词 seedling quality;digital image processing;non-destructive testing;machine learning

起始页码 27

截止页码 32

投稿时间 2020/8/9

最后修改时间 2020/8/26

作者简介 李玉荣,女,汉族,博士生,主要研究方向为机器视觉、苗木质量检测方面的研究,E-mail:air5210@126.com。

通讯作者介绍 刘英,女,汉族,博士,教授,主要从事无损检测、图像处理方面的研究,E-mail:lying_new@163.com。

E-mail 刘英,女,汉族,博士,教授,主要从事无损检测、图像处理方面的研究,E-mail:lying_new@163.com。

分类号 S723

DOI 10.13348/j.cnki.sjlyyj.2020.0099.y

参考文献 [1] 祝燕,李庆梅,李淑娴,等.我国林木种苗质量管理现状与发展对策[J].世界林业研究,2019,32(5):63-66.
[2] 李亚麒,陈诗,孙继伟,等.2年生云南松苗木分级与生物量分配关系研究[J/OL].西南林业大学学报(自然科学),2020,40(5):25-31.[2020-07-10]. http://kns.cnki.net/kcms/detail/53.1218.S. 20200604.0844.002.html.
[3] 王竣,刘永国,曹建新,等.岩溶地区杉木容器苗分级方法及标准探讨[J].西部林业科学,2020,49(3):86-91.
[4] DRVODELIC D,ORSANIC M. Izbor kvalitetne šumske sadnice poljskog jasena (Fraxinus angustifolia Vahl) za umjetnu obnovu i pošumljavanje[J].Šumarski List,2019,143(11/12):577-585.
[5] 王雪莹,郭素娟.切根与不同形态氮素对板栗苗木根系构型及生长的影响[J].东北林业大学学报,2020,48(4):15-19.
[6] JACOBS D F,SALIFU K F,SEIFERT J R. Relative contribution of initial root and shoot morphology in predicting field performance of hardwood seedlings[J].New Forests, 2005, 30(2/3):235-251.
[7] RINGEY M P,KRANZLER G A.Neural network recognition of the conifer seedling root collar[J].Proceedings of SPIE-The International Society for Optical Engineering,1996,2907(20):109-118.
[8] 吴羡,白景峰,蔺百安,等.针叶树种计算机视觉的苗木分级系统的研究[J].东北林业大学学报,1998,26(4):32-35.
[9] 白景峰,赵学增,强锡富,等.针叶造林苗木计算机视觉特征提取方法的研究[J].东北林业大学学报,2000,28(5):94-96.
[10] 汪学良.马尾松苗木活力指数提取若干关键技术的研究[D].南京:南京林业大学,2018.
[11] 李玉荣,刘英,汪力.多信息融合的马尾松苗木静态指标检测方法[J].林业工程学报,2019,4(5):129-133.
[12] 李杨先,张慧春,杨旸.一种基于图像处理技术的植物形态表型参数获取方法[J/OL].林业工程学报,2020,5(6):128-136.[2020-08-08]. https://doi.org/10.13360/j.issn.2096-1359.201911003.
[13] DAVIS A S, JACOBS D F, KEVYN E W, et al.Organic matter added to bareroot nursery beds influences soil properties and morphology of fraxinus pennsylvanica and Quercus rubra Seedlings[J].New Forests, 2006, 31(2):293-303.
[14] MORRISON I K,ARMSON K A.The rhizometer-adevice for measuring roots of tree seedling[J].The Forestry Chroaide,1968,44(2):21-23.
[15] BUCKLEY D J, REID W S, ARMSON K A.A digital recording system for measuring root area and dimensions of tree seedlings[J].Transactions of the Asabe, 1978, 21(2):0222-0226.
[16] COSTA C,DWYER L M,HAMEL C,et al.Root contrast enhancement for measurement with optical scanner-based image analysis[J].Canadian Journal of Botany,2001,79(1):23-29.
[17] COSTA C,DWYER L M,HAMILTON R I,et al.A sampling method for measurement of large root systems with scanner-based image analysis[J].Agronomy Journal,2000,92(4):621-627.
[18] 温维亮,郭新宇,赵春江,等.作物根系构型三维探测与重建方法研究进展[J].中国农业科学,2015,48(3):436-448.
[19] 李一海,周学成,陈富强.基于XCT序列图像的植物根系三维矢量模型构建方法[J].江苏农业科学,2017,45(14):179-184.
[20] 姬兴亮.基于三维激光点云分割匹配的同步定位与构图算法研究[D].成都:电子科技大学,2020.
[21] 李加刚.基于计算机视觉植物根系表型特征的研究[D].太原:山西农业大学,2019.
[22] 倪超,张云,高捍东,等.基于多目视觉的马尾松苗木形态学参数提取研究[J].林业工程学报,2018,3(2):123-128.
[23] 陈拓.基于卷积神经网络的立体匹配技术研究[D].杭州:浙江大学,2017.
[24] 张博宇,滕维超.铅胁迫对黄花风铃木幼苗生长和生理指标的影响[J].东北林业大学学报,2020,48(7):7-10,16.
[25] 高亚利,王振锡,连玲,等.截形叶螨危害下枣叶片含水率高光谱估测模型[J].经济林研究,2020,38(2):114-122.
[26] 倪超,张云,高捍东.基于NIRS的马尾松苗木根部含水量预测模型[J].南京林业大学学报(自然科学版),2019,43(6):91-96.
[27] 杨俊杰,左志宇,毛罕平,等.基于机器视觉的植物水势测量装置设计[J].农机化研究,2020,42(11):76-80.
[28] 苗晨,徐爽,张金鑫,等.基于傅里叶中红外光谱预测东北次生林叶片全氮含量[J].生态学杂志,2019,38(12):3864-3869.
[29] 钟穗希,李子波,唐荣年.基于PCA-Kmeans聚类的橡胶树叶片氮含量近红外高光谱诊断模型研究[J/OL].海南大学学报(自然科学版):2020.[2020-07-06].http://kns.cnki.net/kcms/detail/46.1013.N.20200616.1529.008.html.
[30] NI C,WANG D Y, TAO Y.Variable weighted convolutional neural network for the nitrogen content quantization of Masson pine seedling leaves with near-infrared spectroscopy[J].Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy,2019,209(4):32-39.
[31] 罗曦,吴方喜,谢鸿光,等.近红外光谱的水稻抗性淀粉含量测定研究[J].光谱学与光谱分析,2016,36(3):697-701.
[32] LU X,WEI S,CHEN B C,et al. Rapid and nondestructive detection of multiple adulterants in kudzu starch by near infrared (NIR) spectroscopy and chemometrics[J].LWT-Food Science and Technology,2015,61(2):590-595.
[33] 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.
[34] 龙耀威,孙红,高德华,等.镀膜型光谱成像数据提取与作物叶绿素分布探测研究[J].光谱学与光谱分析,2020,40(5):1581-1587.
[35] VIRK G,SNIDER J L,PILON C.Associations between first true leaf physiology and seedling vigor in cotton under different field conditions[J].Crop Science,2020,60(1):404-418.
[36] ACEVEDO M,RUBILAR R,DUMROESE R K,et al.Nitrogen loading of Eucalyptus globulus seedlings:nutritional dynamics and influence on morphology and root growth potential[J].New Forests, 2020.https://doi.org/10.1007/s11056-020-09778-2.
[37] GROSSNICKLE S,MACDONALD J.Seedling quality:history,applica-tion,and plant attributes[J].Forests,2018,9(5):283.
[38] WALTER A,SPIES H,TERJUNG S,et al. Spatio-temporal dynamics of expansion growth in roots:automatic quantification of diurnal course and temperature response by digital image sequence processing[J].Journal of Experimental Botany,2002,53(369):689-698.
[39] WEELE C M,JIANG H S,PALANIAPPAN K K,et al. A new algorithm for computational image analysis of deformable motion at high spatial and temporal resolution applied to root growth. Roughly uniform elongation in the meristem and also, after an abrupt acceleration, in the elongation zone[J].Plant Physiology,2003,132(3):1138-1148.
[40] RATHNAYAKE A P,KADONO H,TOYOOKA S,et al. A novel optical interference technique to measure minute root elongations of Japanese red pine (Pinus densiflora Seibold & Zucc.) seedlings infected with ectomycorrhizal fungi[J].Environmental and Experimental Botany,2008,64(3):314-321.
[41] 张慧春,周宏平,郑加强,等.植物表型平台与图像分析技术研究进展与展望[J].农业机械学报,2020,51(3):1-17.
[42] 王恒.应用于植物生理检测的高通量叶绿素荧光成像系统研究[D].杭州:浙江大学,2018.
[43] 付美娟.基于激光诱导叶绿素荧光检测技术研究[D].杭州:浙江师范大学,2019.
[44] WANG Z D, HU M H, ZHAI G T. Application of deep learning architectures for accurate and rapid detection of internal mechanical damage of blueberry using hyperspectral transmittance data[J].Sensors,2018,18(4):1126.DOI:10.3390/S18041126.

PDF全文 浏览全文