水稻植株穗部性状在体测量研究
|
摘要
水稻是世界最主要的粮食作物之一，全世界近一半人口以稻米为主食。水稻的产量一直是水稻育种中最为关心的问题。作为果实生长的器官，水稻穗部的性状如穗数、穗鲜重、穗干重、总粒数、实粒数、单株产量等直接与产量相关，因此是水稻的表型参数中能直接反应水稻育种水平的指标。在对水稻品种进行筛选和鉴定时，都需要对穗部性状参数进行测定与评价。
传统的穗部性状测量主要依赖于人工，存在操作繁琐、劳动强度大、测量准确性受人工主观因素影响大等缺点。利用遥感成像和机器视觉等技术实现大面积大田水稻和高通量盆栽水稻测量不依赖手工测量，效率高，应用广。大田水稻穗部性状测量主要利用遥感技术实现大面积水稻的整体产量估测，需要使用专用设备获取遥感数据，不适用于小面积或单株水稻产量的估测，也无法精确估算单株水稻穗部性状参数。针对单株盆栽水稻穂部性状的在体测量技术，经查阅未见相关学术文献发表。此外，现代育种技术能在一天内生产上千个新品种，每一个品种都需要进行穂部性状测量以确定其育种和推广的潜力和价值。在这种背景之下，急需一种快速、简单、有效的穗部性状测量技术，以解决目前穗部性状测量技术的局限性。
本研究基于机器视觉、图像处理、模式识别及数学建模技术，实现单株水稻穗部性状参数包括穗数、穗鲜重、穗干重、总粒数、实粒数、单株产量的在体测量。主要研究内容包括:(1）水稻稻穗区域的提取。研究图像分割与处理算法，从水稻植株图像中提取出稻穗区域，分割算法必须快速有效，以实现快速测量的要求。（2)水稻稻穗区域的识别。经过图像初步处理后提取得到的稻穗区域中，可能存在茎叶等不属于稻穗的区域，需开发合适的识别算法，实现稻穗区域的准确识别。（3）穂部性状在体测量。在稻穗区域的准确提取和识别的基础上，实现水稻穗部性状的在体测量。利用数学建模技术，建立合适的产量相关特征的估测模型。实验结果表明，穗数测量平均误差为0.5，其中95.3%的植株的测量误差在±1以内。5-fold交叉验证结果显示，穗鲜重、穗干重、总粒数、实粒数和单株产量5个回归模型的预测误差分别为7.93%、7.37%、8.59%、7.72%和7.45%。这种方法适用于不同环境下（温室环境下和露天环境下）的水稻产量的在体估测。用后验差检验法对建立的5个回归模型的模型精度验证结果均为二级-合格。
本文所述的水稻穗部性状在体测量方法，克服现有的仪器或研究所存在的问题，不需要将稻穗剪下后脱粒。结合自动化栽培、输送和图像采集平台，可实现盆栽水稻穂部性状的全自动化、高通量测量。主要创新点包括：（1）提出了一种在体、全自动化、高通量测量单株盆栽水稻穂部性状的新方法，解决了穂部性状测量依赖于人工测量的难题。（2）提出了水稻稻穗在体准确提取与识别的图像分析与处理新方法，解决了从水稻植株图像中提取与识别稻穗区域的技术难题，为单株盆栽水稻穂部性状在体测量的实现提供了技术支撑和先决条件。（3）提出了基于稻穗投影面积、茎叶投影面积和分形维数建立水稻产量相关特征包括穗鲜重、穗干重、总粒数、实粒数、单株产量的在体估测数学模型的新分析方法。本研究将提高单株水稻穗部性状参数获取的速度，推动表型组学的发展，对发现并揭示水稻等作物重要基因功能，加强和提升我国在功能基因组及作物遗传改良领域的水平和地位有非常重要的意义。
Rice is one of the world's most important crops. Approximately one half of world'spopulation feed on rice. Yield has always been the key object of most of the rice breedingprograms. Panicle is the reproduction organ of the rice plant where spikelets grow on.Panicle traits, including panicle number, panicle fresh weight, panicle dry weight, totalspikelet number, filled spikelet number, plant yield and so on, directly influence rice yield.In the screening and evaluation of the rice varieties, measuring and evaluating panicletraits is essential.
Traditional measurement of panicle traits mainly depends on manual operation,which is tedious, labor-intensive, subjective and error-prone. Utilizing moderntechnologies such as remote sensing technology and machine vision, it is feasible toautomatically evaluate field rice yield of a large area or pot-grown rice plants, with theadvantage of high efficiency and broad application. Concerning the researches about invivo panicle trait evaluation in the field, remote sensing technology is utilized to predictfield rice yield of a large area, which adopt specialized devices to acquire the spectral data.This technique is not capable of estimating the yield of a small area or individual riceplant. For individual port-grown rice plant trait measurement, academic publishment isunavailable. Meanwhile, modern breeding technologies are able to produce thousands ofnew varieties within a single day, and each variety needs to be measured to evaluate itsvalue and potential for breeding and generalization. Therefore, a fast, simple and effectivetechnique for in vivo rice panicle trait evaluation is urgently needed to withdraw thecurrent limitations.
This research aims to in vivo evaluate rice panicle traits for individual rice plant,including panicle number, panicle fresh weight, panicle dry weight, total spikelet number,filled spikelet number, and plant yield, using machine vision, image processing, patternrecognition and mathematical modelling. The main tasks of this work are:(1) Extractionof panicle regions from the rice plant using image processing algorithms. The algorithmshould be effective and fast so as to achieve high-throughput measurement.(2)Recognition of panicle regions from the rest organs of the plant.(3) Extraction of panicle number and development of mathematical models for estimation of yield-related traits invivo based on separation and recognition of the panicles. The results showed that, meanabsolute error (MAE) for panicle number extraction was0.50and95.3%percent of theplants generated measuring error within±1. Prediction errors evaluated using5-fold crossvalidation were7.93%,7.37%,8.59%,7.72%and7.45%for panicle fresh weight, panicledry weight, total spikelet number, filled spikelet number and plant yield respectively.These models are capable of estimating yield-related traits of rice plants grown in greenhouse and outdoors. Posterior variance test indicated that the precision grade was thesecond grade (up to standard) for all the five regression models.
The method presented in this work is capable of evaluating rice panicle traits in vivofor individual rice plant. This method would overcome the limitations in the currentdevices and researches, with no need of cutting off the panicles and threshing the spikelets.Integrated with automated growth, transportation and inspection platforms, this techniquecan be used for automatic and high-throughput evaluation of panicle traits. The maincontributions includes:(1) This work presents a new method for in vivo, automatic andhigh-throughput measurement of panicle traits for individual pot-grown rice plant.(2) Thiswork illustrates a new image processing pipeline for extraction and recognition of panicleregion from the rest organs of the rice plant.(3) This work proved the new idea ofestimating yield-related traits, including panicle fresh weight, panicle dry weight, totalspikelet number, filled spikelet number and plant yield, based on projected area of panicleregion, projected area of leaf area and stem area, and fractal dimension. This work wouldhave the potential of accelerating the evaluation of panicle traits and would be a promisingimpetus for plant phenomics. The work would also be meaningful in revealing thefunction of some key genes of rice and be a powerful tool in enhancing the researches offunctional genomics and crop genetic improvement in our country.
传统的穗部性状测量主要依赖于人工，存在操作繁琐、劳动强度大、测量准确性受人工主观因素影响大等缺点。利用遥感成像和机器视觉等技术实现大面积大田水稻和高通量盆栽水稻测量不依赖手工测量，效率高，应用广。大田水稻穗部性状测量主要利用遥感技术实现大面积水稻的整体产量估测，需要使用专用设备获取遥感数据，不适用于小面积或单株水稻产量的估测，也无法精确估算单株水稻穗部性状参数。针对单株盆栽水稻穂部性状的在体测量技术，经查阅未见相关学术文献发表。此外，现代育种技术能在一天内生产上千个新品种，每一个品种都需要进行穂部性状测量以确定其育种和推广的潜力和价值。在这种背景之下，急需一种快速、简单、有效的穗部性状测量技术，以解决目前穗部性状测量技术的局限性。
本研究基于机器视觉、图像处理、模式识别及数学建模技术，实现单株水稻穗部性状参数包括穗数、穗鲜重、穗干重、总粒数、实粒数、单株产量的在体测量。主要研究内容包括:(1）水稻稻穗区域的提取。研究图像分割与处理算法，从水稻植株图像中提取出稻穗区域，分割算法必须快速有效，以实现快速测量的要求。（2)水稻稻穗区域的识别。经过图像初步处理后提取得到的稻穗区域中，可能存在茎叶等不属于稻穗的区域，需开发合适的识别算法，实现稻穗区域的准确识别。（3）穂部性状在体测量。在稻穗区域的准确提取和识别的基础上，实现水稻穗部性状的在体测量。利用数学建模技术，建立合适的产量相关特征的估测模型。实验结果表明，穗数测量平均误差为0.5，其中95.3%的植株的测量误差在±1以内。5-fold交叉验证结果显示，穗鲜重、穗干重、总粒数、实粒数和单株产量5个回归模型的预测误差分别为7.93%、7.37%、8.59%、7.72%和7.45%。这种方法适用于不同环境下（温室环境下和露天环境下）的水稻产量的在体估测。用后验差检验法对建立的5个回归模型的模型精度验证结果均为二级-合格。
本文所述的水稻穗部性状在体测量方法，克服现有的仪器或研究所存在的问题，不需要将稻穗剪下后脱粒。结合自动化栽培、输送和图像采集平台，可实现盆栽水稻穂部性状的全自动化、高通量测量。主要创新点包括：（1）提出了一种在体、全自动化、高通量测量单株盆栽水稻穂部性状的新方法，解决了穂部性状测量依赖于人工测量的难题。（2）提出了水稻稻穗在体准确提取与识别的图像分析与处理新方法，解决了从水稻植株图像中提取与识别稻穗区域的技术难题，为单株盆栽水稻穂部性状在体测量的实现提供了技术支撑和先决条件。（3）提出了基于稻穗投影面积、茎叶投影面积和分形维数建立水稻产量相关特征包括穗鲜重、穗干重、总粒数、实粒数、单株产量的在体估测数学模型的新分析方法。本研究将提高单株水稻穗部性状参数获取的速度，推动表型组学的发展，对发现并揭示水稻等作物重要基因功能，加强和提升我国在功能基因组及作物遗传改良领域的水平和地位有非常重要的意义。
Rice is one of the world's most important crops. Approximately one half of world'spopulation feed on rice. Yield has always been the key object of most of the rice breedingprograms. Panicle is the reproduction organ of the rice plant where spikelets grow on.Panicle traits, including panicle number, panicle fresh weight, panicle dry weight, totalspikelet number, filled spikelet number, plant yield and so on, directly influence rice yield.In the screening and evaluation of the rice varieties, measuring and evaluating panicletraits is essential.
Traditional measurement of panicle traits mainly depends on manual operation,which is tedious, labor-intensive, subjective and error-prone. Utilizing moderntechnologies such as remote sensing technology and machine vision, it is feasible toautomatically evaluate field rice yield of a large area or pot-grown rice plants, with theadvantage of high efficiency and broad application. Concerning the researches about invivo panicle trait evaluation in the field, remote sensing technology is utilized to predictfield rice yield of a large area, which adopt specialized devices to acquire the spectral data.This technique is not capable of estimating the yield of a small area or individual riceplant. For individual port-grown rice plant trait measurement, academic publishment isunavailable. Meanwhile, modern breeding technologies are able to produce thousands ofnew varieties within a single day, and each variety needs to be measured to evaluate itsvalue and potential for breeding and generalization. Therefore, a fast, simple and effectivetechnique for in vivo rice panicle trait evaluation is urgently needed to withdraw thecurrent limitations.
This research aims to in vivo evaluate rice panicle traits for individual rice plant,including panicle number, panicle fresh weight, panicle dry weight, total spikelet number,filled spikelet number, and plant yield, using machine vision, image processing, patternrecognition and mathematical modelling. The main tasks of this work are:(1) Extractionof panicle regions from the rice plant using image processing algorithms. The algorithmshould be effective and fast so as to achieve high-throughput measurement.(2)Recognition of panicle regions from the rest organs of the plant.(3) Extraction of panicle number and development of mathematical models for estimation of yield-related traits invivo based on separation and recognition of the panicles. The results showed that, meanabsolute error (MAE) for panicle number extraction was0.50and95.3%percent of theplants generated measuring error within±1. Prediction errors evaluated using5-fold crossvalidation were7.93%,7.37%,8.59%,7.72%and7.45%for panicle fresh weight, panicledry weight, total spikelet number, filled spikelet number and plant yield respectively.These models are capable of estimating yield-related traits of rice plants grown in greenhouse and outdoors. Posterior variance test indicated that the precision grade was thesecond grade (up to standard) for all the five regression models.
The method presented in this work is capable of evaluating rice panicle traits in vivofor individual rice plant. This method would overcome the limitations in the currentdevices and researches, with no need of cutting off the panicles and threshing the spikelets.Integrated with automated growth, transportation and inspection platforms, this techniquecan be used for automatic and high-throughput evaluation of panicle traits. The maincontributions includes:(1) This work presents a new method for in vivo, automatic andhigh-throughput measurement of panicle traits for individual pot-grown rice plant.(2) Thiswork illustrates a new image processing pipeline for extraction and recognition of panicleregion from the rest organs of the rice plant.(3) This work proved the new idea ofestimating yield-related traits, including panicle fresh weight, panicle dry weight, totalspikelet number, filled spikelet number and plant yield, based on projected area of panicleregion, projected area of leaf area and stem area, and fractal dimension. This work wouldhave the potential of accelerating the evaluation of panicle traits and would be a promisingimpetus for plant phenomics. The work would also be meaningful in revealing thefunction of some key genes of rice and be a powerful tool in enhancing the researches offunctional genomics and crop genetic improvement in our country.
引文
[1] Tester M, Langridge P. Breeding technologies to increase crop production in achanging world. Science,2010,327(5967):818-822.
[2] http://www.fao.org/worldfoodsituation.
[3] Zhou Y, Zhu J, Li Z, et al. Deletion in a quantitative trait gene qPE9-1associatedwith panicle erectness improves plant architecture during rice domestication.Genetics,2009,183(1):315-324.
[4] Wang E, Wang J, Zhu X, et al. Control of rice grain-filling and yield by a gene witha potential signature of domestication. Nature Genetics,2008,40(11):1370-1374.
[5]平培元.世界水稻供求形势和增产策略.世界农业,2011,5:77-79.
[6]我国水稻供求现状与展望.中国产业经济动态,2012,18:11-18.
[7]农业部长韩长赋:中国人的饭碗不能端在别人手里.黑龙江粮食,2010,6:5-7.
[8]朱德峰,程式华,张玉屏等.全球水稻生产现状与制约因素分析.中国农业科学,2010,43(3):474-479.
[9] Zhang Q. Strategies for developing green super rice. Proceedings of the NationalAcademy of Sciences,2007,104(42):16402-16409.
[10]谷福林,翟虎渠.水稻矮秆性状研究及矮源育种利用.江苏农业学报,2003,19(001):48-54.
[11]袁隆平.超级杂交水稻育种研究新进展.中国农村科技,2010,179(Z1):24-25.
[12] Ren F, Lu B-R, Li S, et al. A comparative study of genetic relationships among theAA-genome Oryza species using RAPD and SSR markers. TAG Theoretical andApplied Genetics,2003,108(1):113-120.
[13]陈浩,林拥军,张启发.转基因水稻研究的回顾与展望.科学通报,2009,54(18):2699-2717.
[14]肖景华,陈浩,张启发.转基因作物将为我国农业发展注入新动力.生命科学,2011,23(2):151-156.
[15] Holtorf H, Guitton M-C, Reski R. Plant functional genomics. Naturwissenschaften,2002,89(6):235-249.
[16] Furbank R T, Tester M. Phenomics–technologies to relieve the phenotypingbottleneck. Trends in Plant Science,2011,16(12):635-644.
[17] Furbank R. Plant phenomics: from gene to form and function. Functional PlantBiology,2009,36(10):5-6.
[18] Cabrera‐Bosquet L, Crossa J, Von Zitzewitz J, et al. High‐throughputphenotyping and genomic selection: The frontiers of crop breeding converge.Journal of Integrative Plant Biology,2012,54(5):312-320.
[19] Fiorani F, Schurr U. Future Scenarios for Plant Phenotyping. Plant Biology,2013,64:17.11-17.25.
[20] Pieruschka R, Poorter H. Phenotyping plants: genes, phenes and machines.Functional Plant Biology,2012,39(11):813-820.
[21] Houle D, Govindaraju D R, Omholt S. Phenomics: the next challenge. NatureReviews Genetics,2010,11(12):855-866.
[22] Ikeda M, Hirose Y, Takashi T, et al. Analysis of rice panicle traits and detection ofQTLs using an image analyzing method. Breeding Science,2010,60(1):55-64.
[23] Xu Z, Chen W, Zhang L, et al. Design principles and parameters of rice ideal panicletype. Chinese Science Bulletin,2005,50(19):2253-2256.
[24] Yoshida S. Fundamentals of rice crop science. International Rice Research Institute,1981.
[25]张声函,雷雪方.水稻穗重对高产育种的效应研究.江西农业大学学报,1995,17(4):386-389.
[26]叶新福,蒋家焕,卢礼斌等.大穗型杂交水稻穗部性状及其影响.中国农学通报,2004,20(6):120-122.
[27]董桂春,居静,于小风等.不同穗重类型常规籼稻品种产量形成的差异研究.扬州大学学报:农业与生命科学版,2010,001:49-54.
[28]于小凤,袁秋梅,王熠等.氮素高效吸收型粳稻品种物质生产与分配的基本特征研究.安徽农业科学,2012,40(12):7015-7020.
[29] Liu T, Mao D, Zhang S, et al. Fine mapping SPP1, a QTL controlling the number ofspikelets per panicle, to a BAC clone in rice (Oryza sativa). TAG Theoretical andApplied Genetics,2009,118(8):1509-1517.
[30] Ando T, Yamamoto T, Shimizu T, et al. Genetic dissection and pyramiding ofquantitative traits for panicle architecture by using chromosomal segmentsubstitution lines in rice. TAG Theoretical and Applied Genetics,2008,116(6):881-890.
[31] Zhang Y, Luo L, Liu T, et al. Four rice QTL controlling number of spikelets perpanicle expressed the characteristics of single Mendelian gene in near isogenicbackgrounds. TAG Theoretical and Applied Genetics,2009,118(6):1035-1044.
[32]欧连耀,赵忠凯,王嘉秀.农业技术员手册.天津:天津科学技术出版社,1980.
[33]刘岩,陆建飞,曹宏鑫等.基于生物量的水稻叶片主要几何属性模型研究.中国农业科学,2009,42(11):4093-4099.
[34] Ying J, Peng S, He Q, et al. Comparison of high-yield rice in tropical andsubtropical environments: I. Determinants of grain and dry matter yields. FieldCrops Research,1998,57(1):71-84.
[35] Yang J, Peng S, Visperas R M, et al. Grain filling pattern and cytokinin content inthe grains and roots of rice plants. Plant Growth Regulation,2000,30(3):261-270.
[36] Tirol-Padre A, Ladha J, Singh U, et al. Grain yield performance of rice genotypes atsuboptimal levels of soil N as affected by N uptake and utilization efficiency. FieldCrops Research,1996,46(1):127-143.
[37] Bueno C S, Lafarge T. Higher crop performance of rice hybrids than of elite inbredsin the tropics:1. Hybrids accumulate more biomass during each phenological phase.Field Crops Research,2009,112(2):229-237.
[38] Berger B, Parent B, Tester M. High-throughput shoot imaging to study droughtresponses. Journal of Experimental Botany,2010,61(13):3519-3528.
[39] Jansen M, Gilmer F, Biskup B, et al. Simultaneous phenotyping of leaf growth andchlorophyll fluorescence via GROWSCREEN FLUORO allows detection of stresstolerance in Arabidopsis thaliana and other rosette plants. Functional Plant Biology,2009,36(11):902-914.
[40] Finkel E. With Phenomics,‘plant scientists hope to shift breeding into overdrive.Science,2009,325(5939):380-381.
[41] Furbank R T, Von Caemmerer S, Sheehy J, et al. C4rice: a challenge for plantphenomics. Functional Plant Biology,2009,36(11):845-856.
[42] Reuzeau C, Frankard V, Hatzfeld Y, et al. Traitmill: a functional genomicsplatform for the phenotypic analysis of cereals. Plant Genetic Resources,2006,4(1):20-24.
[43] Reuzeau C, Pen J, Frankard V, et al. TraitMill: a discovery engine for identifyingyield-enhancement genes in Cereals. Molecular Plant Breeding,2005,3(5):753-759.
[44] Rajendran K, Tester M, Roy S J. Quantifying the three main components of salinitytolerance in cereals. Plant, Cell&Environment,2008,32(3):237-249.
[45] Golzarian M R, Frick R A, Rajendran K, et al. Accurate inference of shoot biomassfrom high-throughput images of cereal plants. Plant Methods,2011,7(1):2.
[46] Liu Z-Y, Wu H-F, Huang J-F. Application of neural networks to discriminate fungalinfection levels in rice panicles using hyperspectral reflectance and principalcomponents analysis. Computers and Electronics in Agriculture,2010,72(2):99-106.
[47] Liu Z-Y, Shi J-J, Zhang L-W, et al. Discrimination of rice panicles by hyperspectralreflectance data based on principal component analysis and support vectorclassification. Journal of Zhejiang University-Science B,2010,11(1):71-78.
[48]龚红菊,姬长英.基于图像处理技术的麦穗产量测量方法.农业机械学报,2007,38(12):116-119.
[49]龚红菊.基于分形理论及图像纹理分析的水稻产量预测方法研究.南京:南京农业大学,2008.
[50]姜盼,张彬,毕昆.基于图像处理的小麦穗长测量.中国传媒大学学报:自然科学版,2011,4:69-73.
[51] Pazoki A, Pazoki Z. Classification system for rain fed wheat grain cultivars usingartificial neural network. African Journal of Biotechnology,2011,10(41):8031-8038.
[52] Chen X, Xun Y, Li W, et al. Combining discriminant analysis and neural networksfor corn variety identification. Computers and Electronics in Agriculture,2010,71:S48-S53.
[53] Wu Y, Pan Y. Cereal grain size measurement based on image processing technology.Intelligent Control and Information Processing (ICICIP),2010InternationalConference on. IEEE,2010:209-212.
[54] Igathinathane C, Pordesimo L, Columbus E P, et al. Sieveless particle sizedistribution analysis of particulate materials through computer vision. Computersand Electronics in Agriculture,2009,66(2):147-158.
[55] Govindaraj P, Vinod K, Arumugachamy S, et al. Analysing genetic control of cookedgrain traits and gelatinization temperature in a double haploid population of rice byquantitative trait loci mapping. Euphytica,2009,166(2):165-176.
[56] Wallays C, Missotten B, De Baerdemaeker J, et al. Hyperspectral wavebandselection for on-line measurement of grain cleanness. Biosystems Engineering,2009,104(1):1-7.
[57] Singh C, Jayas D, Paliwal J, et al. Fungal Damage Detection in Wheat UsingShort-Wave Near-Infrared Hyperspectral and Digital Colour Imaging. InternationalJournal of Food Properties,2012,15(1):11-24.
[58] Huang M, Wan X, Zhang M, et al. Detection of Insect-damaged Vegetable SoybeansUsing Hyperspectral Transmittance Image. Journal of Food Engineering,2012,116(1):45-49.
[59] Singh C B, Jayas D S, Paliwal J, et al. Identification of insect-damaged wheatkernels using short-wave near-infrared hyperspectral and digital colour imaging.Computers and Electronics in Agriculture,2010,73(2):118-125.
[60]张小津，刘顺康. DS型多用数粒仪的研制.电子工程师,1995,02:27-30.
[61]侯加林,米庆华,丁毅.精密种子数粒仪的研制.农机化研究,2000,03:82-84.
[62]宋礽苏,华娇,蓝景针等.转盘斜刮式光电自动数粒仪设计.农业机械学报,2011,42(11):89-93.
[63]王超,任文涛.水稻单株脱粒计数仪的研制.农机化研究,2007,7:98-100.
[64]张云鹤,乔晓军,王成等.种子自动数粒仪.自动化技术与应用,2005,03:62-64.
[65]凌云.基于机器视觉的谷物外观品质检测技术研究.北京:中国农业大学,2004.
[66] Duan L, Yang W, Bi K, et al. Fast discrimination and counting of filled/unfilled ricespikelets based on bi-modal imaging. Computers and Electronics in Agriculture,2011,75(1):196-203.
[67] Duan L, Yang W, Huang C, et al. A novel machine-vision-based facility for theautomatic evaluation of yield-related traits in rice. Plant Methods,2011,7(1):44.
[68]董克强,王智辉.精准农业——未来农业发展的趋势.民营科技,2012,4:145-145.
[69]赵春江.对我国未来精准农业发展的思考.农业网络信息,2010,004:5-8.
[70] Mulyono S, Fanany M I, Basaruddin T. Genetic algorithm based new sequence ofprincipal component regression (GA-NSPCR) for feature selection and yieldprediction using hyperspectral remote sensing data. Geoscience and Remote SensingSymposium (IGARSS),2012IEEE International. IEEE,2012:4198-4201.
[71] Takayama T, Uchida A, Sekine H, et al. Validation of BiPLS for improving yieldestimation of rice paddy from hyperspectral data in West Java, Indonesia.Geoscience and Remote Sensing Symposium (IGARSS),2012IEEE International.IEEE,2012:6581-6584.
[72] Wang Y-P, Chang K-W, Chen R-K, et al. Large-area rice yield forecasting usingsatellite imageries. International Journal of Applied Earth Observation andGeoinformation,2010,12(1):27-35.
[73] Wang P, Sun R, Zhang J, et al. Yield estimation of winter wheat in the North ChinaPlain using the remote-sensing–photosynthesis–yield estimation for crops(RS–P–YEC) model. International Journal of Remote Sensing,2011,32(21):6335-6348.
[74] Tucker C J. Red and photographic infrared linear combinations for monitoringvegetation. Remote Sensing of Environment,1979,8(2):127-150.
[75] Huete A R. A soil-adjusted vegetation index (SAVI). Remote Sensing ofEnvironment,1988,25(3):295-309.
[76] Gitelson A A, Kaufman Y J, Merzlyak M N. Use of a green channel in remotesensing of global vegetation from EOS-MODIS. Remote Sensing of Environment,1996,58(3):289-298.
[77] Lin W-P, Huang J-F, Hu X-M, et al. Crop yield forecast based on MODISTemperature-Vegetation Angel Index. Journal of Infrared and Millimeter Waves,2010,29(6):476-480.
[78]冯美臣,肖璐洁,杨武德等.基于遥感数据和气象数据的水旱地冬小麦产量估测.农业工程学报.2010,26(11):183-188.
[79] Jégo G, Pattey E, Liu J. Using Leaf Area Index, retrieved from optical imagery, inthe STICS crop model for predicting yield and biomass of field crops. Field CropsResearch,2012,131:63-74.
[80] Guo J, Wang Q, Zheng T, et al. Estimation rice yield based on integration remotesensing information and crop model. SPIE Optical Engineering+Applications.International Society for Optics and Photonics,2012:85130F-85130F-10.
[81] Hua‘an J, Jindi W, Yanchen B, et al. Estimation on regional maize yield based onassimilation of remote sensing data and crop growth model. Transactions of theChinese Society of Agricultural Engineering,2012,6:029.
[82] Jin H, Wang J, Bo Y, et al. Data assimilation of MODIS and TM observations intoCERES-Maize model to estimate regional maize yield.SPIE Optical Engineering+Applications. International Society for Optics and Photonics,2010:780908-780908-10.
[83]邢雅娟,刘东升,王鹏新.遥感信息与作物生长模型的耦合应用研究进展.地球科学进展,2009,24(172):444-451.
[84]王航,朱艳,马孟莉等.基于更新和同化策略相结合的遥感信息与水稻生长模型耦合技术的研究.生态学报,2012,32(14):4505-4515.
[85]陈劲松,黄健熙,林珲等.基于遥感信息和作物生长模型同化的水稻估产方法研究.中国科学:信息科学,2010,40(S1):173-183.
[86]龚红菊,於海明,姬长英.基于分形理论的水稻单产计算机视觉预测技术.农业机械学报,2010,41(8):166-170.
[87]吕行军,韩宪忠,陈含等.改进分量法的麦穗图像灰度-二值化处理.河北农业大学学报,2012,35(003):112-116.
[88]吕行军.基于图像处理技术的麦穗识别研究.河北:河北农业大学,2012.
[89] French A, Ubeda-Tomás S, Holman T J, et al. High-throughput quantification of rootgrowth using a novel image-analysis tool. Plant Physiology,2009,150(4):1784-1795.
[90] Yazdanbakhsh N, Fisahn J. High throughput phenotyping of root growth dynamics,lateral root formation, root architecture and root hair development enabled byPlaRoM. Functional Plant Biology,2009,36(11):938-946.
[91] Armengaud P, Zambaux K, Hills A, et al. EZ‐Rhizo: integrated software for thefast and accurate measurement of root system architecture. The Plant Journal,2009,57(5):945-956.
[92] Granier C, Aguirrezabal L, Chenu K, et al. PHENOPSIS, an automated platform forreproducible phenotyping of plant responses to soil water deficit in Arabidopsisthaliana permitted the identification of an accession with low sensitivity to soil waterdeficit. New Phytologist,2005,169(3):623-635.
[93] Walter A, Scharr H, Gilmer F, et al. Dynamics of seedling growth acclimationtowards altered light conditions can be quantified via GROWSCREEN: a setup andprocedure designed for rapid optical phenotyping of different plant species. NewPhytologist,2007,174(2):447-455.
[94] Chaerle L, Lenk S, Leinonen I, et al. Multi‐sensor plant imaging: Towards thedevelopment of a stress‐catalogue. Biotechnology Journal,2009,4(8):1152-1167.
[95] Harbinson J, Prinzenberg A E, Kruijer W, et al. High throughput screening withchlorophyll fluorescence imaging and its use in crop improvement. Current Opinionin Biotechnology,2012,23(2):221-226.
[96] Munns R, James R A, Sirault X R, et al. New phenotyping methods for screeningwheat and barley for beneficial responses to water deficit. Journal of ExperimentalBotany,2010,61(13):3499-3507.
[97] Jones H G, Serraj R, Loveys B R, et al. Thermal infrared imaging of crop canopiesfor the remote diagnosis and quantification of plant responses to water stress in thefield. Functional Plant Biology,2009,36(11):978-989.
[98] Seelig H D, Hoehn A, Stodieck L, et al. The assessment of leaf water content usingleaf reflectance ratios in the visible, near‐, and short‐wave‐infrared.International Journal of Remote Sensing,2008,29(13):3701-3713.
[99] Bock C, Poole G, Parker P, et al. Plant disease severity estimated visually, by digitalphotography and image analysis, and by hyperspectral imaging. Critical Reviews inPlant Sciences,2010,29(2):59-107.
[100] Ustin S L, Gamon J A. Remote sensing of plant functional types. New Phytologist,2010,186(4):795-816.
[101] Yang W, Xu X, Duan L, et al. High-throughput measurement of rice tillers using aconveyor equipped with x-ray computed tomography. Review of ScientificInstruments,2011,82(2):025102-025107.
[102] Ma T, Du F, Fang C. Sensors State Monitoring based on LabVIEW and WirelessNodes. Procedia Engineering,2011,15:2639-2643.
[103] Hu L, Zuwei T, Hongwei D. Image processing of robotic vision sensing based onLabVIEW. Experimental Technology and Management,2012,7:025.
[104] Giannone L, Cerna M, Cole R, et al. Data acquisition and real-time signalprocessing of plasma diagnostics on ASDEX Upgrade using LabVIEW RT. FusionEngineering and Design,2010,85(3):303-307.
[105] Ohta Y-I, Kanade T, Sakai T. Color information for region segmentation. ComputerGraphics and Image Processing,1980,13(3):222-241.
[106] Philipp I, Rath T. Improving plant discrimination in image processing by use ofdifferent colour space transformations. Computers and Electronics in Agriculture,2002,35(1):1-15.
[107] Gonzalez R C, Woods R E. Digital image processing. Prentice Hall New Jersey.2002.
[108] Benalcázar M, Padín J, Brun M, et al. Measuring leaf area in soy plants by HSIcolor model filtering and mathematical morphology. Journal of Physics: ConferenceSeries. IOP Publishing,2011,332(1):012034.
[109] Guijarro M, Pajares G, Riomoros I, et al. Automatic segmentation of relevanttextures in agricultural images. Computers and Electronics in Agriculture,2011,75(1):75-83.
[110] Otsu N. A threshold selection method from gray-level histograms. Automatica,1975,11(285-296):23-27.
[111] Muthukannan K, Moses M M. Color image segmentation using k-means clusteringand Optimal Fuzzy C-Means clustering. Communication and ComputationalIntelligence (INCOCCI),2010International Conference on. IEEE,2010:229-234.
[112] Kim J S, Hong K S. Color–texture segmentation using unsupervised graph cuts.Pattern Recognition,2009,42(5):735-750.
[113] Wang C, Wang E, Xu J, et al. Bayesian discriminant analysis for prediction of coaland gas outbursts and applicatio. Mining Science and Technology,2010,20(4):520-523.
[114] Okamoto H, Lee W S. Green citrus detection using hyperspectral imaging.Computers and electronics in agriculture,2009,66(2):201-208.
[115] Canny J. A computational approach to edge detection. Pattern Analysis and MachineIntelligence, IEEE Transactions on,1986,6:679-698.
[116] Haralick R M. Statistical and structural approaches to texture. Proceedings of theIEEE,1979,67(5):786-804.
[117] Kira K, Rendell L A. A practical approach to feature selection. Proceedings of theninth international workshop on Machine learning. Morgan Kaufmann PublishersInc.,1992:249-256.
[118] Kononenko I. Estimating attributes: analysis and extensions of RELIEF. MachineLearning: ECML-94. Springer Berlin Heidelberg,1994:171-182.
[119] Mclachlan G J. Discriminant analysis and statistical pattern recognition.Wiley-Interscience,2004.
[120]任志娟. SPSS中判别分析方法的正确使用.统计与决策,2006,2:157.
[121]谢宇.回归分析.社会科学文献出版社,2010.
[122] Mckay R, Campbell N. Variable selection techniques in discriminant analysis: II.Allocation. British Journal of Mathematical and Statistical Psychology,2011,35(1):30-41.
[123] Mckay R, Campbell N. Variable selection techniques in discriminant analysis: I.Description. British Journal of Mathematical and Statistical Psychology,2011,35(1):1-29.
[124] Guyon I, Elisseeff A. An introduction to variable and feature selection. The Journalof Machine Learning Research,2003,3:1157-1182.
[125] Kulatilake P, Qiong W, Hudaverdi T, et al. Mean particle size prediction in rock blastfragmentation using neural networks. Engineering Geology,2010,114(3):298-311.
[126] Goyal S. Artificial Neural Networks for Dairy Industry: A Review. Journal ofAdvanced Computer Science&Technology,2012,1(3):101-115.
[127] Babaei S, Geranmayeh A. Heart sound reproduction based on neural networkclassification of cardiac valve disorders using wavelet transforms of PCG signals.Computers in Biology and Medicine,2009,39(1):8-15.
[128]朱华,姬翠翠.分形理论及其应用.科学出版社,2011.
[129]嵇晓雷.分形理论应用于植物根系形态分布的研究进展及其应用前景.安徽农业科学,2010,025:13693-13694.
[130] Machado B B, Casanova D, Gon alves W N, et al. Partial differential equationsand fractal analysis to plant leaf identification. Journal of Physics: Conference Series.IOP Publishing,2013,410(1):012066.
[131] Du J-X, Zhai C-M, Wang Q-P. Recognition of leaf image based on outline and veinfractal dimension feature. Advanced Intelligent Computing,2012,364-369.
[132] Wu L, Wen Y, Deng X, et al. Identification of weed/corn using BP network based onwavelet features and fractal dimension. Scientific research and essay,2009,4(11):1194-1200.
[133] Backes A R, Junior J J M S, Kolb R M, et al. Plant species identification usingmulti-scale fractal dimension applied to images of adaxial surface epidermis.Computer Analysis Of Images And Patterns. Springer Berlin Heidelberg,2009:680-688.
[134]刘桃菊,唐建军,戚昌瀚.水稻形态的分形特征及其可视化模拟研究.江西农业大学学报(自然科学版),2002,24(5):583-586.
[135] Tél T, Fül p, Vicsek T. Determination of fractal dimensions for geometricalmultifractals. Physica A: Statistical Mechanics and its Applications,1989,159(2):155-166.
[136]朱大奇,史慧.人工神经网络原理及应用.科学出版社,2006.
[137]葛哲学,孙志强.神经网络理论与MATLABR2007实现.北京:电子工业出版社,2007.
[138] Granitto P M, Navone H D, Verdes P F, et al. Weed seeds identification by machinevision. Computers and Electronics in Agriculture,2002,33(2):91-103.
[139] Khazaei J, Naghavi M, Jahansouz M, et al. Yield estimation and clustering ofchickpea genotypes using soft computing techniques. Agronomy Journal,2008,100(4):1077-1087.
[140] Meyer G E, Neto J C. Verification of color vegetation indices for automated cropimaging applications. Computers and Electronics in Agriculture,2008,63(2):282-293.
[141] Akaike H. A new look at the statistical model identification. Automatic Control,IEEE Transactions on,1974,19(6):716-723.
[142] Montgomery D C, Peck E A, Vining G G. Introduction to linear regression analysis.Wiley,2012.
[143] Sarkar N, Chaudhuri B. An efficient differential box-counting approach to computefractal dimension of image. Systems, Man and Cybernetics, IEEE Transactions on,1994,24(1):115-120.
[144] Dong M, Wang N. Adaptive network-based fuzzy inference system withleave-one-out cross-validation approach for prediction of surface roughness. AppliedMathematical Modelling,2011,35(3):1024-1035.
[145]李红霞,赵新华,迟海燕等.基于改进BP神经网络模型的地面沉降预测及分析.天津大学学报.2009,42(1):60-64.
[2] http://www.fao.org/worldfoodsituation.
[3] Zhou Y, Zhu J, Li Z, et al. Deletion in a quantitative trait gene qPE9-1associatedwith panicle erectness improves plant architecture during rice domestication.Genetics,2009,183(1):315-324.
[4] Wang E, Wang J, Zhu X, et al. Control of rice grain-filling and yield by a gene witha potential signature of domestication. Nature Genetics,2008,40(11):1370-1374.
[5]平培元.世界水稻供求形势和增产策略.世界农业,2011,5:77-79.
[6]我国水稻供求现状与展望.中国产业经济动态,2012,18:11-18.
[7]农业部长韩长赋:中国人的饭碗不能端在别人手里.黑龙江粮食,2010,6:5-7.
[8]朱德峰,程式华,张玉屏等.全球水稻生产现状与制约因素分析.中国农业科学,2010,43(3):474-479.
[9] Zhang Q. Strategies for developing green super rice. Proceedings of the NationalAcademy of Sciences,2007,104(42):16402-16409.
[10]谷福林,翟虎渠.水稻矮秆性状研究及矮源育种利用.江苏农业学报,2003,19(001):48-54.
[11]袁隆平.超级杂交水稻育种研究新进展.中国农村科技,2010,179(Z1):24-25.
[12] Ren F, Lu B-R, Li S, et al. A comparative study of genetic relationships among theAA-genome Oryza species using RAPD and SSR markers. TAG Theoretical andApplied Genetics,2003,108(1):113-120.
[13]陈浩,林拥军,张启发.转基因水稻研究的回顾与展望.科学通报,2009,54(18):2699-2717.
[14]肖景华,陈浩,张启发.转基因作物将为我国农业发展注入新动力.生命科学,2011,23(2):151-156.
[15] Holtorf H, Guitton M-C, Reski R. Plant functional genomics. Naturwissenschaften,2002,89(6):235-249.
[16] Furbank R T, Tester M. Phenomics–technologies to relieve the phenotypingbottleneck. Trends in Plant Science,2011,16(12):635-644.
[17] Furbank R. Plant phenomics: from gene to form and function. Functional PlantBiology,2009,36(10):5-6.
[18] Cabrera‐Bosquet L, Crossa J, Von Zitzewitz J, et al. High‐throughputphenotyping and genomic selection: The frontiers of crop breeding converge.Journal of Integrative Plant Biology,2012,54(5):312-320.
[19] Fiorani F, Schurr U. Future Scenarios for Plant Phenotyping. Plant Biology,2013,64:17.11-17.25.
[20] Pieruschka R, Poorter H. Phenotyping plants: genes, phenes and machines.Functional Plant Biology,2012,39(11):813-820.
[21] Houle D, Govindaraju D R, Omholt S. Phenomics: the next challenge. NatureReviews Genetics,2010,11(12):855-866.
[22] Ikeda M, Hirose Y, Takashi T, et al. Analysis of rice panicle traits and detection ofQTLs using an image analyzing method. Breeding Science,2010,60(1):55-64.
[23] Xu Z, Chen W, Zhang L, et al. Design principles and parameters of rice ideal panicletype. Chinese Science Bulletin,2005,50(19):2253-2256.
[24] Yoshida S. Fundamentals of rice crop science. International Rice Research Institute,1981.
[25]张声函,雷雪方.水稻穗重对高产育种的效应研究.江西农业大学学报,1995,17(4):386-389.
[26]叶新福,蒋家焕,卢礼斌等.大穗型杂交水稻穗部性状及其影响.中国农学通报,2004,20(6):120-122.
[27]董桂春,居静,于小风等.不同穗重类型常规籼稻品种产量形成的差异研究.扬州大学学报:农业与生命科学版,2010,001:49-54.
[28]于小凤,袁秋梅,王熠等.氮素高效吸收型粳稻品种物质生产与分配的基本特征研究.安徽农业科学,2012,40(12):7015-7020.
[29] Liu T, Mao D, Zhang S, et al. Fine mapping SPP1, a QTL controlling the number ofspikelets per panicle, to a BAC clone in rice (Oryza sativa). TAG Theoretical andApplied Genetics,2009,118(8):1509-1517.
[30] Ando T, Yamamoto T, Shimizu T, et al. Genetic dissection and pyramiding ofquantitative traits for panicle architecture by using chromosomal segmentsubstitution lines in rice. TAG Theoretical and Applied Genetics,2008,116(6):881-890.
[31] Zhang Y, Luo L, Liu T, et al. Four rice QTL controlling number of spikelets perpanicle expressed the characteristics of single Mendelian gene in near isogenicbackgrounds. TAG Theoretical and Applied Genetics,2009,118(6):1035-1044.
[32]欧连耀,赵忠凯,王嘉秀.农业技术员手册.天津:天津科学技术出版社,1980.
[33]刘岩,陆建飞,曹宏鑫等.基于生物量的水稻叶片主要几何属性模型研究.中国农业科学,2009,42(11):4093-4099.
[34] Ying J, Peng S, He Q, et al. Comparison of high-yield rice in tropical andsubtropical environments: I. Determinants of grain and dry matter yields. FieldCrops Research,1998,57(1):71-84.
[35] Yang J, Peng S, Visperas R M, et al. Grain filling pattern and cytokinin content inthe grains and roots of rice plants. Plant Growth Regulation,2000,30(3):261-270.
[36] Tirol-Padre A, Ladha J, Singh U, et al. Grain yield performance of rice genotypes atsuboptimal levels of soil N as affected by N uptake and utilization efficiency. FieldCrops Research,1996,46(1):127-143.
[37] Bueno C S, Lafarge T. Higher crop performance of rice hybrids than of elite inbredsin the tropics:1. Hybrids accumulate more biomass during each phenological phase.Field Crops Research,2009,112(2):229-237.
[38] Berger B, Parent B, Tester M. High-throughput shoot imaging to study droughtresponses. Journal of Experimental Botany,2010,61(13):3519-3528.
[39] Jansen M, Gilmer F, Biskup B, et al. Simultaneous phenotyping of leaf growth andchlorophyll fluorescence via GROWSCREEN FLUORO allows detection of stresstolerance in Arabidopsis thaliana and other rosette plants. Functional Plant Biology,2009,36(11):902-914.
[40] Finkel E. With Phenomics,‘plant scientists hope to shift breeding into overdrive.Science,2009,325(5939):380-381.
[41] Furbank R T, Von Caemmerer S, Sheehy J, et al. C4rice: a challenge for plantphenomics. Functional Plant Biology,2009,36(11):845-856.
[42] Reuzeau C, Frankard V, Hatzfeld Y, et al. Traitmill: a functional genomicsplatform for the phenotypic analysis of cereals. Plant Genetic Resources,2006,4(1):20-24.
[43] Reuzeau C, Pen J, Frankard V, et al. TraitMill: a discovery engine for identifyingyield-enhancement genes in Cereals. Molecular Plant Breeding,2005,3(5):753-759.
[44] Rajendran K, Tester M, Roy S J. Quantifying the three main components of salinitytolerance in cereals. Plant, Cell&Environment,2008,32(3):237-249.
[45] Golzarian M R, Frick R A, Rajendran K, et al. Accurate inference of shoot biomassfrom high-throughput images of cereal plants. Plant Methods,2011,7(1):2.
[46] Liu Z-Y, Wu H-F, Huang J-F. Application of neural networks to discriminate fungalinfection levels in rice panicles using hyperspectral reflectance and principalcomponents analysis. Computers and Electronics in Agriculture,2010,72(2):99-106.
[47] Liu Z-Y, Shi J-J, Zhang L-W, et al. Discrimination of rice panicles by hyperspectralreflectance data based on principal component analysis and support vectorclassification. Journal of Zhejiang University-Science B,2010,11(1):71-78.
[48]龚红菊,姬长英.基于图像处理技术的麦穗产量测量方法.农业机械学报,2007,38(12):116-119.
[49]龚红菊.基于分形理论及图像纹理分析的水稻产量预测方法研究.南京:南京农业大学,2008.
[50]姜盼,张彬,毕昆.基于图像处理的小麦穗长测量.中国传媒大学学报:自然科学版,2011,4:69-73.
[51] Pazoki A, Pazoki Z. Classification system for rain fed wheat grain cultivars usingartificial neural network. African Journal of Biotechnology,2011,10(41):8031-8038.
[52] Chen X, Xun Y, Li W, et al. Combining discriminant analysis and neural networksfor corn variety identification. Computers and Electronics in Agriculture,2010,71:S48-S53.
[53] Wu Y, Pan Y. Cereal grain size measurement based on image processing technology.Intelligent Control and Information Processing (ICICIP),2010InternationalConference on. IEEE,2010:209-212.
[54] Igathinathane C, Pordesimo L, Columbus E P, et al. Sieveless particle sizedistribution analysis of particulate materials through computer vision. Computersand Electronics in Agriculture,2009,66(2):147-158.
[55] Govindaraj P, Vinod K, Arumugachamy S, et al. Analysing genetic control of cookedgrain traits and gelatinization temperature in a double haploid population of rice byquantitative trait loci mapping. Euphytica,2009,166(2):165-176.
[56] Wallays C, Missotten B, De Baerdemaeker J, et al. Hyperspectral wavebandselection for on-line measurement of grain cleanness. Biosystems Engineering,2009,104(1):1-7.
[57] Singh C, Jayas D, Paliwal J, et al. Fungal Damage Detection in Wheat UsingShort-Wave Near-Infrared Hyperspectral and Digital Colour Imaging. InternationalJournal of Food Properties,2012,15(1):11-24.
[58] Huang M, Wan X, Zhang M, et al. Detection of Insect-damaged Vegetable SoybeansUsing Hyperspectral Transmittance Image. Journal of Food Engineering,2012,116(1):45-49.
[59] Singh C B, Jayas D S, Paliwal J, et al. Identification of insect-damaged wheatkernels using short-wave near-infrared hyperspectral and digital colour imaging.Computers and Electronics in Agriculture,2010,73(2):118-125.
[60]张小津，刘顺康. DS型多用数粒仪的研制.电子工程师,1995,02:27-30.
[61]侯加林,米庆华,丁毅.精密种子数粒仪的研制.农机化研究,2000,03:82-84.
[62]宋礽苏,华娇,蓝景针等.转盘斜刮式光电自动数粒仪设计.农业机械学报,2011,42(11):89-93.
[63]王超,任文涛.水稻单株脱粒计数仪的研制.农机化研究,2007,7:98-100.
[64]张云鹤,乔晓军,王成等.种子自动数粒仪.自动化技术与应用,2005,03:62-64.
[65]凌云.基于机器视觉的谷物外观品质检测技术研究.北京:中国农业大学,2004.
[66] Duan L, Yang W, Bi K, et al. Fast discrimination and counting of filled/unfilled ricespikelets based on bi-modal imaging. Computers and Electronics in Agriculture,2011,75(1):196-203.
[67] Duan L, Yang W, Huang C, et al. A novel machine-vision-based facility for theautomatic evaluation of yield-related traits in rice. Plant Methods,2011,7(1):44.
[68]董克强,王智辉.精准农业——未来农业发展的趋势.民营科技,2012,4:145-145.
[69]赵春江.对我国未来精准农业发展的思考.农业网络信息,2010,004:5-8.
[70] Mulyono S, Fanany M I, Basaruddin T. Genetic algorithm based new sequence ofprincipal component regression (GA-NSPCR) for feature selection and yieldprediction using hyperspectral remote sensing data. Geoscience and Remote SensingSymposium (IGARSS),2012IEEE International. IEEE,2012:4198-4201.
[71] Takayama T, Uchida A, Sekine H, et al. Validation of BiPLS for improving yieldestimation of rice paddy from hyperspectral data in West Java, Indonesia.Geoscience and Remote Sensing Symposium (IGARSS),2012IEEE International.IEEE,2012:6581-6584.
[72] Wang Y-P, Chang K-W, Chen R-K, et al. Large-area rice yield forecasting usingsatellite imageries. International Journal of Applied Earth Observation andGeoinformation,2010,12(1):27-35.
[73] Wang P, Sun R, Zhang J, et al. Yield estimation of winter wheat in the North ChinaPlain using the remote-sensing–photosynthesis–yield estimation for crops(RS–P–YEC) model. International Journal of Remote Sensing,2011,32(21):6335-6348.
[74] Tucker C J. Red and photographic infrared linear combinations for monitoringvegetation. Remote Sensing of Environment,1979,8(2):127-150.
[75] Huete A R. A soil-adjusted vegetation index (SAVI). Remote Sensing ofEnvironment,1988,25(3):295-309.
[76] Gitelson A A, Kaufman Y J, Merzlyak M N. Use of a green channel in remotesensing of global vegetation from EOS-MODIS. Remote Sensing of Environment,1996,58(3):289-298.
[77] Lin W-P, Huang J-F, Hu X-M, et al. Crop yield forecast based on MODISTemperature-Vegetation Angel Index. Journal of Infrared and Millimeter Waves,2010,29(6):476-480.
[78]冯美臣,肖璐洁,杨武德等.基于遥感数据和气象数据的水旱地冬小麦产量估测.农业工程学报.2010,26(11):183-188.
[79] Jégo G, Pattey E, Liu J. Using Leaf Area Index, retrieved from optical imagery, inthe STICS crop model for predicting yield and biomass of field crops. Field CropsResearch,2012,131:63-74.
[80] Guo J, Wang Q, Zheng T, et al. Estimation rice yield based on integration remotesensing information and crop model. SPIE Optical Engineering+Applications.International Society for Optics and Photonics,2012:85130F-85130F-10.
[81] Hua‘an J, Jindi W, Yanchen B, et al. Estimation on regional maize yield based onassimilation of remote sensing data and crop growth model. Transactions of theChinese Society of Agricultural Engineering,2012,6:029.
[82] Jin H, Wang J, Bo Y, et al. Data assimilation of MODIS and TM observations intoCERES-Maize model to estimate regional maize yield.SPIE Optical Engineering+Applications. International Society for Optics and Photonics,2010:780908-780908-10.
[83]邢雅娟,刘东升,王鹏新.遥感信息与作物生长模型的耦合应用研究进展.地球科学进展,2009,24(172):444-451.
[84]王航,朱艳,马孟莉等.基于更新和同化策略相结合的遥感信息与水稻生长模型耦合技术的研究.生态学报,2012,32(14):4505-4515.
[85]陈劲松,黄健熙,林珲等.基于遥感信息和作物生长模型同化的水稻估产方法研究.中国科学:信息科学,2010,40(S1):173-183.
[86]龚红菊,於海明,姬长英.基于分形理论的水稻单产计算机视觉预测技术.农业机械学报,2010,41(8):166-170.
[87]吕行军,韩宪忠,陈含等.改进分量法的麦穗图像灰度-二值化处理.河北农业大学学报,2012,35(003):112-116.
[88]吕行军.基于图像处理技术的麦穗识别研究.河北:河北农业大学,2012.
[89] French A, Ubeda-Tomás S, Holman T J, et al. High-throughput quantification of rootgrowth using a novel image-analysis tool. Plant Physiology,2009,150(4):1784-1795.
[90] Yazdanbakhsh N, Fisahn J. High throughput phenotyping of root growth dynamics,lateral root formation, root architecture and root hair development enabled byPlaRoM. Functional Plant Biology,2009,36(11):938-946.
[91] Armengaud P, Zambaux K, Hills A, et al. EZ‐Rhizo: integrated software for thefast and accurate measurement of root system architecture. The Plant Journal,2009,57(5):945-956.
[92] Granier C, Aguirrezabal L, Chenu K, et al. PHENOPSIS, an automated platform forreproducible phenotyping of plant responses to soil water deficit in Arabidopsisthaliana permitted the identification of an accession with low sensitivity to soil waterdeficit. New Phytologist,2005,169(3):623-635.
[93] Walter A, Scharr H, Gilmer F, et al. Dynamics of seedling growth acclimationtowards altered light conditions can be quantified via GROWSCREEN: a setup andprocedure designed for rapid optical phenotyping of different plant species. NewPhytologist,2007,174(2):447-455.
[94] Chaerle L, Lenk S, Leinonen I, et al. Multi‐sensor plant imaging: Towards thedevelopment of a stress‐catalogue. Biotechnology Journal,2009,4(8):1152-1167.
[95] Harbinson J, Prinzenberg A E, Kruijer W, et al. High throughput screening withchlorophyll fluorescence imaging and its use in crop improvement. Current Opinionin Biotechnology,2012,23(2):221-226.
[96] Munns R, James R A, Sirault X R, et al. New phenotyping methods for screeningwheat and barley for beneficial responses to water deficit. Journal of ExperimentalBotany,2010,61(13):3499-3507.
[97] Jones H G, Serraj R, Loveys B R, et al. Thermal infrared imaging of crop canopiesfor the remote diagnosis and quantification of plant responses to water stress in thefield. Functional Plant Biology,2009,36(11):978-989.
[98] Seelig H D, Hoehn A, Stodieck L, et al. The assessment of leaf water content usingleaf reflectance ratios in the visible, near‐, and short‐wave‐infrared.International Journal of Remote Sensing,2008,29(13):3701-3713.
[99] Bock C, Poole G, Parker P, et al. Plant disease severity estimated visually, by digitalphotography and image analysis, and by hyperspectral imaging. Critical Reviews inPlant Sciences,2010,29(2):59-107.
[100] Ustin S L, Gamon J A. Remote sensing of plant functional types. New Phytologist,2010,186(4):795-816.
[101] Yang W, Xu X, Duan L, et al. High-throughput measurement of rice tillers using aconveyor equipped with x-ray computed tomography. Review of ScientificInstruments,2011,82(2):025102-025107.
[102] Ma T, Du F, Fang C. Sensors State Monitoring based on LabVIEW and WirelessNodes. Procedia Engineering,2011,15:2639-2643.
[103] Hu L, Zuwei T, Hongwei D. Image processing of robotic vision sensing based onLabVIEW. Experimental Technology and Management,2012,7:025.
[104] Giannone L, Cerna M, Cole R, et al. Data acquisition and real-time signalprocessing of plasma diagnostics on ASDEX Upgrade using LabVIEW RT. FusionEngineering and Design,2010,85(3):303-307.
[105] Ohta Y-I, Kanade T, Sakai T. Color information for region segmentation. ComputerGraphics and Image Processing,1980,13(3):222-241.
[106] Philipp I, Rath T. Improving plant discrimination in image processing by use ofdifferent colour space transformations. Computers and Electronics in Agriculture,2002,35(1):1-15.
[107] Gonzalez R C, Woods R E. Digital image processing. Prentice Hall New Jersey.2002.
[108] Benalcázar M, Padín J, Brun M, et al. Measuring leaf area in soy plants by HSIcolor model filtering and mathematical morphology. Journal of Physics: ConferenceSeries. IOP Publishing,2011,332(1):012034.
[109] Guijarro M, Pajares G, Riomoros I, et al. Automatic segmentation of relevanttextures in agricultural images. Computers and Electronics in Agriculture,2011,75(1):75-83.
[110] Otsu N. A threshold selection method from gray-level histograms. Automatica,1975,11(285-296):23-27.
[111] Muthukannan K, Moses M M. Color image segmentation using k-means clusteringand Optimal Fuzzy C-Means clustering. Communication and ComputationalIntelligence (INCOCCI),2010International Conference on. IEEE,2010:229-234.
[112] Kim J S, Hong K S. Color–texture segmentation using unsupervised graph cuts.Pattern Recognition,2009,42(5):735-750.
[113] Wang C, Wang E, Xu J, et al. Bayesian discriminant analysis for prediction of coaland gas outbursts and applicatio. Mining Science and Technology,2010,20(4):520-523.
[114] Okamoto H, Lee W S. Green citrus detection using hyperspectral imaging.Computers and electronics in agriculture,2009,66(2):201-208.
[115] Canny J. A computational approach to edge detection. Pattern Analysis and MachineIntelligence, IEEE Transactions on,1986,6:679-698.
[116] Haralick R M. Statistical and structural approaches to texture. Proceedings of theIEEE,1979,67(5):786-804.
[117] Kira K, Rendell L A. A practical approach to feature selection. Proceedings of theninth international workshop on Machine learning. Morgan Kaufmann PublishersInc.,1992:249-256.
[118] Kononenko I. Estimating attributes: analysis and extensions of RELIEF. MachineLearning: ECML-94. Springer Berlin Heidelberg,1994:171-182.
[119] Mclachlan G J. Discriminant analysis and statistical pattern recognition.Wiley-Interscience,2004.
[120]任志娟. SPSS中判别分析方法的正确使用.统计与决策,2006,2:157.
[121]谢宇.回归分析.社会科学文献出版社,2010.
[122] Mckay R, Campbell N. Variable selection techniques in discriminant analysis: II.Allocation. British Journal of Mathematical and Statistical Psychology,2011,35(1):30-41.
[123] Mckay R, Campbell N. Variable selection techniques in discriminant analysis: I.Description. British Journal of Mathematical and Statistical Psychology,2011,35(1):1-29.
[124] Guyon I, Elisseeff A. An introduction to variable and feature selection. The Journalof Machine Learning Research,2003,3:1157-1182.
[125] Kulatilake P, Qiong W, Hudaverdi T, et al. Mean particle size prediction in rock blastfragmentation using neural networks. Engineering Geology,2010,114(3):298-311.
[126] Goyal S. Artificial Neural Networks for Dairy Industry: A Review. Journal ofAdvanced Computer Science&Technology,2012,1(3):101-115.
[127] Babaei S, Geranmayeh A. Heart sound reproduction based on neural networkclassification of cardiac valve disorders using wavelet transforms of PCG signals.Computers in Biology and Medicine,2009,39(1):8-15.
[128]朱华,姬翠翠.分形理论及其应用.科学出版社,2011.
[129]嵇晓雷.分形理论应用于植物根系形态分布的研究进展及其应用前景.安徽农业科学,2010,025:13693-13694.
[130] Machado B B, Casanova D, Gon alves W N, et al. Partial differential equationsand fractal analysis to plant leaf identification. Journal of Physics: Conference Series.IOP Publishing,2013,410(1):012066.
[131] Du J-X, Zhai C-M, Wang Q-P. Recognition of leaf image based on outline and veinfractal dimension feature. Advanced Intelligent Computing,2012,364-369.
[132] Wu L, Wen Y, Deng X, et al. Identification of weed/corn using BP network based onwavelet features and fractal dimension. Scientific research and essay,2009,4(11):1194-1200.
[133] Backes A R, Junior J J M S, Kolb R M, et al. Plant species identification usingmulti-scale fractal dimension applied to images of adaxial surface epidermis.Computer Analysis Of Images And Patterns. Springer Berlin Heidelberg,2009:680-688.
[134]刘桃菊,唐建军,戚昌瀚.水稻形态的分形特征及其可视化模拟研究.江西农业大学学报(自然科学版),2002,24(5):583-586.
[135] Tél T, Fül p, Vicsek T. Determination of fractal dimensions for geometricalmultifractals. Physica A: Statistical Mechanics and its Applications,1989,159(2):155-166.
[136]朱大奇,史慧.人工神经网络原理及应用.科学出版社,2006.
[137]葛哲学,孙志强.神经网络理论与MATLABR2007实现.北京:电子工业出版社,2007.
[138] Granitto P M, Navone H D, Verdes P F, et al. Weed seeds identification by machinevision. Computers and Electronics in Agriculture,2002,33(2):91-103.
[139] Khazaei J, Naghavi M, Jahansouz M, et al. Yield estimation and clustering ofchickpea genotypes using soft computing techniques. Agronomy Journal,2008,100(4):1077-1087.
[140] Meyer G E, Neto J C. Verification of color vegetation indices for automated cropimaging applications. Computers and Electronics in Agriculture,2008,63(2):282-293.
[141] Akaike H. A new look at the statistical model identification. Automatic Control,IEEE Transactions on,1974,19(6):716-723.
[142] Montgomery D C, Peck E A, Vining G G. Introduction to linear regression analysis.Wiley,2012.
[143] Sarkar N, Chaudhuri B. An efficient differential box-counting approach to computefractal dimension of image. Systems, Man and Cybernetics, IEEE Transactions on,1994,24(1):115-120.
[144] Dong M, Wang N. Adaptive network-based fuzzy inference system withleave-one-out cross-validation approach for prediction of surface roughness. AppliedMathematical Modelling,2011,35(3):1024-1035.
[145]李红霞,赵新华,迟海燕等.基于改进BP神经网络模型的地面沉降预测及分析.天津大学学报.2009,42(1):60-64.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |