基于高光谱成像技术的油菜信息获取研究
|
摘要
精细农业是基于信息和知识支持的现代农业,不仅能合理利用农业资源、提高农作物产量和品质、降低生产成本、减少污染、改善生态环境进而实现农业的可持续发展；而且对促进农业现代化,发展大农业体系和带动相关产业的发展具有显著的作用.其本质是一种以知识和信息为基础的农业管理系统。快速有效地采集和描述作物生长信息是精细农业实践的重要基础。
针对国内外现状,本论文以油菜为研究对象,采用高光谱图像技术确定了油菜籽的特征波段,并用于鉴别不同品种的油菜籽品种研究了油菜叶片高光谱反射率与油菜叶绿素含量(SPAD值)的关系；还研究了不同生长时期不同油菜品种的鉴别方法。本论文的主要研究结论如下：
(1)采用高光谱图像技术对不同品种的油菜籽进行鉴别分析。通过对高光谱数据进行主成分分析,实现了高光谱数据的降维,并找出油菜籽的3个特征波长,采用基于灰度统计矩阵和灰度直方图的纹理特征提取方法,提取了油菜籽的10个纹理参数。研究了基于BP神经网络的油菜籽品种鉴别模型,模型训练时判别率为93.75%,预测时判别率为91.67%。
(2)研究了油菜叶片反射率与油菜叶绿素含量的关系,建立了油菜叶绿素含量的定量分析模型。根据特征波长结合神经网络建立了油菜叶片SPAD值预测模型,结果表明,模型判别的相关系数为0.9237,预测相关系数为0.9526。
(3)对不同生长时期不同油菜品种的鉴别分析,分别找出油菜叶片的特征波长,得到了油菜叶片的特征波段为544-565、674-693和708-723nm,并利用特征波段建立油菜叶片鉴别模型,获得了较好的结果。
(4)研究了高光谱图像信息提取方法：高光谱图像数据处理方法,并结合BP神经网络建立了相应的定量分析模型。说明应用高光谱图像技术对油菜信息进行快速、无损、准确地获取是可行的。
Precision agriculture is modern agriculture which is based on information and knowledge,it can not only utilizate agricultural resources reasonably,increase crop yield and quality,reduce cost and improve the ecological environment,and then realize the sustainable development of agriculture, but also have a significant effect of promoting agricultural modernization the development of industries related to agriculture system.Quick and effective collection and describe crop growth information is an important basis of precision agriculture practice.
According to the situation at home and abroad, this paper choose the Rape as the research object,uses hyperspectral imaging technology to determine the characteristic bands,and then to identify different kinds of rapeseed varieties.we studied the relationships of hyperspectral reflectance of rape leaves and chlorophyll content (the SPAD value).we also research how to identify different rapeseed varieties in different growth periods.This paper mainly studies the conclusion is as follows:
(1)Applying hyperspectral image technology to identify different rapeseed varieties.Through principal component analysis of the hyperspectral data,it realized dimensionality reduction,and three characteristic bands were found out.The texture parameters were extracted from the optimal bands images based on gray level histogram and gray level co-occurrence matrix (GLCM) statistical methods. Artificial neural network model was used for the identification of varieties of rapeseed. Detection results of ANN model showed that calibration and prediction sets of rapeseed varieties were 93.75% and 91.67%, respectively.
(2)The relationship between the reflectivity and chlorophyll content of rape leaves was studied, and establishing the quantitative analysis model of rape chlorophyll content. ANN was applied to establish the model between the spectral reflection values and SPAD values. The prediction results were obtained for the nitrogen content of rape leaf with the correlation of prediction of R=0.9237.
(3)dentifying different rapeseed varieties in different growth periods, finding out the characteristic bands of rape leaves. obtaining features bands of the rape which are 544-565、674-693 and708-723nm, and using features bands to establish the identification models which have good results on the identification.
(4)Studying the extraction methods of hyperspectral image information: hyperspectral data processing method was researched and the model of quantitative analysis was established.It shows that the hyperspectral imaging technology has a fast, nondestructive and accurate classification and identification effects on rape varieties.
针对国内外现状,本论文以油菜为研究对象,采用高光谱图像技术确定了油菜籽的特征波段,并用于鉴别不同品种的油菜籽品种研究了油菜叶片高光谱反射率与油菜叶绿素含量(SPAD值)的关系；还研究了不同生长时期不同油菜品种的鉴别方法。本论文的主要研究结论如下：
(1)采用高光谱图像技术对不同品种的油菜籽进行鉴别分析。通过对高光谱数据进行主成分分析,实现了高光谱数据的降维,并找出油菜籽的3个特征波长,采用基于灰度统计矩阵和灰度直方图的纹理特征提取方法,提取了油菜籽的10个纹理参数。研究了基于BP神经网络的油菜籽品种鉴别模型,模型训练时判别率为93.75%,预测时判别率为91.67%。
(2)研究了油菜叶片反射率与油菜叶绿素含量的关系,建立了油菜叶绿素含量的定量分析模型。根据特征波长结合神经网络建立了油菜叶片SPAD值预测模型,结果表明,模型判别的相关系数为0.9237,预测相关系数为0.9526。
(3)对不同生长时期不同油菜品种的鉴别分析,分别找出油菜叶片的特征波长,得到了油菜叶片的特征波段为544-565、674-693和708-723nm,并利用特征波段建立油菜叶片鉴别模型,获得了较好的结果。
(4)研究了高光谱图像信息提取方法：高光谱图像数据处理方法,并结合BP神经网络建立了相应的定量分析模型。说明应用高光谱图像技术对油菜信息进行快速、无损、准确地获取是可行的。
Precision agriculture is modern agriculture which is based on information and knowledge,it can not only utilizate agricultural resources reasonably,increase crop yield and quality,reduce cost and improve the ecological environment,and then realize the sustainable development of agriculture, but also have a significant effect of promoting agricultural modernization the development of industries related to agriculture system.Quick and effective collection and describe crop growth information is an important basis of precision agriculture practice.
According to the situation at home and abroad, this paper choose the Rape as the research object,uses hyperspectral imaging technology to determine the characteristic bands,and then to identify different kinds of rapeseed varieties.we studied the relationships of hyperspectral reflectance of rape leaves and chlorophyll content (the SPAD value).we also research how to identify different rapeseed varieties in different growth periods.This paper mainly studies the conclusion is as follows:
(1)Applying hyperspectral image technology to identify different rapeseed varieties.Through principal component analysis of the hyperspectral data,it realized dimensionality reduction,and three characteristic bands were found out.The texture parameters were extracted from the optimal bands images based on gray level histogram and gray level co-occurrence matrix (GLCM) statistical methods. Artificial neural network model was used for the identification of varieties of rapeseed. Detection results of ANN model showed that calibration and prediction sets of rapeseed varieties were 93.75% and 91.67%, respectively.
(2)The relationship between the reflectivity and chlorophyll content of rape leaves was studied, and establishing the quantitative analysis model of rape chlorophyll content. ANN was applied to establish the model between the spectral reflection values and SPAD values. The prediction results were obtained for the nitrogen content of rape leaf with the correlation of prediction of R=0.9237.
(3)dentifying different rapeseed varieties in different growth periods, finding out the characteristic bands of rape leaves. obtaining features bands of the rape which are 544-565、674-693 and708-723nm, and using features bands to establish the identification models which have good results on the identification.
(4)Studying the extraction methods of hyperspectral image information: hyperspectral data processing method was researched and the model of quantitative analysis was established.It shows that the hyperspectral imaging technology has a fast, nondestructive and accurate classification and identification effects on rape varieties.
引文
1.白丽,王进,蒋桂英,等.干旱区基于高光谱的棉花遥感估产研究[J].中国农业科学,2008,41(8)：2499-2505.
2.柴阿丽,廖宁放,田立勋.基于高光谱成像和判别分析的黄瓜病害识别[J].光谱学与光谱分析,2010,30(5)：1357-1361.
3.蔡成静,王海光,安虎,等.小麦条锈病高光谱遥感监测技术研究[J].西北农林科技大学学报：自然科学版,2005,33(S1)：31-36.
4.陈鹏程,张建华,雷勇辉,等.高光谱遥感监测农作物病虫害研究进展[J].农业信息科学,2006,22(2)：388-391.
5.方宣钧,刘思衡.品种纯度和真伪的DNA分子标记鉴定及其应用[J].农业生物技术学,2008,8(2)：106-110.
6.冯伟,朱艳,姚霞,等.小麦氮素积累动态的高光谱监测[J].中国农业学,2008,41(7)：1937-1946.
7.冯伟,姚霞,田永超,等.基于高光谱遥感的小麦叶片含氮比监测[J].中国农业科学,2008,41(6)：1630-1639.
8.郭恩有,刘木华,赵杰文,陈全胜,等.脐橙糖度的高光谱图像无损检测技术[J].农业机械学报.2008,39(5)：91-93.
9.何勇,李晓丽,邵咏妮.基于主成分分析和神经网络的近红外光谱苹果品种鉴别方法研究[J].光谱学与光谱分析.2006,26(5)：850-853.
10.黄春燕,王登伟,陈冠文,等.基于高光谱植被指数的棉花干物质积累估算模型研究[J].棉花学报,2006,18(2)：115-119
11.景娟娟,王纪华.不同氮素营养条件下的冬小麦生理及光谱特性[J].应用技术术.2003：28-30.
12.金震宇,田庆久,惠凤鸣,等.稻叶绿素浓度与光谱反射率关系研究[J].遥感忮术与应用,2003,18(3)：134-137.
13.李常保,张靖.作物品种纯度鉴定技术研究[J].种子,1999,3：33-35
14.李映雪,朱艳,田永超,等.小麦叶片氮含量与冠层反射光谱指数的定量关系[J].作物学报.2006,32(3)：358-362.
15.李云梅,倪绍祥,黄敬峰.高光谱数据探讨水稻叶片叶绿素含量对叶片及冠层光 谱反射特性的影响[J].遥感技术与应用,2003,18(1)：1-4.
16.刘海龙,吴希军,田广军.三维荧光光谱技术及平行因子分析法在绿茶分析及种类鉴别中的应用[J].中国激光,2008,5(35)：685-689
17.刘海启.美国农业遥感技术应用现状简介[J].国土资源遥感,1997,19(4)：62-65.
18.刘伟东,项月琴,郑兰芬,等.高光谱数据与水稻叶面积及叶绿素密度的相分析[J].遥感学报,2004,4(4)：279-283.
19.马本学,应义斌,饶秀勤.高光谱成像在水果内部品质无损检测中的研究进展[J].光谱学与光谱分析,2009,29(6)：1611-1615.
20.马玉祥.谈精细农业的发展[J].农业科技管理,2003,22(5)：54-54.
21.蒲瑞良,宫鹏.森林生物化学与CASI高光谱分辨率遥感数据的相关分析[J].遥感学报,1997,1(2)：115-123.
22.齐小明,张录达,杜晓林,等PLS-BP法近红外光谱定量分析研究[J].光谱学与光谱分析,2003,5(23)：870-872.
23.乔红波,周益林,自由路,等地面高光谱和低空遥监测小麦白粉病初探[J].植物保护学报,2006,33(4)：341-344.
24.裘正军,宋海燕.应用SPAD和光谱技术研究油菜生长期间的氮素变化规律[J].农业工程学报,2007,23(7)：150-154.
25.孙贵彬.农业生产中存在的问题及发展精细农业的[J].民营科技,2009,5：95.
26.孙莉,陈曦,武建军,等.水分协迫下棉花冠屡叶片高光谱数据生物量变化研究[J].科学通报,2006(SI)：143-147.
27.唐挺进,等.蛋白质电泳技术的改良及其应用效果[D].山东农业科学,1998,(5)：20.
28.唐延林,王人潮,黄敬峰,等.不同供氮水平下水稻高光谱及其红边特征研究[J].遥感学报,2004,8(2)：185-192.
29.唐延林,王纪华,黄敬峰,等.利用稻成熟期冠层高光谱数据进行估产研究[J].作物学报,2004,30(8)：739-744.
30.唐延林,王秀珍,王福民,等.农作物LAI和生物量的高光谱法测定[J].西北农林科技大学学报(自然科学版),2004,32(11)：100-104.
31.唐延林,王秀珍,王珂,等.利用光谱法测定水稻生物物理参数及其与光谱变量的相关性研究[J].贵州大学学报(农业与生物科学版),2002,21(5)：327-331.
32.田庆久,宫彭,赵春江.用光谱反射率诊断小麦水分状况的可行性分析[J].科学通报,2000(24)：2645-2650
33.田永超,曹卫星,姜东,等.不同水氮条件下水稻冠层反射光谱与叶片水势关系的研究[J].水土保持学报,2003,17(3)：178-180.
34.王纪华,王之杰.冬小麦冠层氮素的垂直分布及光谱响应[J].遥感学报,2004,8(4)：309-315.
35.汪懋华.“精细农业”发展与工程技术创新[J].农业工程学报,1999,1
36.王秀珍,黄敬峰,李云女等.水稻叶面积指数的高光谱遥感估算模型[J].遥感学报,2004,8(1)：81-88.
37.王延颐,高庆芳.稻田光谱与水稻长势及产量结构要素关系的研究[J].国土资源学报,1996,(1)：51-55.
38.吴春霞,王进.基于高光谱技术的棉花冠层反射特征研究[J].农业与技术,2008,28(4)：56-60.
39.吴长山,项月琴,郑兰芬,等.利用高光谱数据对作物群体叶绿素密度估算的研究[J].遥感学报,2000,4(3)：228-232.
40.吴刚,唐振民,程勇,等。吴刚,灰度共生矩阵纹理特征的运动目标跟踪方法[J]。南京理工大学学报(自然科学版),2010,4(34)：459-463
41.吴华兵,朱艳,田永超,等.棉花冠屡高光谱指数与叶片氮积累量的定量关系[J].作物日报,2007,33(3)：518-522.
42.吴建国,石春海,张海珍,等.构建整粒油菜籽脂肪酸成分近红外反射光谱分析模型的研究[J].光谱学与光谱分析,2006,26(2)：259-262.
43.吴倩,林蕾,王学军,李宁宁.福海叶绿素含量的人工神经网络反演模型阴[J].地理与地理信息科学,2004,20(4)：27-30.
44.吴锐,黄剑华,唐降龙,刘家锋.基于灰度直方图和谱聚类的文本图像二值化方法[J].电子与信息学报,2009,10(31)：2460-2463
45.阎平凡,张长水.人工神经网络与模拟进化计算[J].北京：清华大学出社,2000.
46.杨诸胜,郭雷,罗欣,等.基于分段主成分分析的高光谱图像波段选择算法研究[J]. 测绘工程,2006,15(3)：15-18.
47.苑丽红,付丽,杨勇,苗静.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用,2009,4(29)：1018-1021.
48.张春庆,等.NAV-PAGE技术与玉米种子纯度测定[J].中国农业科学,1995,(6)
49.张霞,刘良云.利用高光谱遥感图像估算小麦氮含量[J].遥感学报,2003,7(3)：176-179.
50.张喜杰,李民赞,张彦娥,等.基于自然光照反射光谱的温室黄瓜叶片含氮量预测[J].农业工程学报,2004,20(6)：11-14.
51.郑循刚,罗怀风.四川省油菜产业发展研究[J].农业技术经济,2002,1：51-56.
52.朱述龙,张占睦.遥感图像获取分析[M].北京科学出版社,2000：153-157.
53.朱行.正在不断普及的美国精确农业[J].粮食与油脂,2002(12)：51-53.
54.朱哲燕,鲍一丹.油菜叶绿素与氮含量关系的试验研究[J].浙江大学学报(农业与生命科学版).2006,32(2)：152-154.
55. A.Pinar. Grass chlorophyll and the reflectance red edge [J]. International Journal of Remote Sensing,1996,17(2):351-357.
56. Blackmer T M, Schepers J S, Varvel G E, et al. Nitrogen deficiency detection using reflected short wave radiation from irrigated corn canopies [J]. Agronomy Journal,1996,88 (1):1-5.
57. Bodo M.Urs S.Estimating the nitrogen nutrition index using spectral canopy reflectance measurements [J].European Journal of Agronomy,2008,7:1-7.
58. Bonham-Carter G F. Numerical procedures and computer program for fitting an inverted Gaussian model to vegetation reflectance data [J].Computers & Geosciences,1988,14(3):339-356.
59. Comp ton J. Tucker. Remote Sensing of Leaf Water Content in the Near Infrared [J].Remote Sensing of Environment,1980,10:23-32.
60. Dohermann A, Pampohno M F, Indirect leaf area index measurement as a tool for characterizing rice growth at the field scale [J].Communications on Soil Science and Plant Analysis 1995,26:1507-1523.
61. Everitt J H, Pettit R D, Alaniz M A. Remote sensing of broom snake weed (Gutierrez ia sarothrae) and spiny aster(Aster spinosus)[J]. Weed Science,1987, 35(2):295-302.
62. Feng Lei, Hu Xingyue, He Yong, et al. Ground based nitrogen status of canola leaves using charged coupled device imaging sensor [A]. Proceedings of the 2005 IEEE, Engineering in medicine and bi0109y 27th annual conference, Shanghai[C]. China,3125-3128.
63. Gao Jianqin, Zhang Jiefu, Pu Huiming, et al. Analysis of oil,oleic acid and erucic acid contents in rapeseed by near infrared reflectance spectroscopy (NIRS) [J]. Jiangsu Journal of Agricultural Science,2007,23(3):189-195.
64. Gitelson A, KaufmanY J,Robert,al.Novel algorithms for remote estimation of vegetation fraction[J].Remote Sensing of Environment,2002.80:76-87.
65. Inoue Y, Penuelas J. An AOTE-based hyperspectral imaging system for field use in eco-physiological and agricultural applications [J].International Journal of Remote Sensing,2001,22(18):3883-3888.Peng Y, Lu R. Analysis of spatially resolved hyperspeetral scattering images for assessing apple fruit firmness and soluble solids content [J].Postharvest biology and Technology,2008,48:52-62.
66. Kokaly R,Root R,Brown K,Anderson G L,et al.Calibration of compact airborne sepctrographic imager(CASI) data to Surface reflectance at Theodore Roosevelt National Park[R].Abstract:21st Annual Meeting of the American Chemical Society.San Diego.CA,2001:1-5.
67. Manolakis D, Marden D. Dimensionality Reduction of Hyperspectral Imaging Data Using Local Principal Components Transforms [J]. Proceedings of SPIE, 2004,54(25)393-401.
68. Martin Schweizer, Kevin Segall, Sarah Medina,et al. Rapeseed/Canola Protein Isolates for Use in the Food Industry [A]. In:Fu TD, Guan CY. Proceedings of thel2th International Rapeseed Congress[C]. Science Press USA Inc,2007.
69. Nang Hseng Hom,Heiko C Becker. Non-destructive analysis of rapeseed quality by NIRS of small seed samples and single seeds [J]. Euphytica,2007,153:27-34.
70. Owen CA, Bita Ec, Banilas G,et al.AFLP reveals structural details of genetic diversity within cultivated olive germ plan from the Eastern Mediterranean[J]. Theor Appl Genet,2005,110(7):1169-1176.
71.Peixin Hu, Qimin Lu, Rong Shu,et al.An airborne pushbroom hyperspectral imager with wide field of view [J]. Chin. Opt.Let t.,2005,3 (12):689-691.
72. Peng Y, Lu R. Analysis of spatially resolved hyperspeetral scattering images for assessing apple fruit firmness and soluble solids content [J].Postharvest biology and Technology,2008,48:52-62.
73. Prasad S T,Ronatd B.smith,al.Hyperspectral vegetation indices and their relationship with agricultural crop characteristics [J].Remote Sensing Environment. 2000,71:158-182.
74. RAMALINGAM,LINGP, DERKSEN Background reflectance compensation and its effect on multispectral leaf surface moisture assessment [J]. Transactions of the American Society of Agricultural Engineering (ASAE),2005,48(1):375-383.
75. Shibayama, M.,T. Akiyama. Seasonal visible, near-infrared and mid-infrared spectra of rice canopies in relation to LAI and above-ground dry photo-mass [J]. Remote Sensing of Environment,1989,(27):119-127.
76. Takahashi W, Nguyen C V, Kawaguchi S, et al.Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance office canopies [J].Plant Production Science,2000,3(4): 377-286.
77. Wu Jianguo, Shi Chunhai, Zhang Haizhen, et al. Study on developing calibration mModels of fat acid composition in intact rapeseed by near infrared reflectance spectroscopy[J]. Spectroscopy and Spectral Analysis,2006,26(2):259-262.
78. ZHANG M H,QIN Z H,LIU X.et al.Ustin.Detection Of stress in tomatoes induced by late blight disease in Califomia,USA,using hyperspectral remote sensing [J].Intematitml Joumal Of Applied Earth Observation and Geoinformation, 2003,4:295-310.
2.柴阿丽,廖宁放,田立勋.基于高光谱成像和判别分析的黄瓜病害识别[J].光谱学与光谱分析,2010,30(5)：1357-1361.
3.蔡成静,王海光,安虎,等.小麦条锈病高光谱遥感监测技术研究[J].西北农林科技大学学报：自然科学版,2005,33(S1)：31-36.
4.陈鹏程,张建华,雷勇辉,等.高光谱遥感监测农作物病虫害研究进展[J].农业信息科学,2006,22(2)：388-391.
5.方宣钧,刘思衡.品种纯度和真伪的DNA分子标记鉴定及其应用[J].农业生物技术学,2008,8(2)：106-110.
6.冯伟,朱艳,姚霞,等.小麦氮素积累动态的高光谱监测[J].中国农业学,2008,41(7)：1937-1946.
7.冯伟,姚霞,田永超,等.基于高光谱遥感的小麦叶片含氮比监测[J].中国农业科学,2008,41(6)：1630-1639.
8.郭恩有,刘木华,赵杰文,陈全胜,等.脐橙糖度的高光谱图像无损检测技术[J].农业机械学报.2008,39(5)：91-93.
9.何勇,李晓丽,邵咏妮.基于主成分分析和神经网络的近红外光谱苹果品种鉴别方法研究[J].光谱学与光谱分析.2006,26(5)：850-853.
10.黄春燕,王登伟,陈冠文,等.基于高光谱植被指数的棉花干物质积累估算模型研究[J].棉花学报,2006,18(2)：115-119
11.景娟娟,王纪华.不同氮素营养条件下的冬小麦生理及光谱特性[J].应用技术术.2003：28-30.
12.金震宇,田庆久,惠凤鸣,等.稻叶绿素浓度与光谱反射率关系研究[J].遥感忮术与应用,2003,18(3)：134-137.
13.李常保,张靖.作物品种纯度鉴定技术研究[J].种子,1999,3：33-35
14.李映雪,朱艳,田永超,等.小麦叶片氮含量与冠层反射光谱指数的定量关系[J].作物学报.2006,32(3)：358-362.
15.李云梅,倪绍祥,黄敬峰.高光谱数据探讨水稻叶片叶绿素含量对叶片及冠层光 谱反射特性的影响[J].遥感技术与应用,2003,18(1)：1-4.
16.刘海龙,吴希军,田广军.三维荧光光谱技术及平行因子分析法在绿茶分析及种类鉴别中的应用[J].中国激光,2008,5(35)：685-689
17.刘海启.美国农业遥感技术应用现状简介[J].国土资源遥感,1997,19(4)：62-65.
18.刘伟东,项月琴,郑兰芬,等.高光谱数据与水稻叶面积及叶绿素密度的相分析[J].遥感学报,2004,4(4)：279-283.
19.马本学,应义斌,饶秀勤.高光谱成像在水果内部品质无损检测中的研究进展[J].光谱学与光谱分析,2009,29(6)：1611-1615.
20.马玉祥.谈精细农业的发展[J].农业科技管理,2003,22(5)：54-54.
21.蒲瑞良,宫鹏.森林生物化学与CASI高光谱分辨率遥感数据的相关分析[J].遥感学报,1997,1(2)：115-123.
22.齐小明,张录达,杜晓林,等PLS-BP法近红外光谱定量分析研究[J].光谱学与光谱分析,2003,5(23)：870-872.
23.乔红波,周益林,自由路,等地面高光谱和低空遥监测小麦白粉病初探[J].植物保护学报,2006,33(4)：341-344.
24.裘正军,宋海燕.应用SPAD和光谱技术研究油菜生长期间的氮素变化规律[J].农业工程学报,2007,23(7)：150-154.
25.孙贵彬.农业生产中存在的问题及发展精细农业的[J].民营科技,2009,5：95.
26.孙莉,陈曦,武建军,等.水分协迫下棉花冠屡叶片高光谱数据生物量变化研究[J].科学通报,2006(SI)：143-147.
27.唐挺进,等.蛋白质电泳技术的改良及其应用效果[D].山东农业科学,1998,(5)：20.
28.唐延林,王人潮,黄敬峰,等.不同供氮水平下水稻高光谱及其红边特征研究[J].遥感学报,2004,8(2)：185-192.
29.唐延林,王纪华,黄敬峰,等.利用稻成熟期冠层高光谱数据进行估产研究[J].作物学报,2004,30(8)：739-744.
30.唐延林,王秀珍,王福民,等.农作物LAI和生物量的高光谱法测定[J].西北农林科技大学学报(自然科学版),2004,32(11)：100-104.
31.唐延林,王秀珍,王珂,等.利用光谱法测定水稻生物物理参数及其与光谱变量的相关性研究[J].贵州大学学报(农业与生物科学版),2002,21(5)：327-331.
32.田庆久,宫彭,赵春江.用光谱反射率诊断小麦水分状况的可行性分析[J].科学通报,2000(24)：2645-2650
33.田永超,曹卫星,姜东,等.不同水氮条件下水稻冠层反射光谱与叶片水势关系的研究[J].水土保持学报,2003,17(3)：178-180.
34.王纪华,王之杰.冬小麦冠层氮素的垂直分布及光谱响应[J].遥感学报,2004,8(4)：309-315.
35.汪懋华.“精细农业”发展与工程技术创新[J].农业工程学报,1999,1
36.王秀珍,黄敬峰,李云女等.水稻叶面积指数的高光谱遥感估算模型[J].遥感学报,2004,8(1)：81-88.
37.王延颐,高庆芳.稻田光谱与水稻长势及产量结构要素关系的研究[J].国土资源学报,1996,(1)：51-55.
38.吴春霞,王进.基于高光谱技术的棉花冠层反射特征研究[J].农业与技术,2008,28(4)：56-60.
39.吴长山,项月琴,郑兰芬,等.利用高光谱数据对作物群体叶绿素密度估算的研究[J].遥感学报,2000,4(3)：228-232.
40.吴刚,唐振民,程勇,等。吴刚,灰度共生矩阵纹理特征的运动目标跟踪方法[J]。南京理工大学学报(自然科学版),2010,4(34)：459-463
41.吴华兵,朱艳,田永超,等.棉花冠屡高光谱指数与叶片氮积累量的定量关系[J].作物日报,2007,33(3)：518-522.
42.吴建国,石春海,张海珍,等.构建整粒油菜籽脂肪酸成分近红外反射光谱分析模型的研究[J].光谱学与光谱分析,2006,26(2)：259-262.
43.吴倩,林蕾,王学军,李宁宁.福海叶绿素含量的人工神经网络反演模型阴[J].地理与地理信息科学,2004,20(4)：27-30.
44.吴锐,黄剑华,唐降龙,刘家锋.基于灰度直方图和谱聚类的文本图像二值化方法[J].电子与信息学报,2009,10(31)：2460-2463
45.阎平凡,张长水.人工神经网络与模拟进化计算[J].北京：清华大学出社,2000.
46.杨诸胜,郭雷,罗欣,等.基于分段主成分分析的高光谱图像波段选择算法研究[J]. 测绘工程,2006,15(3)：15-18.
47.苑丽红,付丽,杨勇,苗静.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用,2009,4(29)：1018-1021.
48.张春庆,等.NAV-PAGE技术与玉米种子纯度测定[J].中国农业科学,1995,(6)
49.张霞,刘良云.利用高光谱遥感图像估算小麦氮含量[J].遥感学报,2003,7(3)：176-179.
50.张喜杰,李民赞,张彦娥,等.基于自然光照反射光谱的温室黄瓜叶片含氮量预测[J].农业工程学报,2004,20(6)：11-14.
51.郑循刚,罗怀风.四川省油菜产业发展研究[J].农业技术经济,2002,1：51-56.
52.朱述龙,张占睦.遥感图像获取分析[M].北京科学出版社,2000：153-157.
53.朱行.正在不断普及的美国精确农业[J].粮食与油脂,2002(12)：51-53.
54.朱哲燕,鲍一丹.油菜叶绿素与氮含量关系的试验研究[J].浙江大学学报(农业与生命科学版).2006,32(2)：152-154.
55. A.Pinar. Grass chlorophyll and the reflectance red edge [J]. International Journal of Remote Sensing,1996,17(2):351-357.
56. Blackmer T M, Schepers J S, Varvel G E, et al. Nitrogen deficiency detection using reflected short wave radiation from irrigated corn canopies [J]. Agronomy Journal,1996,88 (1):1-5.
57. Bodo M.Urs S.Estimating the nitrogen nutrition index using spectral canopy reflectance measurements [J].European Journal of Agronomy,2008,7:1-7.
58. Bonham-Carter G F. Numerical procedures and computer program for fitting an inverted Gaussian model to vegetation reflectance data [J].Computers & Geosciences,1988,14(3):339-356.
59. Comp ton J. Tucker. Remote Sensing of Leaf Water Content in the Near Infrared [J].Remote Sensing of Environment,1980,10:23-32.
60. Dohermann A, Pampohno M F, Indirect leaf area index measurement as a tool for characterizing rice growth at the field scale [J].Communications on Soil Science and Plant Analysis 1995,26:1507-1523.
61. Everitt J H, Pettit R D, Alaniz M A. Remote sensing of broom snake weed (Gutierrez ia sarothrae) and spiny aster(Aster spinosus)[J]. Weed Science,1987, 35(2):295-302.
62. Feng Lei, Hu Xingyue, He Yong, et al. Ground based nitrogen status of canola leaves using charged coupled device imaging sensor [A]. Proceedings of the 2005 IEEE, Engineering in medicine and bi0109y 27th annual conference, Shanghai[C]. China,3125-3128.
63. Gao Jianqin, Zhang Jiefu, Pu Huiming, et al. Analysis of oil,oleic acid and erucic acid contents in rapeseed by near infrared reflectance spectroscopy (NIRS) [J]. Jiangsu Journal of Agricultural Science,2007,23(3):189-195.
64. Gitelson A, KaufmanY J,Robert,al.Novel algorithms for remote estimation of vegetation fraction[J].Remote Sensing of Environment,2002.80:76-87.
65. Inoue Y, Penuelas J. An AOTE-based hyperspectral imaging system for field use in eco-physiological and agricultural applications [J].International Journal of Remote Sensing,2001,22(18):3883-3888.Peng Y, Lu R. Analysis of spatially resolved hyperspeetral scattering images for assessing apple fruit firmness and soluble solids content [J].Postharvest biology and Technology,2008,48:52-62.
66. Kokaly R,Root R,Brown K,Anderson G L,et al.Calibration of compact airborne sepctrographic imager(CASI) data to Surface reflectance at Theodore Roosevelt National Park[R].Abstract:21st Annual Meeting of the American Chemical Society.San Diego.CA,2001:1-5.
67. Manolakis D, Marden D. Dimensionality Reduction of Hyperspectral Imaging Data Using Local Principal Components Transforms [J]. Proceedings of SPIE, 2004,54(25)393-401.
68. Martin Schweizer, Kevin Segall, Sarah Medina,et al. Rapeseed/Canola Protein Isolates for Use in the Food Industry [A]. In:Fu TD, Guan CY. Proceedings of thel2th International Rapeseed Congress[C]. Science Press USA Inc,2007.
69. Nang Hseng Hom,Heiko C Becker. Non-destructive analysis of rapeseed quality by NIRS of small seed samples and single seeds [J]. Euphytica,2007,153:27-34.
70. Owen CA, Bita Ec, Banilas G,et al.AFLP reveals structural details of genetic diversity within cultivated olive germ plan from the Eastern Mediterranean[J]. Theor Appl Genet,2005,110(7):1169-1176.
71.Peixin Hu, Qimin Lu, Rong Shu,et al.An airborne pushbroom hyperspectral imager with wide field of view [J]. Chin. Opt.Let t.,2005,3 (12):689-691.
72. Peng Y, Lu R. Analysis of spatially resolved hyperspeetral scattering images for assessing apple fruit firmness and soluble solids content [J].Postharvest biology and Technology,2008,48:52-62.
73. Prasad S T,Ronatd B.smith,al.Hyperspectral vegetation indices and their relationship with agricultural crop characteristics [J].Remote Sensing Environment. 2000,71:158-182.
74. RAMALINGAM,LINGP, DERKSEN Background reflectance compensation and its effect on multispectral leaf surface moisture assessment [J]. Transactions of the American Society of Agricultural Engineering (ASAE),2005,48(1):375-383.
75. Shibayama, M.,T. Akiyama. Seasonal visible, near-infrared and mid-infrared spectra of rice canopies in relation to LAI and above-ground dry photo-mass [J]. Remote Sensing of Environment,1989,(27):119-127.
76. Takahashi W, Nguyen C V, Kawaguchi S, et al.Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance office canopies [J].Plant Production Science,2000,3(4): 377-286.
77. Wu Jianguo, Shi Chunhai, Zhang Haizhen, et al. Study on developing calibration mModels of fat acid composition in intact rapeseed by near infrared reflectance spectroscopy[J]. Spectroscopy and Spectral Analysis,2006,26(2):259-262.
78. ZHANG M H,QIN Z H,LIU X.et al.Ustin.Detection Of stress in tomatoes induced by late blight disease in Califomia,USA,using hyperspectral remote sensing [J].Intematitml Joumal Of Applied Earth Observation and Geoinformation, 2003,4:295-310.