基于计算机图像处理检测温室黄瓜幼苗土壤水份含量的技术研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
在工厂化农业高速发展的今天,作物栽培管理的自动化和现代化日趋重要。应用现代无损伤测量和检测手段进行作物长势诊断的技术研究,成为现代农业技术发展的热点问题之一。本研究选择温室黄瓜作为研究对象,在自然光条件下进行试验,运用计算机图像处理技术,对黄瓜的叶片图像特征进行提取,分析黄瓜植株的生长信息,进而实现对土壤水份含量的检测,检测结果可作为精准灌溉的参考,为后期的灌溉提供科学的依据。
     基于以上目的,本研究主要进行了以下工作:
     (1)按照常规方法对植株的生长进行管理,试验中土壤水份含量设计5个处理水平:90%、80%、70%、60%和50%,浇水量按照土壤水份含量各处理水平的±5%控制。使用数码相机统一采集自植株顶部下数第3片功能叶的图像。
     (2)对叶片图像进行直方图修正、平滑和锐化等预处理,再分割出叶片和背景。提出了一种适合于自然光条件下分割叶片和复杂背景的方法,采用过绿分割法对图像进行分割,并运用自动选择分类阈值的最大方差比法确定分割阈值T,该方法能很好的将叶片和背景进行分割。
     (3)运用图像处理技术,提取出叶片图像各颜色特征值。通过分析土壤水份含量与各颜色特征的线性相关关系得出,土壤水份含量分别与颜色特征r、H之间均呈高度相关性,并且达到了显著性检验水平(p=0.05),同时,它们的值域变化区间和土壤水份含量水平之间存在有较好的对应关系。选用颜色特征参数r分量和H分量作为检测系统的检测指标,对土壤水份含量进行检测是可行的。
     (4)在检测系统的检测指标和土壤水份含量之间建立三层BP神经网络,采用自适应学习速率梯度下降反向传播算法对网络进行训练,训练后的网络对训练样本的正确识别率为100%,对测试样本,处理水平50%至90%的识别率分别为92.5%、97.5%、100%、97.5%和100%。以VC++为开发平台,编制出土壤水份含量的检测系统。
     本研究对于计算机图像处理技术应用于温室作物实际生产,并最终提高工厂化农业的智能化管理水平具有重要的意义。
As industrialized agriculture technology progress rapidly, the automatization for cropraising is becoming more important. The nondestructive measurement and testing is avery hot agricultural production technology. Choosing greenhouse cucumber as theresearch object, cucumber leaves image feature was obtained using computer imageprocessing technology under natural illumination, and the growth information ofcucumber was analyzed, then realizing the moisture content of soil was tested, theresults could be used as a reference for precision irrigation, and provide scientific basisfor the latter part of the irrigation.
     Based on above goals, the following work was finished in this study:
     (1) Managing the plant according to conventional methods, the soil moisture contentwas set as five levels: 90%、80%、70%、60% and 50%. The amount of water wascontrolled with the±5% of soil moisture content. The images of the No.3 leaf wereacquired using digital camera.
     (2) The leaf images were used to pass through histogram correcting, smoothing andsharpening, and then segmented they were leaves and background. A suitable method,super-green, for segmenting leaves and complex background, was advanced undernatural illumination, and the maximal variance ratio subtract method which could chooseautomatically threshold was used to compute the threshold segmentation T, which waseffective by experiment.
     (3) Using computer image processing technology, color feature of leaf image wasobtained. There are both a high correlation between soil moisture content and colorfeatures r, H, by analyzing the linear correlation between soil moisture content and colorfeatures, which achieved confidence level (p=0.05), and then, there is a well relationshipbetween the range of r, H and soil moisture content. It is feasible that color feature r, Hwere selected as testing parameters of the testing system.
     (4) The three tiers BP neural network was designed between the testing parametersand soil moisture content. The network was trained by a reverse transmission algorithmof self adaptive learning rate with gradient reduction, after training the network, thecorrect recognition rate is 100% for training samples, it is 92.5%, 97.5%, 100%, 97.5%and 100% for treatment level 50% to 90% of the tested samples. The testing system wasprogrammed with the development platform of VC++.
     This study may provide a significant help to the greenhouse crop production bycomputer image processing technology, and ultimately to improve the intelligentmanagement level of industrialized agriculture.
引文
1.边肇棋,张学工.模式识别.北京:清华大学出版社,2000
    2.蔡鸿昌,崔海信,宋卫堂,高丽红.黄瓜初花期叶片光合色素含量与颜色特征的初步研究.农业工程学报,2006,22(9):34-38
    3.蔡鸿昌,崔海信,宋卫堂,高丽红.颜色模型在蔬菜谈氮素诊断中的应用前景探讨.农业工程学报,2005,21(增刊):113-117
    4.曹敏,马旭,姚亚利.图像处理技术在农作物营养信息检测中的研究展望.农机化研究,2005,5:5-7
    5.陈佳娟,纪寿文.基于遗传神经网络的玉米叶色的自动测定研究.农业工程学报,2000,16(3):115-117
    6.陈立平,赵春江.应用人工智能技术进行作物形态诊断初探.计算机与农业,2000,9:22-24
    7.陈书海,傅录祥.实用数字图像处理.北京:科学出版社,2005
    8.党安荣,王晓栋,陈晓峰,张建宝.ERDAS IMAGINE遥感图像处理方法.北京:清华大学出版社,2003
    9.杜社妮,梁银丽,徐福利,陈志杰.日光温室不同水分条件下盆栽黄瓜产量和土壤微生物数量.干旱地区农业研究,2005,23(3):49-53
    10.冯嘉玥,邹志荣,陈修斌.土壤水分对温室春黄瓜苗期生长与生理特性的影响.西北植物学报,2005,25(6):1242-1245
    11.官章全,韩云君,李果.VC++6.0高级编程范例.北京:电子工业出版社,2001:483-526
    12.胡春华,李萍萍.基于图像处理的黄瓜缺氮与缺镁判别的研究.江苏大学学报(自然科学版),2004,25(1):9-12
    13.胡上序,程翼宇.人工神经元计算导论.北京:科学出版社,1994
    14.胡永光,李萍萍,堀部和雄.日本的植物工厂及其新技术.世界农业,2002,11:44-46
    15.霍宏涛.数字图像处理.北京:机械工业出版社,2003
    16.焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1995
    17.李弼程,彭天强,彭波.智能图像处理技术.北京:电子工业出版社,2004
    18.李朝晖.数字图像处理及应用.北京:机械工业出版社,2004:84-85
    19.李林,高政.一种新颖的灰度形态学算子.计算机辅助设计与图形学学报,2001,13(9):820-824
    20.李少昆,王崇桃.图象及机器视觉技术在作物科学中的应用进展.石河子大学学报(自然科学版),2002,6(1):79-85
    21.林万孝.电子技术在农业中的应用.世界农业,1997,6:53-54
    22.刘关松,陆宗骐,徐建国,高敦岳.几种彩色模型在不同光照条件下的稳定性分析.小型微型计算机系统,2002,23(7):882-885.
    23.刘艳洁,杨世凤,钱东平,霍晓静.作物水胁迫检测的研究进展和发展方向.大津科技大 学学报,2004,19(4):26-30
    24.罗锡文,藏英,周志艳.精细农业中农情信息采集技术的研究进展.农业工程学报,2006,22(1):167-173
    25.毛罕平,徐贵力,李萍萍.番茄缺素叶片的图像特征提取和优化选择研究.农业工程学报,2003,19(2):133-136
    26.毛罕平.农业装备智能化技术的发展动态和重点领域.农机科技推广,2005,5:12-14
    27.彭淑敏.神经网络图像识别技术研究与实现.[硕士学位论文].西安:西安电子科技大学图书馆,2005
    28.戚大伟,牟洪波.人工神经网络在木材缺陷检测中的应用.森林工程,2006,22(1):21-23
    29.齐龙.基于图像处理的作物病害诊断及叶片形态参数测量技术的研究.[硕士学位论文].长春:吉林大学图书馆,2004
    30.阮秋琦,阮宇智.数字图像处理(第2版).北京:电子工业出版社,2003
    31.沙宗尧,边馥苓.“3S”技术的农业应用与精细农业工程.测绘通报,2003,(6):29-32
    32.宋敏.基于神经网络的目标识别技术研究.[硕士学位论文].南京:南京理工大学图书馆,2005
    33.孙即祥.现代模式识别.长沙:国防大学科技出版社,2002
    34.汤顺青.色度学.北京:北京理工大学出版社,1990
    35.田捷,沙飞,张新生.实用图象分析与处理技术.北京:电子工业出版社,1995
    36.王超龙,陈志华.Visual C++6.0从入门与提高.北京:人民邮电出版社,2002
    37.王惠敏.生物材料降解的图像处理与图像分析.[硕士学位论文].武汉:武汉理工大学图书馆,2002
    38.王润生.图像理解.长沙:国防科技大学出版社,1995
    39.王伟.人工神经网络原理——入门与应用.北京:北京航空航天大学出版社,1995,12
    40.吴微.神经网络计算.北京:高等教育出版社,2003:9-17
    41.徐贵力.基于计算机视觉技术的无土栽培番茄缺素智能识别研究.[博士学位论文].镇江:江苏大学图书馆,2002
    42.杨敏华,刘良云,刘团结,黄文江,赵春江.小麦冠层理化参量的高光谱遥感反演试验研究.测绘学报,2002,31(4):316-321
    43.余成波.数字图像处理及MATLAB实现.重庆:重庆大学出版社,2003
    44.袁向荣.基于神经网络的图像识别技术在机器人视觉系统中的应用.[硕士学位论文].济南:山东大学图书馆,2005
    45.翟胜,梁银丽,王巨媛,杜社妮.七壤水分对日光温室黄瓜生长发育及光合特性的影响.中国农学通报,2005,21(2):187-191
    46.张宏林.Visual C++数字图像模式识别技术及工程实践.北京:人民邮电出版社,2003
    47.张棉天,陈幼媛.春黄瓜品种比较试验.上海蔬菜,1999(1):15-16
    48.张宪法,于贤昌,张振贤.土壤水分对温室黄瓜结果期生长与生理特性的影响.园艺学报, 2002,29(4):343-347
    49.张晓萍,陈金平,王和洲,孟兆江.苗期不同土壤水分状况的秋黄瓜生理反应.灌溉排水,2002,21(9):56-59
    50.张彦娥.基于计算机视觉技术温室作物长势诊断机理与方法研究.[博士学位论文].北京:中国农业大学图书馆,2005
    51.张振贤.蔬菜生理.北京:中国农业科技出版社,1993:272-279
    52.张作贵.自然光照条件下基于机器视觉的番茄缺素的智能诊断研究.[硕士学位论文].镇江:江苏大学图书馆,2005
    53.章霄,董艳雪,赵文娟.数字图像处理技术.北京:冶金工业出版社,2005
    54.赵春江,薛绪掌,王秀,陈立平,潘瑜春,孟志军.精准农业技术体系的研究进展与展望.农业工程学报,2003,19(4):7-12
    55.赵杰文,周晓兵.基于近红外图像纹理分析检测作物叶片含水率的研究.农业工程学报,1999,15(3):39-43
    56.周长吉.现代温室工程.北京:化学工业出版社,2003,3-10
    57.朱大奇,史慧.人工神经网络原理及应用.北京:科学出版社,2006
    58. Ahmad I S, Reid J F. Eval Uation of Color Representations for Maize Image. Agricultural Engineering Research, 1996, 63: 185-196
    59. Benady M, et al. Fruit Ripeness Determination by Electronic Sensing of Aromatic Volatiles. Transactions of the ASAE, 1995, 38(1): 251-257
    60. Colin Bradley. Rapid prototyping models generated from machine vision data. Computers in Industry. 2001, 44: 159-173
    61. D. M. Woebbecke, G. E. Meyer, K. Von Bargen, D. A. Mortehsen. Color Indices for Weed Identification under Various Soil, Residue, and Lighting Conditions. Transactions of the ASAE, 1995, 38(1): 259-269
    62. Gautart, Ramesh Kumar, Panigrahi, et al. Image Processing Techniques and Neural Network Models for Predicting Plant Nitrate Using Aerial Images. Proceedings of the International Joint Conference on Neural Networks. 2003, (2): 1031-1036
    63. Geoffrey Winsor, Peter Adams. Diagnosis of mineral disorders in plants (Vol.3): glasshouse crops. London: Her Majesty's Stationery Office, 2002: 5-12, 14-24
    64. George E Mayer, Date A Davison, An electronic image plant growth measurement system. Transactions of the ASAE, 1987, 30(1): 242-248
    65. Giyoung Kim, Kwan Hee Ryn. Crop Growth Measurements by Image Processing for Greenhouse Automation. An ASAE Meeting Presentation Paper No. 995002, 1999
    66. H. Shimizu, R. D. Hems. Computer-vision-based System for Plant Growth Analysis. Transactions of the ASAE, 1995, 38 (3): 959-964
    67. Hecht-Nielsen M. A. Improvement of the back propagation algorithm for training neural networks. Computers Chem. Engng, 1990,14(3): 337-341
    
    68. Humphries S, Simonton W. Identification of plant parts using color and geometric image data. Transactions of the ASAE, 1993, 36 (5): 1493-1500
    
    69. Ibarra J G, Tao Y, Newberry L, et al. Learning vector quantization for color classification of diseased air sacs in chicken carcasses. Transaction of the ASAE, 2002,45(5): 1629-1635
    
    70. Manish H., Bharati J., Jay Liu, John E, MacGregor. Image texture analysis method and comparisons. Chemometrics and intelligent laboratory systems, 2004, 72: 57-71
    
    71. Perntonis S. J, Lisboa P. Translation rotation and scale invariant pattern recognition by high-order NN and moment classifiers. IEEE Trans. NN, 1992,3: 241—251
    
    72. Seginer I., Elster R. T. Plant Wilt Detection by Computer Vision Tracking of Leaf Tips. Trans of 1992,35 (5): 1917-1991
    
    73. Ta-Te Lin, Jeng-Ming Chang. Vegetable Seedling Feature Using Stereo Color Imaging. ASAE/CSAE-CSGR Annual International Meeting, 1999
    
    74. Tian L. E, Slaughter D. C. Environmentally adaptive segmentation alga rithm for outdoor images segmentation. Computer & Election in Agric, 1998, 21(3): 153-168.

© 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