计算机视觉技术在杂草识别中的应用研究
|
摘要
化学除草是目前最主要的除草方式，但由于除草剂的使用方式都是大面积喷洒，不仅造成了浪费，也带来了许多负面的影响，如对水源、土壤和空气的污染等。提高除草剂的有效利用率是当务之急，研制用于化学除草的智能化变量喷药机是一条很有发展前景的新途径。智能化变量喷药机是指借助于计算机视觉技术，识别出杂草覆盖率并确定杂草的位置，有针对性地喷洒除草剂，这不仅能有效的减轻草害，而且能大大节约除草剂的使用，降低投入，还能保护生态环境。计算机视觉技术用于杂草识别是一个相当新的研究应用领域，目前理论和技术尚不成熟。智能化的变量喷药机能够做到利用计算机视觉技术实时根据杂草的生长密度变量喷洒药液，但是药液的浓度配制还不能实时进行。只能喷药前根据杂草的长势配制相应的药液浓度。杂草叶面积是评估杂草长势的重要指标，也是目前配制除草剂药液浓度的主要依据。论文应用计算机视觉理论和方法开发了一套包含测量叶面积的图像采集和调整模块、图像处理模块、叶面积数据库模块、叶面积曲线图显示和分析模块的软件系统，设计实现了既可用于采摘的叶片又可用于活体原位叶面积测量的硬件系统。整个系统既可用于测量杂草叶面积和分析杂草长势，也可用于其他绿色植物。针对户外采集的杂草图像论文研究实现了一种快速杂草识别算法，使其能够满足后续实时变量控制对信号的要求。根据这种算法设计了一种用于变量喷药机的杂草识别和信号控制系统，为进一步的研究工作打下了一定的基础。
The chemical herbicide is the most effective way of weeding. However, much chemical herbicide are wasted and may cause pollution of water, air and soil because of its use for large area. One promising way of solving the problem is to study and apply the intelligentized variable herbicide machine. The intelligentized variable herbicide machine can sense the density and location of weeds, and spray herbicide according these. So it can alleviate the harm of weeds, reduce cost and protect environment effectively. Because it is a new research filed to apply computer vision for weed-sensing, there are not mature theories to support the weed-sensing technology. Although the intelligentized variable herbicide machine sprays herbicide according to the results of weed-sensing, the herbicide can not be compounded while spraying. The concentration of herbicide must be made before spraying according the condition of weeds. The leaves area of weed is the standard of making the concentration. In this paper a set of softwar
e is made including four modules such as image-processing mould based on computer vision. An equipment for measuring area of live leaves is developed. They can be used to measure and analyses all green leaves. A short time algorithm for outdoor weed-sensing is realized in this paper. It can provide controlling-signal for variable control, and a system of weed-sensing and variable control for the intelligentized variable herbicide machine is designed.
The chemical herbicide is the most effective way of weeding. However, much chemical herbicide are wasted and may cause pollution of water, air and soil because of its use for large area. One promising way of solving the problem is to study and apply the intelligentized variable herbicide machine. The intelligentized variable herbicide machine can sense the density and location of weeds, and spray herbicide according these. So it can alleviate the harm of weeds, reduce cost and protect environment effectively. Because it is a new research filed to apply computer vision for weed-sensing, there are not mature theories to support the weed-sensing technology. Although the intelligentized variable herbicide machine sprays herbicide according to the results of weed-sensing, the herbicide can not be compounded while spraying. The concentration of herbicide must be made before spraying according the condition of weeds. The leaves area of weed is the standard of making the concentration. In this paper a set of softwar
e is made including four modules such as image-processing mould based on computer vision. An equipment for measuring area of live leaves is developed. They can be used to measure and analyses all green leaves. A short time algorithm for outdoor weed-sensing is realized in this paper. It can provide controlling-signal for variable control, and a system of weed-sensing and variable control for the intelligentized variable herbicide machine is designed.
引文
[1] 李孙荣．杂草及其防治[M]．北京：北京农业大学出版社，1991．94
[2] 农业部全国植保总站．中国农田杂草图册(第一集)[M]．北京：化学工业出版，1988．
[3] 马承忠，刘滨，许捷．农田杂草识别及防除—幼苗和成株简明图鉴[S]．北京：中国农业出版社，1999．
[4] 吴汉章等，除草剂药害图谱[S]．江苏：江苏科学技术出版社，1995．
[5] 李亚卿，高丁石，陈红旗等．旱田杂草及其化学防除[M]．北京：中国农业科技出版社，1999．
[6] 黄建中．农田杂草抗药性：产生机理、测定技术、综合治理[M]．北京：中国农业科技出版社，1995．
[7] 李光熙．提高科技含量，迈向新世纪的除草剂开发、研制与应用[J]．杂草科学，1998，17(1)：2～3．
[8] 蒋正荣．计算机杂草识别的实现及应用[J]．杂草科学，1999，24(4)：2～5．
[9] 蒋正荣．计算机杂草识别技术的研究现状[J]．上海环境科学，1999，18(4)：481～483．
[10] Guyer, D E et al. Machine vision and image processing for plant identification[J]. Transactions of the ASAE, 1988, 29(6):1500～1507.
[11] Blackshow, Robert E. Merits of a weed-sensing spayer to control weeds in conservation fallow and cropping Systems[J]. Weed Science, 1998, 46(3): 120～122.
[12] Sub Lee Won. Robotic weed control system fortomatoes using machine vision system and precision chemical application[C]. An ASAE Meeting Presentation, 1997,3093: 1～14.
[13] Dohi M, Fujiura T, Nakao S, et al. Robot and its application weed control in hill Space. Journal of the Japanese Society of Agriculture Machinery[J]. 1993, 55(6): 77～84.
[14] Jame H Everitt. Distinguishing brush and weeds on rangelands using video remote sensing[J]. Weed Technology, 1992, 64(1): 913～921.
[15] 贾云得．机器视觉[M]．北京：科学出版社，2000．
[16] 马颂德，张正友．计算机视觉[M]．北京：科学出版社，1999．
[17] 章毓晋．图像工程(上册)[M]．北京：清华大学出版社，2000．
[18] 方如明，蔡健荣，许俐．计算机图像处理技术及其在农业工程中的应用[M]．北京：清华大学出版社，1999．
[19] 蔡自兴，徐光佑．人工智能及其应用[M]．北京：清华大学出版社，1996，
[20] 李介谷．计算机视觉的理论和实践[M]．上海：上海交通大学出版社，1999．
[21] 何东健，张海亮等，农业自动化领域中计算机视觉技术的应用[J]．农业工程学报，2002，18(2)：171～175。
[22] 应义斌，饶秀勤．机器视觉技术在农产品品质自动识别中的应用[J]．农业工程学报，2000，16(1)：4～17
[23] Franz E, Gebhardt M, et al. The use of local spectral properties of leaves as an aid for identifying weed seedings in digital images[J]. Transactions of the ASAE. 1991, 34(2):682～687
[24] Franz E. Identifying weed seedings by computer vision using leaf shape and spectral information[D]. Unpub. Ph.D.diss, University of Missouri, Columbia, 1999.
[25] N Zhang, C Chaisattapagon. et al. Effective criteria for weed identification in wheat fields using machine vision[J]. Transactions of the ASAE, 1995, 38(3):965～975.
[26] Biller, R H. Reduced input of herbicides by use of optoelectronic sensor[J]. Agric.Eng. Res, 1998, 41(4):357～362.
[27] Franz E, Gebhardt, M. et al. Shape description of completely visible and partially occluded leaves for identifying plants in digital images[J]. Transactions of the ASAE, 1991, 34(2):673～681.
[28] Sarkar, N, R Wolfe. Feature extraction techniques for sorting tomatoes by computer vision[J]. Transctions of the ASAE, 1985, 28(3):970～979.
[29] Zahn, C T, R Z Roskies. Fourier descriptors for plane closed curves[J]. IEEE Transactions on Computers, 1972, 21(3) 269～281.
[30] D M, Woebbecke, G E Meyer, et al. Color indices for weed identification under various soil, residue, and lighting conditions[J]. Transactions of the ASAE, 1995, 38(1):259～269
[31] Shearer, S A, R G holmes. Plant identification using color co-occurrence matrices[J]. Transations of the ASAE, 1990, 33(6): 2037～2044.
[32] Wyszecki,G, W S Stiles. Color Science, Concepts and Methods[M]. New York: John Wiley & Sons, 1982.
[33] Zhang, N, C Chaisattapagon. Effective criteria for weed identification in wheat fields using machine vision[J]. Transactions of the ASAE, 1995, 38(3):965～975.
[34] M S, E1-Faki, N Zhang, et al. Factors affecting color-based weed detection[J]. Transactions of the ASAE, 2000, 43(4): 1001～1009.
[35] T F Burks, S S Shearer, R S Gates, et al. Backpropagation neural network design and evaluation for classifying weed species using color image texture[J]. Transactions of the ASAE, 2000, 43(4): 1029～1037.
[36] Hassouth,M H. Fundamentals of Artificial Neural Networks Cambridge[M]. Mass: The MIT Press, 1995, 227.
[37] Liu, K K. Neural networks inspect and grade apples[J]. Food Engineering, 1992,15(3):67～68.
[38] 吕朝辉．用BP神经网络进行秧苗图像分割[J]．农业工程学报，2001，17(2)：146～147．
[39] N,Wang, N Zhang, et al. Design of an optical weed sensor using plant spectical characteristics[J]. Transactions of the ASAE, 2001, 44(2):409～419.
[40] Felton, W L, K R McCloy. Spot spraying. Agric. Eng[J]. 1992, 73(6): 9～12.
[41] EI-Faki, M S, N Zhang, et al. Weed detection using color machine vision[N]. ASAE Paper, 1997, No 3117～3134.
[42] L Tian. Knowledge based machine vision system for out door plant identification [D]. University of California, Davis, CA. 1995.
[43] L Tian, D C Slaughter. Outdoor field machine vision identification of tomato
seedings for automated weed control[J]. Transactions of the ASAE, 1997, 40(6): 1761 1768.
[44] L Tian, D C Slaughter. Environmentally adaptive segmentation algorithm for outdoor image segmentation[J]. Computers and Electronics in Agriculture, 1998, 21(3):153～168.
[45] Steward B L, L F Tian. Real-time weed detection in outdoor field conditions[A]. In proc. SHE 3543, Precision Agriculture and Biological Quality[C], Bellingham, Wash:SPIE, 199, 266～278.
[46] Andreason, C, M Rudemo, et al. Assessment of weed density at an early stage by use of image processing[J]. Weed Research, 1997, 37(1): 5～18.
[47] Brivot, R, J A Marchant. Segmentation of plants and weeds for a precision crop protection robot using infrared images[J]. IEEE Proceedings on Vision, Image, and Signal Processing, 1996, 143(2):118～124.
[48] Cooke, L. Smart sprayer selects weeds for elimination[J]. Agricultural Research,1996, 44(4): 15.
[49] Critten, D L. Fourier based techniques for the identification of plants and weeds[J]. Journal of Agricultural Engineering Research, 1996, 64(2): 149～154.
[50] L Tang, L Tian, B Steward. Supervised color image segmentation by genetic algorithm for real-time weed sensing in outdoor lighting conditions[EB/OL], http://wwww.age.uiuc.edu/remote-sensing,1999-11-03.
[51] Andrey, P, P Tarroux. Unsupervised image segmentation using a distributed genetic algorithm[J]. Pattern Recognition, 1994, 27(5): 659～673.
[52] L Tang, L Tian, B Steward. GAHSI segmentation algorithm for outdoor image segmentation[J]. Transactions of the ASAE, 2000, 43(4): 1019～1027.
[53] L Tang, L Tian Texture-based weed classification using gabor wavelets and neuralnetwork for real-time selective herbicide applications[EB/OL], http://www.uiuc.edu/remote-sensing.2000-09-23.
[54] 纪寿文，王荣本，陈佳娟等．应用计算机图像处理技术识别玉米苗田间杂草的研究[J]．农业工程学报，2001，(17)154～156．
[55] H Yao, L Tian. Hyperspectral imaging system optimization and image processing[N]. A SAE Meeting Paper, 2001, No. 01-1105.
[56] 王润生．图像理解[M]．长沙：国防科技大学出版社，1997．
[57] Kenneth R, Castleamn. Digital Image Processing[M]. Prentice Hall, Inc, 1996,487～490.
[58] 赵振明．照明工程设计手册[S]，天津：天津科学技术出版社，1984．
[59] [美]David J Kruglinski著．Visual C++技术内幕(第四版)[M]．潘爱民，王国印译．北京：清华大学出版社，1998．
[60] [美]Kate Gregory著．Visual C++6.0开发使用手册[M]．前导工作室译．北京：机械工业出版社，1999．
[61] 王辉等．精通Visual C++6.0[M]．北京：电子工业出版社，1999．
[62] 周长发．精通Visual C++图像编程[M]，北京：电子工业出版社，2000．
[63] 田捷，沙飞，张新生．实用图像分析与处理技术[M]．北京：电子工业出版社，1994．
[64] 何东健，杨青等．实用图像处理技术[M]．西安：陕西科学技术出版社，1998．
[65] Fu K S, Mui J K. A survey on image segmentation[J]. Pattern Recog, 1981,13(2): 3～16.
[66] 李月景．图像识别技术及应用[M]．机械工业出版社，1983．
[67] Tarbell K A, Reid J F. Spatial and spectral characteristics of corn leaves collected using computer vision[J]. Transactions of the ASAE, 1991, 34(5): 2256～2263.
[68] Matas J, Marik R, Kitter J. Color-based object recognition under spectrally non-uniform illumination[J]. Image & Vision Compute, 1995, 13(9): 663～669.
[69] Woebbecke D M, A1-Faraj A, Meyer G E. Calibration of large field-of-view thermal and optical sensors for plant and soil measurements[J]. Transactions of the ASAE, 1994, 37(2): 669～677.
[70] Woebbecke D M, Meyer G E, Mortensen D A, et al. Shape features for identifying young weeds using image analysis[J]. Transactions of the ASAE, 1995, 38(1): 271～281.
[71] Huang L K, Wang M J. Image thresholding by minimizing the measures of fuzziness [J]. Pattren Recognition, 1995, 28(1): 41～51.
[72] 阮秋琦．数字图像处理学[M]．北京：电子工业出版社，2001，325～330．
[73] Franz E, Gebhardt M, Unklesbay K. Algorithms for extracting leaf boundary information from digital images of plant foliage[J]. Transactions of ASAE, 1995, 38(2):625～633.
[74] J Serra. Image Analysis and Mathematical Morphology[M]. New York: Academic Press, 1982.
[75] E R Dougherty. An Introduction to Morphological Image Processing[A]. SPIE Press[C]. Belling-ham, WA, 1992.
[76] 张思玉等．阔叶树面积求算的新方法[J]．八一农学院学报，1995，18(3)：96～99．
[77] 袁哲明，傅凌才．用扫描仪测定害虫食叶面积[J]．南京农业大学学报，1997，23(5)：472～473．
[78] Hanks, J E. Smart sprayer selects weeds for elimination[J]. Agricultural Reasearch, 1996, 44(4): 15.
[79] Rockwell, A D, P D Ayers. Variable rate sprayer development and evaluation[J]. Applied Engineering in Agriculture, 1994, 10(3):327～333.
[80] Shearer, S A, P T Jones. Selective application of postemergence herbicides using photoelectrics[J]. Transactions of the ASAE, 1991, 34(4): 1661～1666.
[81] Johnson, G A, D A. Mortensen.et al. A simulation of herbicide use based on weed spatial diatribution[J]. Weed Research, 1995, 35(3): 197～205.
[82] Marshall, E J P. Field-scale estimates of grass weed population in arable land[J].
Weed Reasearch, 1988, 28(3): 191～198.
[83] Meyer G E, T Mehta, M F Kocher, et al. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying[J]. Transactions of the ASAE, 1998,41(4): 1189～1197.
[84] 周孝宽．实用微机图象处理[M]．北京：北京航空航天大学出版社，1994，10
[85] 章毓晋．图像工程(下册)[M]．北京：清华大学出版社，2000．
[86] 何东健，杨青等．实用图像处理技术[M]．西安：陕西科学技术出版社，1998
[87] 崔屹．图像处理与分析一数学形态学方法及应用[M]．北京：科学出版社，2000
[88] 边肇棋，张学工等．模式识别(第二版)[M]．北京：清华大学出版社，1999
[89] Menges R M,Nixon P R,Richardson A J.Light reflectance and remote sensing of wees in agronomic and horticultural crops[J]. Weed Science, 1985,33:569～581
[90] 唐常青，吕宏伯等．数学形态学方法及其应用[M]．北京：科学出版社，1999
[91] Andrey P, Tarroux P. Unsupervised Image segmentation using a distributed genetic algorithm[J]. Pattern Recognition, 1994, 27(5): 659～673.
[92] Billings W D, Morris R J. Reflection of visible and infrared radiation from leaves of different ecological groups[J]. American Journal of Botany, 1951,38:327～331.
[93] BlackShow Robert E. Merits of a weed-sensing sprayer to control weeds in conservation fallow and cropping systems[J]. Weed Science, 1998, 46:120～122.
[94] Brown G K, Segerlind L J, Summit R. Near-infrared reflectance of bruised apples[J]. Transactions of the ASAE, 1974, 17(1): 17～19.
[95] Chang Y C, Reid J F. Characterization of a color vision system[J]. Transactions of the ASAE, 1996, 39(1): 263～273.
[96] Choi K, Lee G, Hah Y J, et al. Tomato maturity evaluation using color image analysis[J]. Transactions of the ASAE, 1995, 38(1):171～176.
[97] Cousans G. Machine vision for weed identification[M]. Informal weed Detection Workshop, Silsoe Research Institute, Bedford, UK. 1995.
[98] Davis L S, Jobs S A, Aggarwal J K. Texture analysis using generalized co-ocurrence matrices[J]. IEEE Trans, 1979(1): 251～259.
[99] Fu K S, Mui J K. A survey on image segmentation[J]. Pattern Recog,1981(13):3～16.
[100] Gates D M, Kcegan H J, Schleter J C, et al. Spectral properties of plants[J]. Applied Optices, 1965, 4(1):11～20.
[101] Liao K, Paulsen Marvin R, Reid J F. Real-Time detection of color and surface defects of maize kernels using machine vision[J]. Journal of Agricultural Engineering Research, 1994, 59:263～271.
[102] Tillett N D, Hague T, Marchant J A. A robotic system for plant-scale husbandry[J]. Journal of Agricutural Engineering Research, 1998, 69:169～178.
[103] Tillett R D. Image analysis for agricultural process: a review of potential opportunities[J]. Journal of Agricutural Engineering Research, 1991, (50): 247～258.
[2] 农业部全国植保总站．中国农田杂草图册(第一集)[M]．北京：化学工业出版，1988．
[3] 马承忠，刘滨，许捷．农田杂草识别及防除—幼苗和成株简明图鉴[S]．北京：中国农业出版社，1999．
[4] 吴汉章等，除草剂药害图谱[S]．江苏：江苏科学技术出版社，1995．
[5] 李亚卿，高丁石，陈红旗等．旱田杂草及其化学防除[M]．北京：中国农业科技出版社，1999．
[6] 黄建中．农田杂草抗药性：产生机理、测定技术、综合治理[M]．北京：中国农业科技出版社，1995．
[7] 李光熙．提高科技含量，迈向新世纪的除草剂开发、研制与应用[J]．杂草科学，1998，17(1)：2～3．
[8] 蒋正荣．计算机杂草识别的实现及应用[J]．杂草科学，1999，24(4)：2～5．
[9] 蒋正荣．计算机杂草识别技术的研究现状[J]．上海环境科学，1999，18(4)：481～483．
[10] Guyer, D E et al. Machine vision and image processing for plant identification[J]. Transactions of the ASAE, 1988, 29(6):1500～1507.
[11] Blackshow, Robert E. Merits of a weed-sensing spayer to control weeds in conservation fallow and cropping Systems[J]. Weed Science, 1998, 46(3): 120～122.
[12] Sub Lee Won. Robotic weed control system fortomatoes using machine vision system and precision chemical application[C]. An ASAE Meeting Presentation, 1997,3093: 1～14.
[13] Dohi M, Fujiura T, Nakao S, et al. Robot and its application weed control in hill Space. Journal of the Japanese Society of Agriculture Machinery[J]. 1993, 55(6): 77～84.
[14] Jame H Everitt. Distinguishing brush and weeds on rangelands using video remote sensing[J]. Weed Technology, 1992, 64(1): 913～921.
[15] 贾云得．机器视觉[M]．北京：科学出版社，2000．
[16] 马颂德，张正友．计算机视觉[M]．北京：科学出版社，1999．
[17] 章毓晋．图像工程(上册)[M]．北京：清华大学出版社，2000．
[18] 方如明，蔡健荣，许俐．计算机图像处理技术及其在农业工程中的应用[M]．北京：清华大学出版社，1999．
[19] 蔡自兴，徐光佑．人工智能及其应用[M]．北京：清华大学出版社，1996，
[20] 李介谷．计算机视觉的理论和实践[M]．上海：上海交通大学出版社，1999．
[21] 何东健，张海亮等，农业自动化领域中计算机视觉技术的应用[J]．农业工程学报，2002，18(2)：171～175。
[22] 应义斌，饶秀勤．机器视觉技术在农产品品质自动识别中的应用[J]．农业工程学报，2000，16(1)：4～17
[23] Franz E, Gebhardt M, et al. The use of local spectral properties of leaves as an aid for identifying weed seedings in digital images[J]. Transactions of the ASAE. 1991, 34(2):682～687
[24] Franz E. Identifying weed seedings by computer vision using leaf shape and spectral information[D]. Unpub. Ph.D.diss, University of Missouri, Columbia, 1999.
[25] N Zhang, C Chaisattapagon. et al. Effective criteria for weed identification in wheat fields using machine vision[J]. Transactions of the ASAE, 1995, 38(3):965～975.
[26] Biller, R H. Reduced input of herbicides by use of optoelectronic sensor[J]. Agric.Eng. Res, 1998, 41(4):357～362.
[27] Franz E, Gebhardt, M. et al. Shape description of completely visible and partially occluded leaves for identifying plants in digital images[J]. Transactions of the ASAE, 1991, 34(2):673～681.
[28] Sarkar, N, R Wolfe. Feature extraction techniques for sorting tomatoes by computer vision[J]. Transctions of the ASAE, 1985, 28(3):970～979.
[29] Zahn, C T, R Z Roskies. Fourier descriptors for plane closed curves[J]. IEEE Transactions on Computers, 1972, 21(3) 269～281.
[30] D M, Woebbecke, G E Meyer, et al. Color indices for weed identification under various soil, residue, and lighting conditions[J]. Transactions of the ASAE, 1995, 38(1):259～269
[31] Shearer, S A, R G holmes. Plant identification using color co-occurrence matrices[J]. Transations of the ASAE, 1990, 33(6): 2037～2044.
[32] Wyszecki,G, W S Stiles. Color Science, Concepts and Methods[M]. New York: John Wiley & Sons, 1982.
[33] Zhang, N, C Chaisattapagon. Effective criteria for weed identification in wheat fields using machine vision[J]. Transactions of the ASAE, 1995, 38(3):965～975.
[34] M S, E1-Faki, N Zhang, et al. Factors affecting color-based weed detection[J]. Transactions of the ASAE, 2000, 43(4): 1001～1009.
[35] T F Burks, S S Shearer, R S Gates, et al. Backpropagation neural network design and evaluation for classifying weed species using color image texture[J]. Transactions of the ASAE, 2000, 43(4): 1029～1037.
[36] Hassouth,M H. Fundamentals of Artificial Neural Networks Cambridge[M]. Mass: The MIT Press, 1995, 227.
[37] Liu, K K. Neural networks inspect and grade apples[J]. Food Engineering, 1992,15(3):67～68.
[38] 吕朝辉．用BP神经网络进行秧苗图像分割[J]．农业工程学报，2001，17(2)：146～147．
[39] N,Wang, N Zhang, et al. Design of an optical weed sensor using plant spectical characteristics[J]. Transactions of the ASAE, 2001, 44(2):409～419.
[40] Felton, W L, K R McCloy. Spot spraying. Agric. Eng[J]. 1992, 73(6): 9～12.
[41] EI-Faki, M S, N Zhang, et al. Weed detection using color machine vision[N]. ASAE Paper, 1997, No 3117～3134.
[42] L Tian. Knowledge based machine vision system for out door plant identification [D]. University of California, Davis, CA. 1995.
[43] L Tian, D C Slaughter. Outdoor field machine vision identification of tomato
seedings for automated weed control[J]. Transactions of the ASAE, 1997, 40(6): 1761 1768.
[44] L Tian, D C Slaughter. Environmentally adaptive segmentation algorithm for outdoor image segmentation[J]. Computers and Electronics in Agriculture, 1998, 21(3):153～168.
[45] Steward B L, L F Tian. Real-time weed detection in outdoor field conditions[A]. In proc. SHE 3543, Precision Agriculture and Biological Quality[C], Bellingham, Wash:SPIE, 199, 266～278.
[46] Andreason, C, M Rudemo, et al. Assessment of weed density at an early stage by use of image processing[J]. Weed Research, 1997, 37(1): 5～18.
[47] Brivot, R, J A Marchant. Segmentation of plants and weeds for a precision crop protection robot using infrared images[J]. IEEE Proceedings on Vision, Image, and Signal Processing, 1996, 143(2):118～124.
[48] Cooke, L. Smart sprayer selects weeds for elimination[J]. Agricultural Research,1996, 44(4): 15.
[49] Critten, D L. Fourier based techniques for the identification of plants and weeds[J]. Journal of Agricultural Engineering Research, 1996, 64(2): 149～154.
[50] L Tang, L Tian, B Steward. Supervised color image segmentation by genetic algorithm for real-time weed sensing in outdoor lighting conditions[EB/OL], http://wwww.age.uiuc.edu/remote-sensing,1999-11-03.
[51] Andrey, P, P Tarroux. Unsupervised image segmentation using a distributed genetic algorithm[J]. Pattern Recognition, 1994, 27(5): 659～673.
[52] L Tang, L Tian, B Steward. GAHSI segmentation algorithm for outdoor image segmentation[J]. Transactions of the ASAE, 2000, 43(4): 1019～1027.
[53] L Tang, L Tian Texture-based weed classification using gabor wavelets and neuralnetwork for real-time selective herbicide applications[EB/OL], http://www.uiuc.edu/remote-sensing.2000-09-23.
[54] 纪寿文，王荣本，陈佳娟等．应用计算机图像处理技术识别玉米苗田间杂草的研究[J]．农业工程学报，2001，(17)154～156．
[55] H Yao, L Tian. Hyperspectral imaging system optimization and image processing[N]. A SAE Meeting Paper, 2001, No. 01-1105.
[56] 王润生．图像理解[M]．长沙：国防科技大学出版社，1997．
[57] Kenneth R, Castleamn. Digital Image Processing[M]. Prentice Hall, Inc, 1996,487～490.
[58] 赵振明．照明工程设计手册[S]，天津：天津科学技术出版社，1984．
[59] [美]David J Kruglinski著．Visual C++技术内幕(第四版)[M]．潘爱民，王国印译．北京：清华大学出版社，1998．
[60] [美]Kate Gregory著．Visual C++6.0开发使用手册[M]．前导工作室译．北京：机械工业出版社，1999．
[61] 王辉等．精通Visual C++6.0[M]．北京：电子工业出版社，1999．
[62] 周长发．精通Visual C++图像编程[M]，北京：电子工业出版社，2000．
[63] 田捷，沙飞，张新生．实用图像分析与处理技术[M]．北京：电子工业出版社，1994．
[64] 何东健，杨青等．实用图像处理技术[M]．西安：陕西科学技术出版社，1998．
[65] Fu K S, Mui J K. A survey on image segmentation[J]. Pattern Recog, 1981,13(2): 3～16.
[66] 李月景．图像识别技术及应用[M]．机械工业出版社，1983．
[67] Tarbell K A, Reid J F. Spatial and spectral characteristics of corn leaves collected using computer vision[J]. Transactions of the ASAE, 1991, 34(5): 2256～2263.
[68] Matas J, Marik R, Kitter J. Color-based object recognition under spectrally non-uniform illumination[J]. Image & Vision Compute, 1995, 13(9): 663～669.
[69] Woebbecke D M, A1-Faraj A, Meyer G E. Calibration of large field-of-view thermal and optical sensors for plant and soil measurements[J]. Transactions of the ASAE, 1994, 37(2): 669～677.
[70] Woebbecke D M, Meyer G E, Mortensen D A, et al. Shape features for identifying young weeds using image analysis[J]. Transactions of the ASAE, 1995, 38(1): 271～281.
[71] Huang L K, Wang M J. Image thresholding by minimizing the measures of fuzziness [J]. Pattren Recognition, 1995, 28(1): 41～51.
[72] 阮秋琦．数字图像处理学[M]．北京：电子工业出版社，2001，325～330．
[73] Franz E, Gebhardt M, Unklesbay K. Algorithms for extracting leaf boundary information from digital images of plant foliage[J]. Transactions of ASAE, 1995, 38(2):625～633.
[74] J Serra. Image Analysis and Mathematical Morphology[M]. New York: Academic Press, 1982.
[75] E R Dougherty. An Introduction to Morphological Image Processing[A]. SPIE Press[C]. Belling-ham, WA, 1992.
[76] 张思玉等．阔叶树面积求算的新方法[J]．八一农学院学报，1995，18(3)：96～99．
[77] 袁哲明，傅凌才．用扫描仪测定害虫食叶面积[J]．南京农业大学学报，1997，23(5)：472～473．
[78] Hanks, J E. Smart sprayer selects weeds for elimination[J]. Agricultural Reasearch, 1996, 44(4): 15.
[79] Rockwell, A D, P D Ayers. Variable rate sprayer development and evaluation[J]. Applied Engineering in Agriculture, 1994, 10(3):327～333.
[80] Shearer, S A, P T Jones. Selective application of postemergence herbicides using photoelectrics[J]. Transactions of the ASAE, 1991, 34(4): 1661～1666.
[81] Johnson, G A, D A. Mortensen.et al. A simulation of herbicide use based on weed spatial diatribution[J]. Weed Research, 1995, 35(3): 197～205.
[82] Marshall, E J P. Field-scale estimates of grass weed population in arable land[J].
Weed Reasearch, 1988, 28(3): 191～198.
[83] Meyer G E, T Mehta, M F Kocher, et al. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying[J]. Transactions of the ASAE, 1998,41(4): 1189～1197.
[84] 周孝宽．实用微机图象处理[M]．北京：北京航空航天大学出版社，1994，10
[85] 章毓晋．图像工程(下册)[M]．北京：清华大学出版社，2000．
[86] 何东健，杨青等．实用图像处理技术[M]．西安：陕西科学技术出版社，1998
[87] 崔屹．图像处理与分析一数学形态学方法及应用[M]．北京：科学出版社，2000
[88] 边肇棋，张学工等．模式识别(第二版)[M]．北京：清华大学出版社，1999
[89] Menges R M,Nixon P R,Richardson A J.Light reflectance and remote sensing of wees in agronomic and horticultural crops[J]. Weed Science, 1985,33:569～581
[90] 唐常青，吕宏伯等．数学形态学方法及其应用[M]．北京：科学出版社，1999
[91] Andrey P, Tarroux P. Unsupervised Image segmentation using a distributed genetic algorithm[J]. Pattern Recognition, 1994, 27(5): 659～673.
[92] Billings W D, Morris R J. Reflection of visible and infrared radiation from leaves of different ecological groups[J]. American Journal of Botany, 1951,38:327～331.
[93] BlackShow Robert E. Merits of a weed-sensing sprayer to control weeds in conservation fallow and cropping systems[J]. Weed Science, 1998, 46:120～122.
[94] Brown G K, Segerlind L J, Summit R. Near-infrared reflectance of bruised apples[J]. Transactions of the ASAE, 1974, 17(1): 17～19.
[95] Chang Y C, Reid J F. Characterization of a color vision system[J]. Transactions of the ASAE, 1996, 39(1): 263～273.
[96] Choi K, Lee G, Hah Y J, et al. Tomato maturity evaluation using color image analysis[J]. Transactions of the ASAE, 1995, 38(1):171～176.
[97] Cousans G. Machine vision for weed identification[M]. Informal weed Detection Workshop, Silsoe Research Institute, Bedford, UK. 1995.
[98] Davis L S, Jobs S A, Aggarwal J K. Texture analysis using generalized co-ocurrence matrices[J]. IEEE Trans, 1979(1): 251～259.
[99] Fu K S, Mui J K. A survey on image segmentation[J]. Pattern Recog,1981(13):3～16.
[100] Gates D M, Kcegan H J, Schleter J C, et al. Spectral properties of plants[J]. Applied Optices, 1965, 4(1):11～20.
[101] Liao K, Paulsen Marvin R, Reid J F. Real-Time detection of color and surface defects of maize kernels using machine vision[J]. Journal of Agricultural Engineering Research, 1994, 59:263～271.
[102] Tillett N D, Hague T, Marchant J A. A robotic system for plant-scale husbandry[J]. Journal of Agricutural Engineering Research, 1998, 69:169～178.
[103] Tillett R D. Image analysis for agricultural process: a review of potential opportunities[J]. Journal of Agricutural Engineering Research, 1991, (50): 247～258.