摘要
肉牛业在中国的出现是农村改革开放成功的标志。随着人民生活水平的提高,肉牛业在农业生产和国民经济中的地位显得越来越重要,自动化和产业化是肉牛业的必然趋势。研究针对肉牛体型参数人工测量效率低,而且测量精度不高,测量结果易受测量者技术水平、疲劳程度和测量仪器本身精度的制约等问题,应用计算机视觉技术进行肉牛主要体型参数的测量,并基于Web对图像信息进行管理。主要研究内容如下:
(1)根据研究性质和要求,分析了影响系统性能的因素,综合分析性能价格比的基础上,组成了计算机视觉系统。选择合适的摄像角度,在自然环境下获取肉牛图像。
(2)运用参考物标记法对体型参数进行测量,使得图像获取过程不受摄像焦距的影响,使图像大小和清晰度得以改善,给测量带来了很大方便。
(3)利用判别分析法确定阈值,色度能有效的识别肉牛和背景,识别正确率在98%以上,且对土壤、光照强度变化、建筑物阴影的敏感性小。
(4)以区域面积为依据,去除测量对象以外的无用信息、噪声信息。在色度二值化后,无需通过其他去噪方法,也可以准确的去除无用信息,从而大大提高了目标识别的效率。
(5)针对获取的二维图像在测量时,有些参数无法直接测量的情况,本文提出通过近椭圆计算和人工神经网络数据拟合法,通过胸宽和胸深实现了对胸围的计算。
(6)在参数测量中,通过分析肉牛形体特征,通过局部最大曲率以及考察点相对坐标夹角变化能够较为准确的检测测量点。
(7)基于Visual C++6.0开发了计算机视觉肉牛体型参数测量软件,能够实现重要体型参数的测量和主要体尺指数的计算,其基本的图像处理功能有较好的通用性。
(8)以B/S为模型设计了的图像信息管理系统,能够实现图像信息的常规管理(图像信息的添加、删除、更新和查询),局域网测试结果表明,系统有良好的运行稳定性。
The appearance of cattle-raising industry in china is the symbol of the success of revolution and opening. With the improvement of people's living situation, the status of cattle-raising industry is becoming more and more important hi agricultural manufacture and national economy. Industrialization and automation are the inevitable trend. Aim at the problems of manual measuring of cattle's shape parameters: low efficiency, low precision, the results easily effected by the technique level and fatigue level of worker, and the precision of measure tools, the research used computer vision technology to measure the main shape parameters of cattle. And the research setup a information management system to manage image information. The main contents and results of the dissertation as follows:
(1) According to the property and demand of the study, the factors affecting system performance were analyzed. On the basis of considering the ratio of performance and price, hardwares were chosen to setup the computer vision system. Under the natural environment, cattle images were acquired.
(2) Using reference object demarcation method to measure the shape parameters, this made the process of image acquiring avoid the effection of camera's focus. And it can eveluate the image's size and definition, at the same time it mad the measurment easy.
(3) Hue can identify cattle from backgroud through Ostu's thresholding, the correctness is over 98%. And it's insensitive to earth, the illumiation intensity and shadow.
(4) Basing of the area, can delete the area which is useless to measurment and noise. After binary based on hue, just use this method can delete useless information, then improved the efficiency of identifying.
(5) Aimed at some parameters cann't measure directly from the 2-dimension image, the paper indicate that can through near-ellipse calculation and using BP neural network to calculation the chest circumference of cattle.
(6) In the process of measurment, when measure the shape parameter, can calculate the max local-curvature, and analysis the angle from the edge-point to coordinate system to find the beginning point and stopping point of measure.
(7) Software system for cattle's shape parameter measurment by computer vision were developed by using VC++6.0. It can measure the main shape parameters and main index from cattle image. The function of basic image processing can used in other
objects and fields.
(8) Designed and developed the information management system for cattle's image based on the B/S modle. It can complete the basic function of information management(insert image information, delete image information, update and query image information). The system is running on local intranet to test it's performance, and it works well.
引文
[1] 昝林森.牛生产学.中国农业出版社,1999
[2] 邱怀.牛生产学.中国农业出版社,1995
[3] 冯仰廉.实用养牛学(第四版).科学出版社,1995
[4] 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.农业工程学报,2002,18(2):171-175
[5] 宁纪锋,龙满生,何东健.农业领域中的计算机视觉研究.计算机与农业,2001,1:1-3
[6] 何东健,杨青,薛少平.农业机器人视觉系统及识别技术研究.中国农业大学学报,1996(第一卷,增刊),38—43
[7] 应义斌,景寒松等.黄花梨果形的机器视觉识别方法研究.农业工程学报,1999,15(1):192-196
[8] 应义斌,铙秀勤等.机器视觉技术在农产品品质自动识别中的应用(Ⅰ).农业工程学报,2000,16(1):103-108
[9] 应义斌,铙秀勤等.机器视觉技术在农产品品质自动识别中的应用.农业工程学报,2000,16(3):4-8
[10] 陈顺三,汪懋华,谭玫芳.奶牛体型图像信息系统研究.农业工程学报,1996,12(3):149-152
[11] 许志详,卢宏,沈剑.摄像机标定机器误差分析.自动化学报,1993,19(1):114-117
[12] 钟瑞永,李芳繁.使用双眼立体机器视觉定位果树.农业工程学报,1993,39(4):74-87
[13] 何东健.计算机视觉果实分级技术的研究.博士学位论文.西北农业大学.1998
[14] 龙满生.玉米苗期杂草识别的机器视觉研究.硕士学位论文.西北农林科技大学.2002
[15] 宁纪锋.玉米品种的计算机视觉识别研究.硕士学位论文.西北农林科技大学.2002
[16] 耿楠,党革荣.判别分析法确定最佳阈值的快速算法.西北农林科技大学学报,2001,29(6):119-121
[17] 耿楠,何东健.小麦生长信息计算机视觉检测技术研究.农业工程学报,2001,17(1):136-139
[18] 何东健,杨青等.实用图像处理技术.西安:陕西科学技术出版社.1998
[19] 周孝宽.实用微机图像处理.北京:北京航空航天大学出版社.1994.10
[20] 贾云得.机器视觉.北京:科学出版社.2000
[21] 何斌,马天予等.Visual C++数字图像处理.北京:人民邮电出版社.2001
[22] 田捷,沙飞,张新生.实验图像分析和处理技术.北京:电子工业出版社.1994
[23] 吕凤军.数字图像处理入门——做一个自己得Photoshop.北京:清华大学出版社.1999
[24] 章毓晋.图像工程(上册)——图像处理和计算机视觉.北京:清华大学出版社.2000
[25] 边肇旗,张学工等.模式识别(第二版).北京:清华大学出版社.1999
[26] 崔屹.图像处理和分析——数学形态学方法和应用.北京:科学出版社.2000
[27] 章毓晋.图像工程(下册)——图像处理和计算机视觉.北京:清华大学出版社.2000
[28] 王厚大.一种计算任意封闭形状面积的方法.南京邮电学院学报,1997,17(4):83-85
[29] 徐贵力,毛罕平等.基于计算机视觉技术参考物法测量叶片面积,农业工程学报,2002,18(1):154-157
[30] 汪萍,侯慕英.机械优化设计.北京:中国地质大学出版社.1990
[31] 任金昌,赵荣椿.一种有效的平面曲线关键点检测新方法.电子学报,2002,30.5
[32] 焦李成.神经网络系统理论.西安:西安电子科技大学出版社.1991
[33] 丛爽.面向MATIAB工具箱的神经网络理论与应用.合肥:中国科学技术大学出版社.1998
[34] 焦李成.神经网络的应用与实现.西安:西安电子科技大学出版社.1991
[35] 胡上序,程翼宇.人工神经元计算导论.北京:科学出版社.1994
[36] [美]David J Kruglinski.Visual C++技术内幕(第四版).潘爱民,王国印译.北京:清华大学出版社.1998
[37] [美]Kate Gregory.Visual C++6.0 开发使用手册.前导工作室译.北京:机械工业出版社.1999
[38] 周长发.精通Visual C++图像编程.北京:电子工业出版社.2000
[39] 王晖等.精通Visual C++6.0.北京:电子工业出版社.1999
[40] 刘冬杰,廖春盛.基于WWW的交互式远程教学系统的设计.计算机应
用增刊,1999(10).第四卷
[41] 欧翔.基于INTERNET/INTRANET中小型企业管理信息系统的研究与开发.中国农业大学硕士论文.2000.3
[42] 侯宗浩.集成C/S、B/S结构的物资采供系统的研究.西安理工大学硕士论文.2000.3
[43] 庄卫华.网络环境下分布式数据管理模式的研究及实现.计算机工程与应用.2000(10):114-118
[44] 范三龙.基于INTERNET的数据驱动的信息发布系统.西安交通大学硕士毕业论文.2001
[45] 杨振刚.基于Web的作物图像信息管理系统的研究.西北农林科技大学硕士毕业论文.2001.6
[46] 王国荣.Active Server Page&Web数据库.北京:人民邮电出版社.1999
[47] 林风,李维章.动态网站设计捷径——ASP.陕西:西安电子科技大学出版社.1999.11
[48] 伍华聪.ASP与网站开发实战.北京:科学出版社.2001
[49] 萨师煊,王珊.数据库系统概论(第三版).北京:高等教育出版社.2000.2
[50] 李劲.精通ASP数据库程序设计.北京:科学出版社.2001.2
[51] 廖信彦.ASP应用经典.北京:中国铁道出版社.2000.9
[52] 耿冲.SQL Server 2000数据库管理.北京:机械工业出版社.2001.7
[53] 高盈发.数据库原理和应用.陕西:西安电子科技大学出版社.1998.6
[54] 郑成增.基于Web的数据库技术研究.电脑技术信息.2000.3
[55] 施伯乐等.关系数据库的理论及应用.郑州:河南科学技术出版社.1989
[56] 王珊,陈红.数据库系统原理教程.北京:清华大学出版社.1998
[57] 裴有福.Web技术大全.北京:中国水利水电出版社.1998
[58] 李湘江.基于Web的网络编程技术.计算机时代.2001.11:1-4
[59] 江晓平等.ASP网络开发指南.北京:人民邮电出版社.199.4
[60] 雷光复.面向对象的新一代数据库系统.北京:北京希望电子出版社.2000.1
[61] Ahmad I S. Reid J F. Evaluation of color representations for maize image. Journal of Agricultural Engineering Research, 1996,63:185-196
[62] Andrey P, Tarroux P. Unsupervised image segmentation using a distributed genetic algorithm. Pattern Recognition, 1994,27(5): 659-673
[63] B Wang, et al. A multi-media presentation system on Web-Dynamic homepage approach. IEICE Trans. Inf & Syst. 1999. 4:E82(4): 729-735
[64] Castleman K R. Digital Image Processing. Prentice Hall, Inc. 1996
[65] Cheng, Y. , Liu, K. et al. A novel feature extraction method for image recognition based on similar discrimination function (SDF). Pattern Recognition. 1993, Vol. 26(1) : 115-125
[66] Castleman K R. Digital Image Processing.北京:清华大学出版社. 1998 (Prentice Hall, Inc. 授权影印出版)
[67] Choi K, Lee G, Han Y J et al. Tomato maturity evaluation using color image analysis. Transactions of the ASAE, 1995,38(1) : 171-176
[68] Ding K, R. V. Morey. Corn quality evaluation with computer vision. ASAE Paper NO. 90-3532. St Joseph, MI: ASAE
[69] Ding K, Gunasekaran S. Shape feature extraction and classification of food material using computer vision. Transactions of ASAE, 1994,37(5) : 1537-1545
[70] D. Wang, F. E. Doewll, R . E. Lacey. Single wheat kernel color classification using neural network. Transactions of The ASAE, 1999, Vol. 40(1) : 233-240
[71] D. E. Guyer, G. E. Miles et al. Application of machine vision to shape analysis in leaf and plant identification. American Society of Agriculture Engineers, 1993,36(1) : 163-171
[72] Douglas Hydo. Web-Based Management-The new Paradigm for Network Management. http : //www. 3com. com/technology/tech-net/white-papers. 1998
[73] Franz E, Gebhardt M R, Unklesbay K B. Shape discrimination if completely visible and partially occluded leaves for identifying plants in digital images. Transactions of the ASAE, 1991,34(2) : 673-681
[74] Franz E, Gebhardt M R, Unklesbay K B. The use of local spectral properties of leaves as an aid for identifying weed seedlings in digital images. Transactions of the ASAE, 1991,34(2) : 682-687
[75] Fuchsia K. A Neural Network for Visual Pattern Recognition, Neural Networks, edited by Clifford Lau, IEEE Press, 1992:222-232
[76] Fu K S, Mui J K. A survey on image segmentation. Pattern Recog, 1981, 13: 3-16
[77] Guyer D E, Miles G. E, Gaultney L D, et al. Application of machine vision shape analysis in leaf and plant identification. Transactions of the ASAE,
1993,36(1) : 163-171
[78] Guyer D E, Miles G. E, Schreober M M, et al. Machine vision and image processing for plant identification. Transactions of the ASAE, 1993,36(1) : 163-171
[79] Giles D K, Slaughter D C. Precision band spraying with machine-vision guidance and adjustable fan nozzles [J]. Trans of the ASAE, 1997, 40(1) : 29-36
[80] http://www. jsai.or.jp/english/AGMain. html
[81] Kulpa Z. Area and Perimeter measurements of blobs in discrete binary pictures. Computer graphics and Image Processing, 1977,6:434-451
[82] Liao K, Paulsen M R, Reid J F, et al. Corn kernel breakage classification by machine vision using a neural network classifier [J]. Trans of the ASAE, 1993,36(6) : 1949-1952
[83] Ling P P, Searcy S W. Feature extraction for a machine-vision-based shrimp deheader [J]. Trans of the ASAE, 1991,34(6) : 2631-2637
[84] Mike Gunderloy Joseph L. Jorden 著. SQL Server 2000 从入门到精通,北 京:北京天竺颖华印刷厂, 2001. 3
[85] Miller B K, M J Cooper, A G Berlage, et al. Image processing for stress cracks in corn kernels. Trans of the ASAE, 1987,30(1) : 266-271
[86] Milan Sonka, Vaclav Hlavac, Roger Boyle, et al. Image Processing, Analysis, and Machine Vision (Second Edition). Brooks/Cole, a division of Thomson Asia Pte Led, 1993
[87] Miller B K, Delwiche M J. A color vision system for peach grading. Transactions of the ASAE, 1989,32(4) : 1484-1490
[88] Miller B K, Delwiche M J. Peach defect detection with machine vision. Transactions of the ASAE, 1991,34(6) : 2588-2597
[89] Nakatani, M. T. Nanseki and T. Kouno. Development of Image Database of Resource Crops on Hyper-Card and WWW. Agr. Info. Res. 5(2) : 69-83
[90] Panigrahi S, Misra M. Background segmentation and dimensional measurement of corn germplasm. Trans of the ASAE, 1995,38(1) : 291-297
[91] Pitas, I. and Venetsanopoulos, A. N. Morphological shape representation. Pattern Recognition, 1992, Vol. 25(6) : 555-565
[92] Powell, M. J. D., An Efficient method for finding the minimum of a function of several variables without calculation derivatives. 《Computer
Journal》. 1964, Vol. 7:155-162
[93] Raghu Ramakrishnam. DATABASE MANAGEMENT SYSTEM (影印本).北京:清华 大学出版社. 2000. 3
[94] Rehkugler G E, Throop J A. Apple sorting with machine vision. Transactions of the ASAE, 1986,29(5) : 1388-1396
[95] Sarkar N, Wolfe R R. Computer vision based system for quality separation of fresh market tomatoes [J]. Trans of the ASAE, 1985b, 28(5) : 1714-1718
[96] Schafer, A. and Teyssen, T. Size, shape and orientation of grains in sands and sandstones: image analysis applied to rock thin sections. Sedimentary Geology, 1987,52:251-271
[97] Slaughter DC, Harrell R C. Discriminating fruit for robotic harvest using color in natural outdoor scenes [J]. Trans of the ASAE, 1989,32(2) : 757-763
[98] S. Ninomiya, et al. Development of WWW image database system "lotus in Japan" . Agr. Info. Res. 3(2) : 109-125
[99] Tao Y. Closed-loop search method for on-line automatic calibrations of multi-camera inspection systems. Transactions of the ASAE, 1995, 38(5) : 1555-1561
[100] Tang L, Tian L, Steward B L. Color Image Segmentation With Genetic Algorithm for In-Field Weed Sensing. Transactions of the ASAE, 2000,43(4) : 1019-1027
[101] Tian L, Slaughter D C. Environmentally adaptive segmentation algorithm for outdoor image segmentation. Computer &. Electronics in Agric, 1998,21(3) : 153-168
[102] Tarbell K A, Reid J F. Spatial and spectral characteristics of corn leaves collected using computer vision. Transactions of the ASAE, 1991,34(5) : 2256-2263
[103] Tao Y, Heinemann P H, Varghese Z, et al. Machine vision for color inspection of potatoes and apples. Transactions of the ASAE, 1995, 38(5) : 1555-1561
[104] Tao Y. Spherial transform of fruit images for on-line defect extraction of mass objects. Opt. Eng. 1996, 35(2) : 344-350
[105] Tao Y, Wen Z. Item defect detection apparatus and method [J]. United States Patent Pending, 1998,09/046,270
[106] Tsukasa Kouno, et al. Visible Agriculture by FARMWEB, An Advanced Web-based Farming Database System. http://www. jsai. ro.jp/english/AGMain. html
[107] Woebbecke D M, AL-Faraj A, Meyer G E. Calibration of large field-of-view thermal and optical sensors for plant and soil measurements. Transactions of the ASAE, 1994,37(2) : 669-677
[108] Woebbecke D M, Meyer G E, Mortensen D A, Von Bargen K. Shape features for identifying young weeds using image analysis. Transactions of the ASAE, 1995,38(1) : 271-281
[109] Walter H, Koch W. Light reflectance characteristics of weed and crop leaves as effected by plant species and herbicides. In Proc. British Crop Protection Conference-Weeds. Brighton, East Sussex. 1980,243-250
[110] Y. C Chang, J.F.Reid. Characterization of Color Vision System. Transactions of the ASAE, 1996, Vol. 39 (1) : 263-273
[111] Young, I. T. Sampling density and quantitative microscopy. AQCH, 1988,10:269-275
[112] Yonekawa, S., Sakai, N., and Kitani, 0. Identification for idealized leaf types using simple dimensionless shape factors by image analysis. Trans of the ASAE, 1996,39(4) : 1525-1533
[113] Zhang Shuhai, Takahashi-T, et al. Studies on automation of work in orchards (Part 1) . Detection of apple by pattern recognition [J]. Journal of the Japanese Society of Agricultural Machinery, 1996, 58:1, 9-16
[114] Zayas I, Lai F S, Pomeranz Y. Discrimination between wheat classes and varieties by image analysis [J]. Cereal Chemistry, 1986,63(1) : 52-56
[115] Zayas I, Converse H, Steele J. Discrimination of whole from broken corn kernels with image analysis [J]. Trans of the ASAE, 1990,33(5) : 1642-1646