农田图像的统计迭代分割方法研究
|
摘要
传统农业工作方式强度高、效率低、较易发生农业事故,如农药中毒、皮肤晒伤病变等。农业机械自动导航的出现有效解决了这些问题,而导航过程中视觉方式的路径检测以其使用灵活、信息量丰富、不限定外部环境(即只需要找到农田或果园中预先存在的路径特征就可以,如垄、田间地头等)等优点成为导航中的主导方式。在视觉探测路径的过程中,图像分割是关键,本文在研究适合农田处理的统计图像处理算法的基础上,对农田图像进行了分割。此外农业机械自动导航的出现,也适应了精细农业发展的需要,起到环境保护的作用。
以往采用的农田分割算法不能很好的去除农田断垄、杂草、阴影及光照改变等噪声影响,使得对后续导航线提取算法要求很高,加上导航线算法计算过程复杂,如Hough变换等,使得整个农田处理过程鲁棒性下降。针对农田图像分割目的主要是检测大尺度作物行,将统计迭代算法Meanshift和支持向量机应用于农田图像分割,为了提高算法实时性分别将两种统计迭代算法和小波多分辨率分析相结合。为了给农田彩色模型的选取提供理论依据,从颜色混合角度出发分析了几个常用的模型。最后将农田图像分割中采用的各种典型分割算法和本文提出的基于小波多分辨率分解的快速Meanshift算法以及基于小波多分辨率分解的各种支持向量机算法进行了实验对比研究。
本文的主要研究成果如下：
1)基于农田结构特点,首次提出了在图像分割中只应用小波多分辨率分解的低分辨率图像。不仅保留了农田待检测信息,并有助于断垄、杂草、小的阴影等高频干扰的去除,还大大减少了算法程序运行时间。
2)提出了分块选种子点的快速Meanshift算法,并应用于农田图像分割。改进Meanshift算法具有良好的去除干扰的能力,作为统计迭代算法唯一的缺点就是执行速度慢。为了提高速度,达到实时导航要求,除了采用小波多分辨率分解外,还依据农田特点,选取具有明显特征的种子点,只对种子点进行该算法,节省了运行时间。由于农田结构整体的统一性,还可将农田图像沿垂直于行的方向分块,使每次迭代运算只在一块中进行,有效减少了每次迭代运算参与像素的数量,进一步减少了运行时间。改进Meanshift算法的应用有效克服的断垄、杂草或阴影的干扰。
3)依据农田结构提出了长方形有权重的均值计算模板。这种模板的应用充分考虑了农田作物行颜色空间分布的特点,在行方向上的像素点更具有和当前点相似的特性,这种模版的采用有效克服了断垄、行间杂草的影响。
4)提出了将图像均值和图像方差信息融合后代表农田图像特征,作为支持向量机的输入,使得行宽信息最大程度保留下来,有利于后续导航线的提取。
5)首次将支持向量机相关算法应用于农田图像分割,有效克服了农田图像中断垄、杂草、阴影、光照变化等干扰。
The traditional agriculture work is very tedious, low efficiency and occasionally dangerous, such as pesticide poisoning, sunburned skin or even worse. The emergency of agriculture navigation effectively resolves these problems. To detect path based on machine vision in automatic navigation is a main method, because of rich information, flexible use and not considered the circumstance (mainly based on the ridge, balk that is formed before in farmland and orchard). The image segmentation is the key factor in the vision detection of path. This paper mainly researches the statistic interation algorithm and its application in agriculture image segmentation. On the other hand, the auto navigation of agriculture vehicle meets the demand of the development of precision agriculture, and protects the circumstance.
The image segmentation algorithm that used in agriculture navigation before couldn't effectively remove the imfluence of broken ridge, weeds, shadow and illumination change. So the followed guidance line detection algorithm must resolve these problems, it would result in lower robust because of the complexicity of itself, such as Hough thansform. The purpose of agriculture image segmentation is to detect the crop row, so the statistic iteration algorithm Meanshift and Support Vector Machine was used in this paper. In order to save running time the two statistic iteration algorithm were integrated with wavelet multi resolution individually. The color models that usually used in agriculture image segmentation were discussed from the point of theory view. In the last some typical agriculture image segmentation algorithms were contrasted with the algorithm that used in this paper based on experiments.
The main innovation work of this thesis as follows:
1. Based on the structure features of agriculture field, gives a new idea that only used the lower resolution image. This not only could remain the information that would be detected, but also effectively removed the influence of broken ridge, weeds and shadows, and the running time was saved too.
2. Based on the former method and the features of farmland, this paper proposed a new fast Meanshift algorithm that divided the agriculture image into several pieces and run the Meanshift algorithm only on the seeds that selected from each pieces. Based on the wavelet multi resolution decomposion, the Meanshift algorithm remove the the influence of broken ridge, weeds and shadows further.
3. Gave a rectangle model with weight coefficients to calculate the average value. This model considered the distribution of the color in agriculture field, that is the color is more similar in the crop row direction. The use of this model can remove the influence of broken ridge and weeds.
4. The combination of averge and standard deviation as a new input feature of Support Vector Machine, the result imply that not only obtained a good segmentation but the width of crop row remained too. This is benefit for the followed navigation line detection.
5. The Support Vector Machine algorithm were used in the agriculture image segmentation for the first time, and can removed the influence of broken ridge, weeds, shadow and illumination change.
以往采用的农田分割算法不能很好的去除农田断垄、杂草、阴影及光照改变等噪声影响,使得对后续导航线提取算法要求很高,加上导航线算法计算过程复杂,如Hough变换等,使得整个农田处理过程鲁棒性下降。针对农田图像分割目的主要是检测大尺度作物行,将统计迭代算法Meanshift和支持向量机应用于农田图像分割,为了提高算法实时性分别将两种统计迭代算法和小波多分辨率分析相结合。为了给农田彩色模型的选取提供理论依据,从颜色混合角度出发分析了几个常用的模型。最后将农田图像分割中采用的各种典型分割算法和本文提出的基于小波多分辨率分解的快速Meanshift算法以及基于小波多分辨率分解的各种支持向量机算法进行了实验对比研究。
本文的主要研究成果如下：
1)基于农田结构特点,首次提出了在图像分割中只应用小波多分辨率分解的低分辨率图像。不仅保留了农田待检测信息,并有助于断垄、杂草、小的阴影等高频干扰的去除,还大大减少了算法程序运行时间。
2)提出了分块选种子点的快速Meanshift算法,并应用于农田图像分割。改进Meanshift算法具有良好的去除干扰的能力,作为统计迭代算法唯一的缺点就是执行速度慢。为了提高速度,达到实时导航要求,除了采用小波多分辨率分解外,还依据农田特点,选取具有明显特征的种子点,只对种子点进行该算法,节省了运行时间。由于农田结构整体的统一性,还可将农田图像沿垂直于行的方向分块,使每次迭代运算只在一块中进行,有效减少了每次迭代运算参与像素的数量,进一步减少了运行时间。改进Meanshift算法的应用有效克服的断垄、杂草或阴影的干扰。
3)依据农田结构提出了长方形有权重的均值计算模板。这种模板的应用充分考虑了农田作物行颜色空间分布的特点,在行方向上的像素点更具有和当前点相似的特性,这种模版的采用有效克服了断垄、行间杂草的影响。
4)提出了将图像均值和图像方差信息融合后代表农田图像特征,作为支持向量机的输入,使得行宽信息最大程度保留下来,有利于后续导航线的提取。
5)首次将支持向量机相关算法应用于农田图像分割,有效克服了农田图像中断垄、杂草、阴影、光照变化等干扰。
The traditional agriculture work is very tedious, low efficiency and occasionally dangerous, such as pesticide poisoning, sunburned skin or even worse. The emergency of agriculture navigation effectively resolves these problems. To detect path based on machine vision in automatic navigation is a main method, because of rich information, flexible use and not considered the circumstance (mainly based on the ridge, balk that is formed before in farmland and orchard). The image segmentation is the key factor in the vision detection of path. This paper mainly researches the statistic interation algorithm and its application in agriculture image segmentation. On the other hand, the auto navigation of agriculture vehicle meets the demand of the development of precision agriculture, and protects the circumstance.
The image segmentation algorithm that used in agriculture navigation before couldn't effectively remove the imfluence of broken ridge, weeds, shadow and illumination change. So the followed guidance line detection algorithm must resolve these problems, it would result in lower robust because of the complexicity of itself, such as Hough thansform. The purpose of agriculture image segmentation is to detect the crop row, so the statistic iteration algorithm Meanshift and Support Vector Machine was used in this paper. In order to save running time the two statistic iteration algorithm were integrated with wavelet multi resolution individually. The color models that usually used in agriculture image segmentation were discussed from the point of theory view. In the last some typical agriculture image segmentation algorithms were contrasted with the algorithm that used in this paper based on experiments.
The main innovation work of this thesis as follows:
1. Based on the structure features of agriculture field, gives a new idea that only used the lower resolution image. This not only could remain the information that would be detected, but also effectively removed the influence of broken ridge, weeds and shadows, and the running time was saved too.
2. Based on the former method and the features of farmland, this paper proposed a new fast Meanshift algorithm that divided the agriculture image into several pieces and run the Meanshift algorithm only on the seeds that selected from each pieces. Based on the wavelet multi resolution decomposion, the Meanshift algorithm remove the the influence of broken ridge, weeds and shadows further.
3. Gave a rectangle model with weight coefficients to calculate the average value. This model considered the distribution of the color in agriculture field, that is the color is more similar in the crop row direction. The use of this model can remove the influence of broken ridge and weeds.
4. The combination of averge and standard deviation as a new input feature of Support Vector Machine, the result imply that not only obtained a good segmentation but the width of crop row remained too. This is benefit for the followed navigation line detection.
5. The Support Vector Machine algorithm were used in the agriculture image segmentation for the first time, and can removed the influence of broken ridge, weeds, shadow and illumination change.
引文
[1]J. F. Reid, Q. Zhang, N. Noguchi, and M. Dickson. Agricultural Automatic Gguidance Research in North America [J]. COMPUT ELECTRON AGR,2000,25(1),155-167.
[2]O. N. Luciano, O. R. Valentin, and T. J. Onofer. A Method for Agricultural Machine Guidance on Row Crops Based on the Vanishing Point[C]. ICVES,2007,1-6.
[3]M. Kise, Q. Zhang, and F. Mas. A Stereovision-based Crop Row Detection Method for Tractor-automated Guidance [J]. Biosystems Engineering,2005,90(4),357-367.
[4]T. Pilarski, M. Happold, H. Pangels, M. Ollis, K. Fitzpatrick, and A. Stentz. The Demeter System for Automated Harvesting [J]. Autonomous Robots,2002,13(1), 9-12.
[5]张淑娟.基于GPS和GIS的精细农业田间信息的采集和处理方法的研究[D].浙江大学,2003,1-4.
[6]T.Hambita, J.S.Duppence and G.Vellidis. Precision Farming Practices [J]. IEEE Industry Applications Magazine,2009,15(2),34-42.
[7]N.Sigrimis, P.Antsaklis and P.P.Groumpos. Advances in Control of Agriculture and the Environment [J]. IEEE Control Systems Magazine,2001,21(5),8-12.
[8]G.Pajares, A.Tellaeche, X.P.BurgosArtizzu and A. Ribeiro. Design of a Computer Vision System for a Differential Spraying Operation in Precision Agriculture using Hebbian Learning [J]. IET Comput. Vis,2007,1(3-4),93-99.
[9]周俊.农用轮式移动机器人视觉导航系统的研究[D].南京农业大学,2003,7-9.
[10]罗锡文,臧英,周志艳.精细农业中农情信息采集技术的研究进展[J].农业机械学报,2006,22(1),167-173.
[11]J.N.Wilson. Guidance of Agricultural Vehicles-A Historical Perspective [J].COMPUT ELECTRON AGR,2000,25(1),3-9.
[12]R.Keicher, H.Seufert. Automatic Guidance for Agricultural Vehicles in Europe [J]. COMPUT ELECTRON AGR,2000,25(1),169-194.
[13]J.B.Gerrish, T.C.Surbrook. Mobile Robots in Agriculture [C]. Robotics and Intelligent Machines in Agriculture,1984,30-41.
[14]B.W.Fehr, J.B.Gerrish. Vision-guided Row Crop Follower [J]. Appl. Eng. Agric,1995, 11(4),613-620.
[15]J.F.Reid, S.W.Searcy. Vision-based Guidance of an Agricultural Tractor [J]. IEEE Control Systems,1987,7(12),39-43.
[16]N.D.Tillett, T.Hague, S.J.Miles. Inter-Row Vision Guidance for Mechanical Weed Control in Sugar Beet [J]. COMPUT ELECTRON AGR,2002,33(3),163-177.
[17]H.T.Sogaard, H.J.Olsen. Determination of Crop Rows by Image Analysis without Segmentation [J]. COMPUT ELECTRON AGR,2003,38(2),141-158.
[18]S.Han, Q.Zhang, B.Ni and J.F.Reid. A Guidance Directrix Approach to Vision-based Vehicle Guidance Systems [J]. COMPUT ELECTRON AGR,2004,43(3),179-195.
[19]M.Kise, Q.Zhang, F.Rovira Mas. A Stereovision-based Crop Row Detection Method for Tractor-automated Guidance [J].Biosystems Engineering,2005,90(4),357-367.
[20]B.Astrand, A.J.Baerveldt. A Vision Based Row-following System for Agricultural Field Machinery [J]. Mechatronics,2005,15(2),251-269.
[21]F.R.Mas, Q.Zhang, J.F.Reid, and J.D.Will. Hough-transform-based Vision Algorithm for Crop Row Detection of an Automated Agricultural Vehicle [J]. Automobile Engineering,2005,219(8),999-1010.
[22]V.Leemans, M.F.Destain. Application of the Hough Transform for Seed Row Localisation Using Machine Vision [J]. Biosystems Engineering,2006,94(3), 325-336.
[23]V.Leemans, M.F.Destain. Line Cluster Detection Using a Variant of the Hough Transform for Culture Row Localisation [J]. Image and Vision Computing,24(5), 541-550.
[24]V. Subramanian, T.F.Burks and A.A.Arroyo. Development of Machine Vision and Laser Radar Based Autonomous Vehicle Guidance Systems for Citrus Grove Navigation [J]. COMPUT ELECTRON AGR,2006,53(2),130-143.
[25]O. N. Luciano, O. R. Valentin, and T. J. Onofer. A Method for Agricultural Machine Guidance on Row Crops Based on the Vanishing Point [C]. ICVES,2007,1-6.
[26]V.Leemans, M.F.Destain. A Computer-vision Based Precision Seed Drill Guidance Assistance [J]. COMPUT ELECTRON AGR,2007,59(1-2),1-12.
[27]T.Bakker, H.Wouters and K.V.Asselt et.al. A Vision Based Row Detection System for Sugar Beet [J]. COMPUT ELECTRON AGR,2008,60(1),87-95.
[28]M.Kise, Q.Zhang. Developmemt of a Stereovision Sensing System for 3D Crop Row Structure Mapping and Tractor Guidance [J]. Biosystems Engineering,2008,101(2), 191-198.
[29]R.Gottschalk, X.P.Burgos-Artizzu and A.Ribeiro et al. Real-time Image Processing for the Guidance of a Small Agricultural Field Inspection Vehicle [C]. M2VIP08,2008, 493-498.
[30]沈明霞,姬长英.基于纹理频谱的农田景物区域检测[J].农机化研究,2000,3,43-47.
[31]沈明霞,张瑞合,姬长英.农作物边缘提取方法研究[J].农业机械学报,2000,31(6),49-51.
[32]沈明霞,姬长英.农业机器人视觉导航技术发展与展望[J].农业机械学报,2001,32(1),109-111.
[33]沈明霞,姬长英,张瑞合.基于农田景物边缘的农业机器人自定位方法[J].农业机械学报,2001,32(6),49-51.
[34]沈明霞,李秀智,姬长英.基于形态学的农田景物区域检测技术[J].农业机械学报,2003,34(1),92-94.
[35]周俊,姬长英.基于知识的视觉导航农业机器人行走路径识别[J].农业工程学报,2003,19(6),101-105.
[36]周俊,姬长英.农业机器人视觉导航中多分辨率路径识别[J].农业机械学报,2003,34(6),120-123.
[37]周俊,刘成良,姬长英.农用轮式移动机器人相对位姿的求解方法[J].中国图象图形学报,2005,10(3),310-314.
[38]张志斌,罗锡文,李庆等人.基于良序集和垄行结构的农机视觉导航参数提取算法[J].农业工程学报,2007,23(7),122-126.
[39]张志斌,罗锡文,周学成,臧英.基于Hough变换和Fisher准则的垄线识别算法[J].中国图象图形学报,2007,12(12),2164-2168.
[40]张志斌,罗锡文,王在满.基于良序子集的最近邻垄行图像识别算法[J].中国图象图形学报,2007,12(11),2048-2051.
[41]Zhang Fangming, Yin Yibin, Jiang Huanyu and Shin Beomsoo. Correlation Analysis-based Image Segmentation Approch for Automatic Agriculture Vehicle [J]. Journal of Zhejiang University,2005,6A(10),1158-1162.
[42]Fangming Zhang, Yibin Ying, Chuan Shen, Huanyu Jiang, Qin Zhang. Stereovision-based 3D Field Recognization for Automatic Guidance System of Off-road vehicle [C]. Proceedings of SPIE,2005,6000(32).
[43]钟珞,潘昊,封筠等人.模式识别[M].武汉：武汉大学出版社,2006,1-5.
[44]R.C.Gonzalez, R.E.Woods. Digital Image Processing [M]. Beijing:Publishing House of Electronics Industry,2006,282-283.
[45]A.Koschan, M.Abidi(著),章毓晋(译).彩色数字图像处理[M].北京：清华大学出版社,2010,6-9.
[46]Y.Wang, J.Ostermann, Y.Q.Zhang. Video Processing and Communications [M]. Beijing:Tsinghua University Press,2004,1-7.
[47]赵金英,张铁中,杨丽.西红柿采摘机器人视觉系统的目标提取[J].农业机械学报,2006,37(10),201-203.
[48]徐丽明,张铁中.果蔬果实收获机器人的研究现状及关键问题和对策[J].农业工程学报,2004,20(5),38-42.
[49]孙元义,张绍磊,李伟.棉田喷药农业机器人的导航路径识别[J].清华大学学报(自然科学版),2007,47(2),206-209.
[50]战强,吴佳.未知环境下移动机器人单目视觉导航算法[J].北京航天航空大学学报,2008,34(6),613-617.
[51]J.M.Kasson, S.I.Nin, W.Plouffe and J.L.Hafner. Performing Color Space Conversions with Three-dimensional Linear Interpolation [J]. Journal of Electronic Imaging,1995, 4(3),226-250.
[52]C.Connolly, T.Fliess. A Study of Efficiency and Accuracy in the Transtormation from RGB to CIELAB Color Space [J]. IEEE Teansactions on Image Processing,1997, 6(7),1046-1048.
[53]G.J.Klinker, S.A.Shafer and T.Kanade. Physical Approach to Color Image Understanding [J]. International Journal of Computer Vision,1990,4(1),7-38.
[54]甘谷党建网.甘谷34.61万亩小麦开镰分割.http://www.ggyjw.gov.cn/Html/ xncjs/162040659.html,2010.06.25.
[55]Dong Bing-Feng, Qiu Yun-Jie and Lu Hong-Tao. A Novel Blinding Digital Watermark Algorithm Based on Lab Color Space [C].2nd International Conference on Digital Image Processing,2010,7546(2),75460C.
[56]R. Michal, L. Franz. Windows Detection Using K-means in CIE-lab color space[C]. ICPR,2010,356-359.
[57]S. Alisa, A. Thumronqrat. Digital Watermarking Based on Pixels Modification Using Adaptive Pixel Replacement in Lab Color Space [C]. ISCIT,2010,761-766.
[58]L.Brechet, M.F. Lucas, C.Doncarli and D.Farina. Compression of Biomedical Signals With Mother Wavelet Optimization and Best-basis Wavelet Packet Selection [J]. IEEE Transactions on Biomedical Engineering,2007,54(12),2186-2192.
[59]G.Quellec, M.Lamard and G.Cazuguel et.al. Adaptive Nonseparable Wavelet Transform Via Lifting and its Application to Content-based Image Retrieval [J]. IEEE Transactions on Image Processing,2010,19(1),25-35.
[60]M.Unser, D.Sage, D.V.D.Van. Multiresolution Monogenic Signal Anzlysis Using the Riesz-laplace Wavelet Transform [J]. IEEE Transactions on Image Processing,2009, 18(11),2402-2418.
[61]M.D.Gaubatz, S.S.Hemami. Robust Rate-control for Wavelet-based Image Coding via Conditional Probability Models [J]. IEEE Transactions on Image Processing,2007, 16(3),2402-2418.649-663.
[62]张方明,应义斌.田间路径识别算法和基于立体视觉的车辆自动导航方法研究[D].浙江大学,2006,26-36.
[63]闫敬文.数字图像处理[M].北京：国防工业出版社,2007,6-13.
[64]S.Mallat. A Theory for Multiresolution Signal Decomposition:the Wavelet Representation [J]. IEEE Pattern Anal. and Machine Intell,1989,11(7),674-693.
[65]A.Mayer, H.Greenspan. An Adaptive Mean-Shift Framework for MRI Brain Segmentation [J]. IEEE Transactions on Medical Imaging,2009,28(8),1238-1250.
[66]D.M.Tsai, J.Y.Luo. Mean Shift-Based Defect Detection in Multicrystalline Solar Wafer Surfaces [J]. IEEE Transactions on Industrial Informatics,2011,7(1), 125-135.
[67]X.D.Yang, H.Q.Li and X.B.Zhou. Nuclei Segmentation Using Marker Controlled Watershed, Tracking Using Mean-Shift, and Kalman Filter in Time-Lapse Microscopy. IEEE Transactions on Circuits and Systems,2006,53(11),2405-2414.
[68]K.L.Kim, K.Jung and J.H.Kim. Texture-based Approach for Text Detection in Images Using Support Vector Machines and Continuously Adaptive Mean Shift Algorithm [J]. IEEE Transactions on Pattern and Machine Intelligence,2003,25(12),1631-1639.
[69]K. Fukunaga, L.D. Hostetler. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition [J] IEEE Trans. Info. Theory,1975,21, 32-40.
[70]Y.Cheng. Mean Shift, Mode Seeking, and Clustering [J]. IEEE Trans, on Pattern Analysis and Machine Intelligence,1995,17(8),790-799.
[71]J.Wang, B.Thiesson, Y.Xu, and M.Cohen. Image and Video Segmentation by Anisotropic Kernel Mean Shif t[J]. Lecture Notes in Computer Science,2004 238-249.
[72]D.Comaniciu, V.Ramesh and P.Meer. Kernel-Based Object Tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,564-577.
[73]D.Comaniciu, P.Meer. Mean Shift Analysis and Applications [C]. Proc. Seventh Int'l Conf. Computer Vision,1999,1197-1203.
[74]P.F.Felzenszwalb, D.P.Huttenlocher. Image Segmentation Using Local Variation [C]. IEEE Conf. Comp. Vis.and Pattern Recogn, Santa Barbara,1998,98-103.
[75]诸葛振荣,徐敏,刘洋飞.基于Meanshift的织物图像分割算法[J].纺织学报,2007,28(10),108-116.
[76]郭显久.小波与细分方法在图像处理中的应用研究[D].大连理工大学,2008,66-71.
[77]A. Miguel, C.Perpinan. Gaussian Mean-Shift Is an EM Algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5),767-776.
[78]A.Pooransingh, C.A.Radix. The Path Assigned Mean Shift Algorithm:a New Fast Mean Shift Implementation for Color Image Segmentation [C]. ICIP,2008,597-600.
[79]K.Zhang, M.Tang and J.T.Kwok. Applying Neighborhood Consistency for Fast Clustering and Kernel Density Estimation [C]. CVPR,2005,2,1001-1007.
[80]李艳灵,沈轶.基于共轭梯度法的快速Mean Shift图像分割[J].光电工程,2009,36(8),94-98.
[81]李刚,李艳灵.快速均值飘移图像分割算法研究[J].数学的实践与认识,2009,39(8),173-177.
[82]D.Comaniciu, P.Meer, Robust Analysis of Feature Spaces:Color Image Segmentation [C]. IEEE Conf. Comp.Vis. and Pattern Recogn,1997,750-755.
[83]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京：科学出版社,2009,1-5.
[84]V.N.Vapnik. The Nature of Statistical Learning Theory [J]. IEEE Transactions on Neural Network,1997,8(6),1564.
[85]V.N.Vapnik. An Overview of Statistical Learning Theory [J]. IEEE Transactions on Neural Network,1999,10(5),988-999.
[86]梁锦锦.支持向量机和支持向量域描述的若干问题研究[D].西安电子科技大学,2009,1-9.
[87]杜喆.几类支持向量机变型算法的研究[D].西安电子科技大学,2009,1-9.
[88]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京：科学出版社,2009,118-124.
[89]D.A.Reynolds, R.C.Rose. Robust Text-independent speaker identification using Gaussian Mixture Speaker Models [J]. IEEE Transactions on Speech and Audio Processing,1995,3(1),72-83.
[90]G.Camps-Valls, L.Gomez-Chova and J.Calpe-Maravilla, et.al. Robust Support Vector Method for Hyperspectral Data Classification and Knowledge Discovery [J]. IEEE Transactions on Geoscience and Remote Sensing,2004,42(7),1530-1542.
[91]Y.F.Shi, Y.P.Zhao. Comparison of Text Categorization Algorithms [J]. Wuhan University Journal of Natural Sciences,2004,9(5),798-804.
[92]D.A.Forsyth, J.Ponce(著),林学訚,王宏(译).计算机视觉—一种现代方法[M].北京：电子工业出版社,2002,451-458.
[93]X.Fan, G.Zhang and X.Z.Xia. Performance Evaluation of SVM in Image Segmentation [J]. ICSP,2008,1207-1210.
[94]边肇祺,张学工.模式识别[M].北京：清华大学出版社,2000,198-210.
[95]G.M. Hilario, M. B. Saturnino, G. J. Pedro, and L. A. Sergio. Goal Evaluation of Segmentation Algorithms for Traffic Sign Recognition [J]. IEEE T INTELL TRANSP,2010,11(4),917-930.
[96]O. Selmi, A. Pinti, A.Taleb-Ahmed, and N. Kerkeni. Use of Support Vector Machines for Color Image Segmentation[C]. CESA,2006,1,574-577.
[97]L. Lei, L. Jin-Yan, and D. Wen-Yan. A New Method for Color Image Segmentation Based on FSVM [C]. ICMLC,2010,2,664-668.
[98]E. Ricci, R. Perfetti. Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification [J]. IEEE T MED IMAGING,2007,26(10), 1357-1365.
[99]J. Chia-Feng, C. Shih-Hsuan, and C. Shu-Wew. A Self-Organizing TS-Type Fuzzy Network with Support Vector Learning and its Application to Classification Problems [J]. IEEE T FUZZY SYST,2007,15(5),998-1008.
[100]G. Chicco, I.-S. Ilie. Support Vector Clustering of Electrical Load Pattern Data [J] IEEE T POWER SYST,2009,24(3),1619-1628.
[101]O. Chapelle, P. Haffner, and V. N. Vapnik. Support Vector Machines for Histogram-based Image Classification [J] IEEE T NEURAL NETWOR,1999,10(5), 1055-1064.
[102]J. S. Wang, J. C. Chiang. A Cluster Validity Measure With Outlier Detection for Support Vector Clustering [J]. IEEE TRANSACTIONS ON SYSTEMS,MAN,AND CYBERNETICS—RART B:CYBERNETICS,2008,38(1),78-89.
[103]C.C.Chung, L.C. Jen. LIBSVM:a Library for Support Vector Machines.2004, Available at http://www.csie.ntu.edu.tw/-cjlin.
[104]吴佳艺,杨庆华,鲍官军等.基于机器视觉的林间导航路径生成算法[J].农业机械学报,2009,40(7),176-179.
[2]O. N. Luciano, O. R. Valentin, and T. J. Onofer. A Method for Agricultural Machine Guidance on Row Crops Based on the Vanishing Point[C]. ICVES,2007,1-6.
[3]M. Kise, Q. Zhang, and F. Mas. A Stereovision-based Crop Row Detection Method for Tractor-automated Guidance [J]. Biosystems Engineering,2005,90(4),357-367.
[4]T. Pilarski, M. Happold, H. Pangels, M. Ollis, K. Fitzpatrick, and A. Stentz. The Demeter System for Automated Harvesting [J]. Autonomous Robots,2002,13(1), 9-12.
[5]张淑娟.基于GPS和GIS的精细农业田间信息的采集和处理方法的研究[D].浙江大学,2003,1-4.
[6]T.Hambita, J.S.Duppence and G.Vellidis. Precision Farming Practices [J]. IEEE Industry Applications Magazine,2009,15(2),34-42.
[7]N.Sigrimis, P.Antsaklis and P.P.Groumpos. Advances in Control of Agriculture and the Environment [J]. IEEE Control Systems Magazine,2001,21(5),8-12.
[8]G.Pajares, A.Tellaeche, X.P.BurgosArtizzu and A. Ribeiro. Design of a Computer Vision System for a Differential Spraying Operation in Precision Agriculture using Hebbian Learning [J]. IET Comput. Vis,2007,1(3-4),93-99.
[9]周俊.农用轮式移动机器人视觉导航系统的研究[D].南京农业大学,2003,7-9.
[10]罗锡文,臧英,周志艳.精细农业中农情信息采集技术的研究进展[J].农业机械学报,2006,22(1),167-173.
[11]J.N.Wilson. Guidance of Agricultural Vehicles-A Historical Perspective [J].COMPUT ELECTRON AGR,2000,25(1),3-9.
[12]R.Keicher, H.Seufert. Automatic Guidance for Agricultural Vehicles in Europe [J]. COMPUT ELECTRON AGR,2000,25(1),169-194.
[13]J.B.Gerrish, T.C.Surbrook. Mobile Robots in Agriculture [C]. Robotics and Intelligent Machines in Agriculture,1984,30-41.
[14]B.W.Fehr, J.B.Gerrish. Vision-guided Row Crop Follower [J]. Appl. Eng. Agric,1995, 11(4),613-620.
[15]J.F.Reid, S.W.Searcy. Vision-based Guidance of an Agricultural Tractor [J]. IEEE Control Systems,1987,7(12),39-43.
[16]N.D.Tillett, T.Hague, S.J.Miles. Inter-Row Vision Guidance for Mechanical Weed Control in Sugar Beet [J]. COMPUT ELECTRON AGR,2002,33(3),163-177.
[17]H.T.Sogaard, H.J.Olsen. Determination of Crop Rows by Image Analysis without Segmentation [J]. COMPUT ELECTRON AGR,2003,38(2),141-158.
[18]S.Han, Q.Zhang, B.Ni and J.F.Reid. A Guidance Directrix Approach to Vision-based Vehicle Guidance Systems [J]. COMPUT ELECTRON AGR,2004,43(3),179-195.
[19]M.Kise, Q.Zhang, F.Rovira Mas. A Stereovision-based Crop Row Detection Method for Tractor-automated Guidance [J].Biosystems Engineering,2005,90(4),357-367.
[20]B.Astrand, A.J.Baerveldt. A Vision Based Row-following System for Agricultural Field Machinery [J]. Mechatronics,2005,15(2),251-269.
[21]F.R.Mas, Q.Zhang, J.F.Reid, and J.D.Will. Hough-transform-based Vision Algorithm for Crop Row Detection of an Automated Agricultural Vehicle [J]. Automobile Engineering,2005,219(8),999-1010.
[22]V.Leemans, M.F.Destain. Application of the Hough Transform for Seed Row Localisation Using Machine Vision [J]. Biosystems Engineering,2006,94(3), 325-336.
[23]V.Leemans, M.F.Destain. Line Cluster Detection Using a Variant of the Hough Transform for Culture Row Localisation [J]. Image and Vision Computing,24(5), 541-550.
[24]V. Subramanian, T.F.Burks and A.A.Arroyo. Development of Machine Vision and Laser Radar Based Autonomous Vehicle Guidance Systems for Citrus Grove Navigation [J]. COMPUT ELECTRON AGR,2006,53(2),130-143.
[25]O. N. Luciano, O. R. Valentin, and T. J. Onofer. A Method for Agricultural Machine Guidance on Row Crops Based on the Vanishing Point [C]. ICVES,2007,1-6.
[26]V.Leemans, M.F.Destain. A Computer-vision Based Precision Seed Drill Guidance Assistance [J]. COMPUT ELECTRON AGR,2007,59(1-2),1-12.
[27]T.Bakker, H.Wouters and K.V.Asselt et.al. A Vision Based Row Detection System for Sugar Beet [J]. COMPUT ELECTRON AGR,2008,60(1),87-95.
[28]M.Kise, Q.Zhang. Developmemt of a Stereovision Sensing System for 3D Crop Row Structure Mapping and Tractor Guidance [J]. Biosystems Engineering,2008,101(2), 191-198.
[29]R.Gottschalk, X.P.Burgos-Artizzu and A.Ribeiro et al. Real-time Image Processing for the Guidance of a Small Agricultural Field Inspection Vehicle [C]. M2VIP08,2008, 493-498.
[30]沈明霞,姬长英.基于纹理频谱的农田景物区域检测[J].农机化研究,2000,3,43-47.
[31]沈明霞,张瑞合,姬长英.农作物边缘提取方法研究[J].农业机械学报,2000,31(6),49-51.
[32]沈明霞,姬长英.农业机器人视觉导航技术发展与展望[J].农业机械学报,2001,32(1),109-111.
[33]沈明霞,姬长英,张瑞合.基于农田景物边缘的农业机器人自定位方法[J].农业机械学报,2001,32(6),49-51.
[34]沈明霞,李秀智,姬长英.基于形态学的农田景物区域检测技术[J].农业机械学报,2003,34(1),92-94.
[35]周俊,姬长英.基于知识的视觉导航农业机器人行走路径识别[J].农业工程学报,2003,19(6),101-105.
[36]周俊,姬长英.农业机器人视觉导航中多分辨率路径识别[J].农业机械学报,2003,34(6),120-123.
[37]周俊,刘成良,姬长英.农用轮式移动机器人相对位姿的求解方法[J].中国图象图形学报,2005,10(3),310-314.
[38]张志斌,罗锡文,李庆等人.基于良序集和垄行结构的农机视觉导航参数提取算法[J].农业工程学报,2007,23(7),122-126.
[39]张志斌,罗锡文,周学成,臧英.基于Hough变换和Fisher准则的垄线识别算法[J].中国图象图形学报,2007,12(12),2164-2168.
[40]张志斌,罗锡文,王在满.基于良序子集的最近邻垄行图像识别算法[J].中国图象图形学报,2007,12(11),2048-2051.
[41]Zhang Fangming, Yin Yibin, Jiang Huanyu and Shin Beomsoo. Correlation Analysis-based Image Segmentation Approch for Automatic Agriculture Vehicle [J]. Journal of Zhejiang University,2005,6A(10),1158-1162.
[42]Fangming Zhang, Yibin Ying, Chuan Shen, Huanyu Jiang, Qin Zhang. Stereovision-based 3D Field Recognization for Automatic Guidance System of Off-road vehicle [C]. Proceedings of SPIE,2005,6000(32).
[43]钟珞,潘昊,封筠等人.模式识别[M].武汉：武汉大学出版社,2006,1-5.
[44]R.C.Gonzalez, R.E.Woods. Digital Image Processing [M]. Beijing:Publishing House of Electronics Industry,2006,282-283.
[45]A.Koschan, M.Abidi(著),章毓晋(译).彩色数字图像处理[M].北京：清华大学出版社,2010,6-9.
[46]Y.Wang, J.Ostermann, Y.Q.Zhang. Video Processing and Communications [M]. Beijing:Tsinghua University Press,2004,1-7.
[47]赵金英,张铁中,杨丽.西红柿采摘机器人视觉系统的目标提取[J].农业机械学报,2006,37(10),201-203.
[48]徐丽明,张铁中.果蔬果实收获机器人的研究现状及关键问题和对策[J].农业工程学报,2004,20(5),38-42.
[49]孙元义,张绍磊,李伟.棉田喷药农业机器人的导航路径识别[J].清华大学学报(自然科学版),2007,47(2),206-209.
[50]战强,吴佳.未知环境下移动机器人单目视觉导航算法[J].北京航天航空大学学报,2008,34(6),613-617.
[51]J.M.Kasson, S.I.Nin, W.Plouffe and J.L.Hafner. Performing Color Space Conversions with Three-dimensional Linear Interpolation [J]. Journal of Electronic Imaging,1995, 4(3),226-250.
[52]C.Connolly, T.Fliess. A Study of Efficiency and Accuracy in the Transtormation from RGB to CIELAB Color Space [J]. IEEE Teansactions on Image Processing,1997, 6(7),1046-1048.
[53]G.J.Klinker, S.A.Shafer and T.Kanade. Physical Approach to Color Image Understanding [J]. International Journal of Computer Vision,1990,4(1),7-38.
[54]甘谷党建网.甘谷34.61万亩小麦开镰分割.http://www.ggyjw.gov.cn/Html/ xncjs/162040659.html,2010.06.25.
[55]Dong Bing-Feng, Qiu Yun-Jie and Lu Hong-Tao. A Novel Blinding Digital Watermark Algorithm Based on Lab Color Space [C].2nd International Conference on Digital Image Processing,2010,7546(2),75460C.
[56]R. Michal, L. Franz. Windows Detection Using K-means in CIE-lab color space[C]. ICPR,2010,356-359.
[57]S. Alisa, A. Thumronqrat. Digital Watermarking Based on Pixels Modification Using Adaptive Pixel Replacement in Lab Color Space [C]. ISCIT,2010,761-766.
[58]L.Brechet, M.F. Lucas, C.Doncarli and D.Farina. Compression of Biomedical Signals With Mother Wavelet Optimization and Best-basis Wavelet Packet Selection [J]. IEEE Transactions on Biomedical Engineering,2007,54(12),2186-2192.
[59]G.Quellec, M.Lamard and G.Cazuguel et.al. Adaptive Nonseparable Wavelet Transform Via Lifting and its Application to Content-based Image Retrieval [J]. IEEE Transactions on Image Processing,2010,19(1),25-35.
[60]M.Unser, D.Sage, D.V.D.Van. Multiresolution Monogenic Signal Anzlysis Using the Riesz-laplace Wavelet Transform [J]. IEEE Transactions on Image Processing,2009, 18(11),2402-2418.
[61]M.D.Gaubatz, S.S.Hemami. Robust Rate-control for Wavelet-based Image Coding via Conditional Probability Models [J]. IEEE Transactions on Image Processing,2007, 16(3),2402-2418.649-663.
[62]张方明,应义斌.田间路径识别算法和基于立体视觉的车辆自动导航方法研究[D].浙江大学,2006,26-36.
[63]闫敬文.数字图像处理[M].北京：国防工业出版社,2007,6-13.
[64]S.Mallat. A Theory for Multiresolution Signal Decomposition:the Wavelet Representation [J]. IEEE Pattern Anal. and Machine Intell,1989,11(7),674-693.
[65]A.Mayer, H.Greenspan. An Adaptive Mean-Shift Framework for MRI Brain Segmentation [J]. IEEE Transactions on Medical Imaging,2009,28(8),1238-1250.
[66]D.M.Tsai, J.Y.Luo. Mean Shift-Based Defect Detection in Multicrystalline Solar Wafer Surfaces [J]. IEEE Transactions on Industrial Informatics,2011,7(1), 125-135.
[67]X.D.Yang, H.Q.Li and X.B.Zhou. Nuclei Segmentation Using Marker Controlled Watershed, Tracking Using Mean-Shift, and Kalman Filter in Time-Lapse Microscopy. IEEE Transactions on Circuits and Systems,2006,53(11),2405-2414.
[68]K.L.Kim, K.Jung and J.H.Kim. Texture-based Approach for Text Detection in Images Using Support Vector Machines and Continuously Adaptive Mean Shift Algorithm [J]. IEEE Transactions on Pattern and Machine Intelligence,2003,25(12),1631-1639.
[69]K. Fukunaga, L.D. Hostetler. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition [J] IEEE Trans. Info. Theory,1975,21, 32-40.
[70]Y.Cheng. Mean Shift, Mode Seeking, and Clustering [J]. IEEE Trans, on Pattern Analysis and Machine Intelligence,1995,17(8),790-799.
[71]J.Wang, B.Thiesson, Y.Xu, and M.Cohen. Image and Video Segmentation by Anisotropic Kernel Mean Shif t[J]. Lecture Notes in Computer Science,2004 238-249.
[72]D.Comaniciu, V.Ramesh and P.Meer. Kernel-Based Object Tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,564-577.
[73]D.Comaniciu, P.Meer. Mean Shift Analysis and Applications [C]. Proc. Seventh Int'l Conf. Computer Vision,1999,1197-1203.
[74]P.F.Felzenszwalb, D.P.Huttenlocher. Image Segmentation Using Local Variation [C]. IEEE Conf. Comp. Vis.and Pattern Recogn, Santa Barbara,1998,98-103.
[75]诸葛振荣,徐敏,刘洋飞.基于Meanshift的织物图像分割算法[J].纺织学报,2007,28(10),108-116.
[76]郭显久.小波与细分方法在图像处理中的应用研究[D].大连理工大学,2008,66-71.
[77]A. Miguel, C.Perpinan. Gaussian Mean-Shift Is an EM Algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5),767-776.
[78]A.Pooransingh, C.A.Radix. The Path Assigned Mean Shift Algorithm:a New Fast Mean Shift Implementation for Color Image Segmentation [C]. ICIP,2008,597-600.
[79]K.Zhang, M.Tang and J.T.Kwok. Applying Neighborhood Consistency for Fast Clustering and Kernel Density Estimation [C]. CVPR,2005,2,1001-1007.
[80]李艳灵,沈轶.基于共轭梯度法的快速Mean Shift图像分割[J].光电工程,2009,36(8),94-98.
[81]李刚,李艳灵.快速均值飘移图像分割算法研究[J].数学的实践与认识,2009,39(8),173-177.
[82]D.Comaniciu, P.Meer, Robust Analysis of Feature Spaces:Color Image Segmentation [C]. IEEE Conf. Comp.Vis. and Pattern Recogn,1997,750-755.
[83]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京：科学出版社,2009,1-5.
[84]V.N.Vapnik. The Nature of Statistical Learning Theory [J]. IEEE Transactions on Neural Network,1997,8(6),1564.
[85]V.N.Vapnik. An Overview of Statistical Learning Theory [J]. IEEE Transactions on Neural Network,1999,10(5),988-999.
[86]梁锦锦.支持向量机和支持向量域描述的若干问题研究[D].西安电子科技大学,2009,1-9.
[87]杜喆.几类支持向量机变型算法的研究[D].西安电子科技大学,2009,1-9.
[88]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京：科学出版社,2009,118-124.
[89]D.A.Reynolds, R.C.Rose. Robust Text-independent speaker identification using Gaussian Mixture Speaker Models [J]. IEEE Transactions on Speech and Audio Processing,1995,3(1),72-83.
[90]G.Camps-Valls, L.Gomez-Chova and J.Calpe-Maravilla, et.al. Robust Support Vector Method for Hyperspectral Data Classification and Knowledge Discovery [J]. IEEE Transactions on Geoscience and Remote Sensing,2004,42(7),1530-1542.
[91]Y.F.Shi, Y.P.Zhao. Comparison of Text Categorization Algorithms [J]. Wuhan University Journal of Natural Sciences,2004,9(5),798-804.
[92]D.A.Forsyth, J.Ponce(著),林学訚,王宏(译).计算机视觉—一种现代方法[M].北京：电子工业出版社,2002,451-458.
[93]X.Fan, G.Zhang and X.Z.Xia. Performance Evaluation of SVM in Image Segmentation [J]. ICSP,2008,1207-1210.
[94]边肇祺,张学工.模式识别[M].北京：清华大学出版社,2000,198-210.
[95]G.M. Hilario, M. B. Saturnino, G. J. Pedro, and L. A. Sergio. Goal Evaluation of Segmentation Algorithms for Traffic Sign Recognition [J]. IEEE T INTELL TRANSP,2010,11(4),917-930.
[96]O. Selmi, A. Pinti, A.Taleb-Ahmed, and N. Kerkeni. Use of Support Vector Machines for Color Image Segmentation[C]. CESA,2006,1,574-577.
[97]L. Lei, L. Jin-Yan, and D. Wen-Yan. A New Method for Color Image Segmentation Based on FSVM [C]. ICMLC,2010,2,664-668.
[98]E. Ricci, R. Perfetti. Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification [J]. IEEE T MED IMAGING,2007,26(10), 1357-1365.
[99]J. Chia-Feng, C. Shih-Hsuan, and C. Shu-Wew. A Self-Organizing TS-Type Fuzzy Network with Support Vector Learning and its Application to Classification Problems [J]. IEEE T FUZZY SYST,2007,15(5),998-1008.
[100]G. Chicco, I.-S. Ilie. Support Vector Clustering of Electrical Load Pattern Data [J] IEEE T POWER SYST,2009,24(3),1619-1628.
[101]O. Chapelle, P. Haffner, and V. N. Vapnik. Support Vector Machines for Histogram-based Image Classification [J] IEEE T NEURAL NETWOR,1999,10(5), 1055-1064.
[102]J. S. Wang, J. C. Chiang. A Cluster Validity Measure With Outlier Detection for Support Vector Clustering [J]. IEEE TRANSACTIONS ON SYSTEMS,MAN,AND CYBERNETICS—RART B:CYBERNETICS,2008,38(1),78-89.
[103]C.C.Chung, L.C. Jen. LIBSVM:a Library for Support Vector Machines.2004, Available at http://www.csie.ntu.edu.tw/-cjlin.
[104]吴佳艺,杨庆华,鲍官军等.基于机器视觉的林间导航路径生成算法[J].农业机械学报,2009,40(7),176-179.