路面图象病害自动检测算法的研究
|
摘要
本文致力于路面图象病害自动检测算法的研究和实现。
首先本文分析了路面图象的特点，并对原始路面图象进行了必要的预处理，然后结合病害的定义和形态将病害分为块状和裂缝状两大类。
接下来回顾了图象分割的方法以及基于数学形态学的后处理。在图象分割中，重点讨论了效率较高的阈值分割方法。在上述技术的基础上，本文提出了针对块状病害的分级处理模型，此模型灵活，高效并能有效地适应复杂图象情况。通过在大量数据上的实验证明了基于此模型的算法在块状病害检测上的有效性。
针对裂缝状病害，本文回顾了各种边缘检测方法，并结合实例对各种方法进行了分析。本文重点研究了Canny算子，并在几个方面对其进行改进，最后在其基础上实现了一种比较有效的裂缝检测算法。在典型裂缝图象上的试验证明了此算法的有效性。
This paper is focused on the study and implementation of auto-detecting of distresses in pavement image .
Initially, the characteristics of pavement image are analyzed , then certain pre-processings are carried on the pavement image . Based on the definition and appearance of the distress image , the distresses are divided into two big classes : patch distress and crack distress .
Then the paper reviewed the image segmetation and morphological methods . The attention is put on thresholding segmetation method which are famous for their high efficiency . Based on the above techniques , a hiberarchy model is presented which is flexible and effective in dealing with the complicated situation in the pavement image . An experiment on a large amount of data show the good performance of the model in finding the patch distress .
For the crack distress , several classical methods in edge detecting are explored . Canny algorithm is chosen as the base of the detecting algorithm for crack distress . Several improvement are made . The tests on typical crack distress image prove the effectiveness of the algorithm.
首先本文分析了路面图象的特点，并对原始路面图象进行了必要的预处理，然后结合病害的定义和形态将病害分为块状和裂缝状两大类。
接下来回顾了图象分割的方法以及基于数学形态学的后处理。在图象分割中，重点讨论了效率较高的阈值分割方法。在上述技术的基础上，本文提出了针对块状病害的分级处理模型，此模型灵活，高效并能有效地适应复杂图象情况。通过在大量数据上的实验证明了基于此模型的算法在块状病害检测上的有效性。
针对裂缝状病害，本文回顾了各种边缘检测方法，并结合实例对各种方法进行了分析。本文重点研究了Canny算子，并在几个方面对其进行改进，最后在其基础上实现了一种比较有效的裂缝检测算法。在典型裂缝图象上的试验证明了此算法的有效性。
This paper is focused on the study and implementation of auto-detecting of distresses in pavement image .
Initially, the characteristics of pavement image are analyzed , then certain pre-processings are carried on the pavement image . Based on the definition and appearance of the distress image , the distresses are divided into two big classes : patch distress and crack distress .
Then the paper reviewed the image segmetation and morphological methods . The attention is put on thresholding segmetation method which are famous for their high efficiency . Based on the above techniques , a hiberarchy model is presented which is flexible and effective in dealing with the complicated situation in the pavement image . An experiment on a large amount of data show the good performance of the model in finding the patch distress .
For the crack distress , several classical methods in edge detecting are explored . Canny algorithm is chosen as the base of the detecting algorithm for crack distress . Several improvement are made . The tests on typical crack distress image prove the effectiveness of the algorithm.
引文
[1] 南京理工大学，“N-1型道路路面检测系统研制报告”，2002。
[2] 何斌、马天予编著，Visual C++数字图像处理。人民邮电出版社，2001。
[3] 高建贞 基于图像分析的道路病害自动检测研究，博士论文，南京理工大学，2003。
[4] 中华人民共和国行业标准，JTJ075—94，公路养护质量检查评定标准，1994。
[5] 中华人民共和国行业标准，JTJ073—96，公路养护技术规范，1996。
[6] 章硫晋，图像处理和分析，清华大学出版社，1999。
[7] 章毓晋，图像分割．科学出版社，2001。
[8] Ostu N A "Threshold Selection Method from Gray-leve histogram", IEEE Trans. On System, Man, and Cybernetics, Vol. 9, 1,1979,62-66
[9] Kapur ,Saho-p P, Wong A. "A new method for Gray-level Picture Thresholding Using the Entroy of the histogram" Computer Vision Graphics and image processing, 29, 210-239,1985
[10] M.Miyojim," Automatic pavement distress detection system", Journal of information sciences vol. 18 219-240 ,1998
[11] Randal C. Nelson," Finding line segments by stick growing" ,IEEE trans. PAMI vol. 16 No. 5, May 1994
[12] H. Lee and H. Oshima," New crack-imaging procedure using spatial autocorrelation function" ,Journal of transportation engineering ,Vol. 120, No 3, May, 1994
[13] H.N. Koutsopoulos and I.E. Sanhouri," Methods and algorithms for automated analysis of pavement images", Transportation Research Record ,1311,1991
[14] Kenneth R. Castleman," Digital image processing" ,Prentice Hal1,1996,115-138
[15] 阮秋琦，数字图像处理学，电子工业出版社，2001．1
[16] L.G. Roberts, "Machine Perception of Three-Dimension Solids," in Optical and Electro-Optimal Information Processing, J.t. Tippett, et al., Ed. Cambridge, MA: MIT Press, 1965, 99-159-197
[17] J. Prewitt, "Object Enhancement and Extraction," Picture Process. Psvchopict., 110pp.75-149, 1970.
[18] L. Sobel, "Camera Models and Machine Perception," PhD theses, Stanford University, Standford, CA, 1970
[19] Marr D著，姚国正译 视觉计算理论 科学出版社 1998
[20] Canny, John. "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986. Vol. PAMI-8, No. 6, pp. 679-698
[21] 刘杰平等，一种简易的图象去噪方法，华南理工大学学报，2000，28(2)：60～63
[22] 王廷忠，水泥混凝土路面病害及处理，林业建设，1998，(6)：32～33
[23] 周长发．精通Visum C++图像编程．电子工业出版社．2000
[24] 何斌等．Visum C++数字图像处理．人民邮电出版社．2001
[25] 王润生，图象理解，长沙：国防科技大学出版社，1995
[26] 楼伟．高等级公路路面病害识别与检测中的算法研究．西安工业学院．2001
[27] 斐继红等，基于平滑性测度的直方图自适应模糊增强图像分割，信号处理，1999，(12)
[29] 李向吉等，受噪声污染图像中的基于排序统计的非线性边缘检测器，信号处理，1999，(1)
[30] R. Nevatia," Locating Object Boundaries in Textured Environments ,"IEEE Trans.Comp.C-25:1170-1180,1976.
[31] J.M. Lester, H. A. Williams, B. A. Weintraub, and J. F. Brenner," Two Graph Searching Techniques for Boundary Finding in White Blood Cell Image," Computers in Biology and Mechine,8:293-308,1978
[32] A. W. C. Liew, S. H. Leung, W. H. Lau. Fuzzy image clustering incorprrating spatial continuity [J] IEE Proe Vis, Image Signal Process,2000,147(2):185～192
[33] 杨绍清等，基于模糊判决的图像边缘连接，光学技术，2002，28(2)
[34] Zhang Y J. Quantitaive image quality measures and their applications in segmentation evaluation. Journal of Electronics, 1997.14
[35] Tsai Du Ming. Boundary based corner detecting using neural networks, Pattern Recognition, 1997, 30(1): 85～97
[36] D.Marr and E.Hildrety, Theory of edge detection, Proc.ofthe Royal society of London, Vol.207, 1980
[37] 张文景等，一种基于曲率提取轮廓特征点的方法，上海交通大学学报，1999，(5)
[38] 邹国辉等，基于MAP准则的图象恢复和边缘检测方法，北方交通大学学
报，1998，(6)
[39] 郑南宁．计算机视觉与模式识别．国防工业出版社，1998
[40] 余新平等，一种具有抗噪声干扰的图像边缘提取算法的研究，电子技术应用，1999，(1)
[41] Milan Sonka, Vac]av Hlavac, Roger Boyle. Image Processing, Analysis and Machine Vision. Printed in Great britain at the University Press, Cambridge
[42] Edward Dougherty Mathematical morphology in image processing M. Dekker, New York 1993
[43] J. Serra Introduction to Mathematical Morphology Computer Vision Graphic and image processing 35 3 1986 283-305
[44] S.R. Sternberg Grayscale Morphology Computer Graphics and and image processing 35 3 1986 333-355
[45] T.R. Reed J.M.H. du Bur A Review of Recent Texture Information Computer Graphics and and image processing 57 3 1978 359-327
[46] 周凌翔，顾伟康最佳边缘检测的准则与算子模式识别与人工智能 111 1998 54～61
[47] 韩思奇，王蕾 图像分割的阈值法综述 系统工程与电子技术 24 6 2001
[48] 赵荣椿，迟耀斌，朱重光 图像分割技术进展 中国的体视学和图像分析 3 12 1998 121～128
[49] 罗希平等 图像分割方法综述 模式识别与人工智能 12 3 1999 300～312
[50] Pal N R, Pal S K A review on image segmentation techniques Pattern Recognition 26 1993 1277～1294
[2] 何斌、马天予编著，Visual C++数字图像处理。人民邮电出版社，2001。
[3] 高建贞 基于图像分析的道路病害自动检测研究，博士论文，南京理工大学，2003。
[4] 中华人民共和国行业标准，JTJ075—94，公路养护质量检查评定标准，1994。
[5] 中华人民共和国行业标准，JTJ073—96，公路养护技术规范，1996。
[6] 章硫晋，图像处理和分析，清华大学出版社，1999。
[7] 章毓晋，图像分割．科学出版社，2001。
[8] Ostu N A "Threshold Selection Method from Gray-leve histogram", IEEE Trans. On System, Man, and Cybernetics, Vol. 9, 1,1979,62-66
[9] Kapur ,Saho-p P, Wong A. "A new method for Gray-level Picture Thresholding Using the Entroy of the histogram" Computer Vision Graphics and image processing, 29, 210-239,1985
[10] M.Miyojim," Automatic pavement distress detection system", Journal of information sciences vol. 18 219-240 ,1998
[11] Randal C. Nelson," Finding line segments by stick growing" ,IEEE trans. PAMI vol. 16 No. 5, May 1994
[12] H. Lee and H. Oshima," New crack-imaging procedure using spatial autocorrelation function" ,Journal of transportation engineering ,Vol. 120, No 3, May, 1994
[13] H.N. Koutsopoulos and I.E. Sanhouri," Methods and algorithms for automated analysis of pavement images", Transportation Research Record ,1311,1991
[14] Kenneth R. Castleman," Digital image processing" ,Prentice Hal1,1996,115-138
[15] 阮秋琦，数字图像处理学，电子工业出版社，2001．1
[16] L.G. Roberts, "Machine Perception of Three-Dimension Solids," in Optical and Electro-Optimal Information Processing, J.t. Tippett, et al., Ed. Cambridge, MA: MIT Press, 1965, 99-159-197
[17] J. Prewitt, "Object Enhancement and Extraction," Picture Process. Psvchopict., 110pp.75-149, 1970.
[18] L. Sobel, "Camera Models and Machine Perception," PhD theses, Stanford University, Standford, CA, 1970
[19] Marr D著，姚国正译 视觉计算理论 科学出版社 1998
[20] Canny, John. "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986. Vol. PAMI-8, No. 6, pp. 679-698
[21] 刘杰平等，一种简易的图象去噪方法，华南理工大学学报，2000，28(2)：60～63
[22] 王廷忠，水泥混凝土路面病害及处理，林业建设，1998，(6)：32～33
[23] 周长发．精通Visum C++图像编程．电子工业出版社．2000
[24] 何斌等．Visum C++数字图像处理．人民邮电出版社．2001
[25] 王润生，图象理解，长沙：国防科技大学出版社，1995
[26] 楼伟．高等级公路路面病害识别与检测中的算法研究．西安工业学院．2001
[27] 斐继红等，基于平滑性测度的直方图自适应模糊增强图像分割，信号处理，1999，(12)
[29] 李向吉等，受噪声污染图像中的基于排序统计的非线性边缘检测器，信号处理，1999，(1)
[30] R. Nevatia," Locating Object Boundaries in Textured Environments ,"IEEE Trans.Comp.C-25:1170-1180,1976.
[31] J.M. Lester, H. A. Williams, B. A. Weintraub, and J. F. Brenner," Two Graph Searching Techniques for Boundary Finding in White Blood Cell Image," Computers in Biology and Mechine,8:293-308,1978
[32] A. W. C. Liew, S. H. Leung, W. H. Lau. Fuzzy image clustering incorprrating spatial continuity [J] IEE Proe Vis, Image Signal Process,2000,147(2):185～192
[33] 杨绍清等，基于模糊判决的图像边缘连接，光学技术，2002，28(2)
[34] Zhang Y J. Quantitaive image quality measures and their applications in segmentation evaluation. Journal of Electronics, 1997.14
[35] Tsai Du Ming. Boundary based corner detecting using neural networks, Pattern Recognition, 1997, 30(1): 85～97
[36] D.Marr and E.Hildrety, Theory of edge detection, Proc.ofthe Royal society of London, Vol.207, 1980
[37] 张文景等，一种基于曲率提取轮廓特征点的方法，上海交通大学学报，1999，(5)
[38] 邹国辉等，基于MAP准则的图象恢复和边缘检测方法，北方交通大学学
报，1998，(6)
[39] 郑南宁．计算机视觉与模式识别．国防工业出版社，1998
[40] 余新平等，一种具有抗噪声干扰的图像边缘提取算法的研究，电子技术应用，1999，(1)
[41] Milan Sonka, Vac]av Hlavac, Roger Boyle. Image Processing, Analysis and Machine Vision. Printed in Great britain at the University Press, Cambridge
[42] Edward Dougherty Mathematical morphology in image processing M. Dekker, New York 1993
[43] J. Serra Introduction to Mathematical Morphology Computer Vision Graphic and image processing 35 3 1986 283-305
[44] S.R. Sternberg Grayscale Morphology Computer Graphics and and image processing 35 3 1986 333-355
[45] T.R. Reed J.M.H. du Bur A Review of Recent Texture Information Computer Graphics and and image processing 57 3 1978 359-327
[46] 周凌翔，顾伟康最佳边缘检测的准则与算子模式识别与人工智能 111 1998 54～61
[47] 韩思奇，王蕾 图像分割的阈值法综述 系统工程与电子技术 24 6 2001
[48] 赵荣椿，迟耀斌，朱重光 图像分割技术进展 中国的体视学和图像分析 3 12 1998 121～128
[49] 罗希平等 图像分割方法综述 模式识别与人工智能 12 3 1999 300～312
[50] Pal N R, Pal S K A review on image segmentation techniques Pattern Recognition 26 1993 1277～1294
© 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 |