沥青路面裂缝图像检测算法研究
|
摘要
路面破损检测是高速公路养护与管理工作中很重要的一部分,但我国在路面破损检测方面运用的仍然是传统方法,已不能满足高速公路路面养护与管理的需求。论文基于国内公路交通行业发展的迫切需要,探讨了针对沥青路面裂缝类破损的图像检测算法及系统。论文的主要工作和取得的研究成果有:
(1)针对路面图像中裂缝目标和背景区域灰度值相近,不利于裂缝目标的提取,将模糊集合理论引入到沥青路面裂缝检测中,提出了一种封闭性和移植性好的广义模糊变换算子,并将其应用于图像增强算法中,可以很好地增强裂缝边缘的信息。
(2)针对实际应用中很难兼顾边缘提取算法的图像处理效果和速度,利用梯度算子获得图像中的感兴趣区域,再构造四种结构元素,结合形态学梯度和OTSU算子提取感兴趣区域的边缘,提出了一种改进的数学形态学边缘检测算法,其不仅具有很好的边缘提取能力,而且具有很快的处理速度。
(3)对提取出的物体进行标识和统计,将统计出的噪声滤除,通过区域填充技术弥合裂缝中的空隙,并对处理后的裂缝进行分类。然后对规则裂缝进行细化,通过计数的方法计算出规则裂缝的长度和宽度,或通过蚕食方法计算出不规则裂缝的面积。
(4)基于图像处理技术设计了一种沥青路面裂缝检测系统。在Visual C++ 6.0软件开发环境下,借助Mil-Lite 8.0软件开发包,实现了系统的各个模块及相关的图像处理算法。并将该系统应用于沥青路面裂缝检测,实验结果表明,该系统检测效果好、检测精度高,具有很高的实用性和推广性。
Pavement distress detection plays an important role in the highway management and maintenance. But the traditional method for the pavement distress detection is still used in our nation. This method has many disadvantages, which disatisfies with the requirement for the highway management and maintenance. Based on that the highway construction and transit is urgently in need of the automation management, the image detecting algorithms and system are discussed for the asphalt pavement crack in this thesis. The main work and accomplishment are as follows:
(1) The gray of the crack target is close to that of the background region, so it is very hard to pick up the crack target. In order to solve this problem, the fuzzy set theory is introduced to crack detection for the asphalt pavement. A novel generalized fuzzy image enhancement operator with close-character and transplantable-character is proposed. Then the presented operator is applied to image enhancement algorithm, which can enhance the crack edge better.
(2) In the practical applications, it is difficult to make a balance between processing effect and processing speed for the edge detection algorithm. In order to solve this problem, a novel edge detection algorithm is presented based on the mathematics morphology. The proposed algorithm employs the gradient operator to gain the interested regions in the image. Based on the morphology-gradient operator and OTSU segmentation operator, then the proposed algorithm constructs four structural elements to detect the edges in interested regions. This algorithm has not only a good ability to extract the image edge, but also a fast speed ability to process the image.
(3) The extracted objects are marked and computed, and the marked noises are filtered. The interspaces of the crack are filled by region filling method. Then the gained cracks are classified as regular cracks and irregular cracks. At last, the length and width of the thinned regular crack are obtained by counting method, or the area of the irregular crack is obtained by nibbling method.
(4) A novel crack detecting system for the asphalt pavement is proposed based on the image processing technology. In the programming environment of Visual C++ 6.0, the corresponding modules and image processing algorithms are implemented by dint of Mil 8.0 SDK. Finally, this system is applied to the asphalt pavement crack image detection experiment, and the experiment result is satisfactory. So the presented system has very high practicability and generality.
(1)针对路面图像中裂缝目标和背景区域灰度值相近,不利于裂缝目标的提取,将模糊集合理论引入到沥青路面裂缝检测中,提出了一种封闭性和移植性好的广义模糊变换算子,并将其应用于图像增强算法中,可以很好地增强裂缝边缘的信息。
(2)针对实际应用中很难兼顾边缘提取算法的图像处理效果和速度,利用梯度算子获得图像中的感兴趣区域,再构造四种结构元素,结合形态学梯度和OTSU算子提取感兴趣区域的边缘,提出了一种改进的数学形态学边缘检测算法,其不仅具有很好的边缘提取能力,而且具有很快的处理速度。
(3)对提取出的物体进行标识和统计,将统计出的噪声滤除,通过区域填充技术弥合裂缝中的空隙,并对处理后的裂缝进行分类。然后对规则裂缝进行细化,通过计数的方法计算出规则裂缝的长度和宽度,或通过蚕食方法计算出不规则裂缝的面积。
(4)基于图像处理技术设计了一种沥青路面裂缝检测系统。在Visual C++ 6.0软件开发环境下,借助Mil-Lite 8.0软件开发包,实现了系统的各个模块及相关的图像处理算法。并将该系统应用于沥青路面裂缝检测,实验结果表明,该系统检测效果好、检测精度高,具有很高的实用性和推广性。
Pavement distress detection plays an important role in the highway management and maintenance. But the traditional method for the pavement distress detection is still used in our nation. This method has many disadvantages, which disatisfies with the requirement for the highway management and maintenance. Based on that the highway construction and transit is urgently in need of the automation management, the image detecting algorithms and system are discussed for the asphalt pavement crack in this thesis. The main work and accomplishment are as follows:
(1) The gray of the crack target is close to that of the background region, so it is very hard to pick up the crack target. In order to solve this problem, the fuzzy set theory is introduced to crack detection for the asphalt pavement. A novel generalized fuzzy image enhancement operator with close-character and transplantable-character is proposed. Then the presented operator is applied to image enhancement algorithm, which can enhance the crack edge better.
(2) In the practical applications, it is difficult to make a balance between processing effect and processing speed for the edge detection algorithm. In order to solve this problem, a novel edge detection algorithm is presented based on the mathematics morphology. The proposed algorithm employs the gradient operator to gain the interested regions in the image. Based on the morphology-gradient operator and OTSU segmentation operator, then the proposed algorithm constructs four structural elements to detect the edges in interested regions. This algorithm has not only a good ability to extract the image edge, but also a fast speed ability to process the image.
(3) The extracted objects are marked and computed, and the marked noises are filtered. The interspaces of the crack are filled by region filling method. Then the gained cracks are classified as regular cracks and irregular cracks. At last, the length and width of the thinned regular crack are obtained by counting method, or the area of the irregular crack is obtained by nibbling method.
(4) A novel crack detecting system for the asphalt pavement is proposed based on the image processing technology. In the programming environment of Visual C++ 6.0, the corresponding modules and image processing algorithms are implemented by dint of Mil 8.0 SDK. Finally, this system is applied to the asphalt pavement crack image detection experiment, and the experiment result is satisfactory. So the presented system has very high practicability and generality.
引文
[1]高建贞,任明武,唐振民.路面裂缝的自动检测与识别[J].计算机工程, 2003, 29(2): 149-150.
[2] Yong Gen Huang, Howard Tillotson, Martin Snaith. Massively Parallel Computing Techniques Might Improve Highway Maintenance[J]. IEEE Concurrency, 1998, 6(1): 58-67.
[3] Cheng H. D., Miyojim M.. Automatic Pavement Distress Detection System[J]. Journal of Information Sciences, 1998, 108(1-4): 219-240.
[4] Cheng H. D., Miyojim M.. Novel System For Automatic Pavement Distress Detection[J]. Journal of Computing in Civil Engineering, 1998, 12(3): 145-152.
[5] Tomikawa T.. Study of Road Crack Detection by the Meta-genetic Algorithm[C]. IEEE AFRICON Conference, Cape Town, S Afr, Sep 28-Oct 1 1999: 543-548.
[6] Cuhadar A., Shalaby A., Tasdoken S.. Automatic Segmentation of Pavement Condition Data Using Wavelet Transform[C]. Canadian Conference on Electrical and Computer Engineering, Winipeg, Manitoba, May 12-15 2002: 1009-1014.
[7] De L. E., Flintsch G. W.. A Non-contact System to Detect and Quantify Segregation in Hot Mix Asphalt Pavements[C]. Applications of Advanced Technology in Transportation - Proceedings of the Ninth International Conference on Applications of Advanced Technology in Transportation, Chicago, IL, United States, Aug 13-16 2006: 93-98.
[8]潘玉利.路面管理系统[M].人民交通出版社, 2000.
[9] Fukuhara. Automatic Pavement-distress-survey System[J]. Journal of Transportation Engineering, 1990, 116(3): 280-286.
[10] Wang Kelvin C. P.. Designs and Implementations of Automated Systems for Pavement Surface Distress Survey[J]. Journal of Infrastructure Systems, 2000, 6(1): 24-32.
[11] Offrell P.. Automatic Crack Measurement in Sweden Pavement Surface Characteristics[C]. IVth International Symposium"SURF 2000", Nantes, France, May 22-24 2000: 497-506.
[12] Wang Kelvin C. P., Elliott R. P.. Investigation of Image Archiving for Pavement Surface Distress Survey[R]: A final report submitted to Mack-Blackwell Transportation Center. July, 1999.
[13]李晋惠.用图像处理的方法检测公路路面裂缝类病害[J].长安大学学报(自然科学版), 2004, 24(3): 24-29.
[14]李晋惠,楼伟.基于CCD的公路路面病害检测技术研究[J].西安工业大学学报, 2002, 22(2): 95-99.
[15]王荣本等.路面破损图像识别研究进展[J].吉林大学学报, 2002, 32(4):91-97.
[16]初秀民,王荣本,储江伟等.沥青路面破损图像分割方法研究[J].中国公路学报, 2003, 16(3):11-14.
[17]施树明,初秀民,王荣本.沥青路面破损图像测量方法研究[J].公路交通科技,2004, 21(7):12-16.
[18]储江伟,初秀民,王荣本.沥青路面破损图像自动检测系统设计[J].光学技术, 2003, 29(3): 316-319.
[19]候相深,王哲人,刘振鹏.路面损坏图像的自动采集与处理设备的技术探究[J].公路, 2003(2): 66-69.
[20]黄卫,肖旺新,路小波等.基于图像子块分布特性的路面破损图像特征提取.土木工程学报, 2005, 38(10): 54-60.
[21]李弼程,郭志刚,文超.图像的多层次模糊增强与边缘提取[J].模糊系统与数学, 2000, 14(4): 77-83.
[22]周德龙,赵志国.基于模糊集的图像增强算法研究[J].电子与信息学报, 2002, 24(7): 905-909.
[23]王保平,李宗领,谢维信.基于区域信息的模糊加权图像恢复方法[J].计算机工程, 2003, 29(19): 11-12,108.
[24]王保平,刘怀亮,李南京等.一种新的自适应图像模糊增强算法[J]. 2005, 32(2): 307-313.
[25]王保平,刘升虎,范九伦.基于模糊熵的自适应图像多层次模糊增强算法[J].电子学报, 2005, 33(4): 730-734.
[26]石振刚,高立群.一种基于模糊逻辑的图像多层次增强算法[J].控制工程, 2006, 13(5):463-465.
[27]刘玉臣,王国强,林建荣.基于模糊理论的路面裂缝图像增强方法[J].筑路机械与施工机械化, 2006, 23(2): 35-37.
[28]程丹松,黄建华,于志国等.基于模糊理论的医学图像增强方法[J].哈尔滨工业大学学报, 2007, 39(3): 435-437.
[29] Pal S. K., King R. A.. Image Enhancement Using Fuzzy Sets[J]. Electron. Lett., 1980, 16(9): 376-378.
[30] Pal S. K., King R. A.. Image Enhancement Using Smoothingwith Fuzzy Sets[J]. IEEE Trans. Syst. Man. Cybern., 1981, 11(7): 494-501.
[31] Pal S. K., King R. A.. On Edge Detection X-ray Iamges Using Fuzzy Sets[J]. IEEE Trans. Patt Anal and MachineIntell, 1983, 5(1): 67-69.
[32]付忠良.图像阈值选取方法-OTSU方法的推广[J].计算机应用, 2000, 20(5): 37-39.
[33]陈武凡.彩色图像边缘检测的新算法-广义模糊算子法[J].中国科学(A辑), 1995, 25(2): 219-224.
[34] (美)Castleman K. R.著.朱志刚译.数字图像处理[M].北京:电子工业出版社, 1998: 387-392.
[35]初秀民,王荣本.基于神经网络的沥青路面破损图像识别研究[J].武汉理工大学学报(交通科学与工程版), 2004, 28(3): 373-376.
[36]侯相深,王哲人,杨泽众.路面损坏的图像处理算法浅析[J].公路, 2003, 47(3): 41-44.
[37]初秀民,王荣本,储江伟等.基于不变矩特征的沥青路面破损图像识别[J].吉林大学学报(工学版), 2003, 33(1): 1-7.
[38]初秀民,王荣本,李斌等.路面破损图像几何畸变校正技术研究[J].公路交通科技, 2002, 19(4): 22-26.
[39] Zaremba M. B., Palenichka R. M., Missaoui, et al. Multi-scale Morphological Modeling of A Class of Structural Texture[J]. Machine Graphics and Vision, 2005, 14(2): 171-199.
[40] Guo Xiaoxin, Xu Zhiwen, Pang Yunjie. An Adaptive Soft Morphological Gradient Filter for Edge Detection[C]. IEEE Image and Graphics, Third International Conference, Hong Kong, China, Dec 18-20 2004, 64-67.
[41] Gao H., Siu W., Hou C.. Improved Techniques for Automatic Image Segmentation[J]. IEEE Trans.Circuits and Systems for Video Technology, 2001, 11(12): 1273-1280.
[42]姜涌,曹杰,杜亚玲等.基于形态学梯度矢量的图像边缘提取算法[J].南京航空航天大学学报, 2005, 37(6): 771-775.
[43]付永庆,王咏胜.一种基于数学形态学的灰度图像边缘检测算法[J].哈尔滨工程大学学报, 2005, 26(5): 685-687.
[44]雷艳敏,黄秋元.基于数学形态学的图像边缘检测[J].武汉理工大学学报(信息与管理工程版), 2005, 25(5): 25-26.
[45]王吉晖,金伟其,王霞等.基于数学形态学的像增强器缺陷的图像检测方法[J].光学技术, 2005, 31(3): 463-464, 467.
[46]陈虎,周朝辉,王守尊.基于数学形态学的图像去噪方法研究[J].工程图学学报, 2004, 25(2): 116-119.
[47]梁勇,李天牧.多方位形态学结构元素在图像边缘检测中的应用[J].云南大学学报(自然科学版), 1999, 21(5): 392-394.
[48] Poggio T., Voorhees H., Yuille A.. A Regularized Solution to Edge Detection[R]. Tech. Rep. MA, Rep. AIM-833, MIT Artificial Intell. Lab., May 1985.
[49] Nalwa V. S., Binford T. O.. On Detectiong Edge[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(6): 699-714.
[50]章毓晋.图像工程(上册)图像处理和分析[M],北京:清华大学出版社, 1999.
[51] Lee, Byoung Jik. Position-invariant Neural Network for Digital Pavement Crack Analysis[J]. Computer-Aided Civil and Infrastructure Engineering, 2004, 19(3): 105-118.
[52]匡蕴娟,张圣希.多种链编码在数字图像中的标定算法[J].计算机应用研究, 2007, 24(2): 160-162.
[53]顾国庆,许彦冰.数字图像区域标定的方法[J].上海理工大学学报, 2001, 23(4): 295-299.
[54]张娟,沙爱民,高怀钢等.基于数字图像处理的路面裂缝自动识别与评价系统[J].长安大学学报(自然科学版): 2004, 24(2): 18-22.
[55]程民德.图像识别导论[M].上海科学技术出版社, 1983.
[56]边肈祺,张学工等.模式识别(第二版)[M].清华大学出版社, 2000.
[57] Richard O Duda, Peter E Hart, David G Stork.模式分类(英文:第二版)[M].机械工业出版社, 2004.
[58] Meignen D., Bernadet M., Briand H.. One Application of Neural Networks for Detection of Defects Using Video Data Base: Identification of Road Distress[C]. Proceedings of the 1997 8th International Workshop on Database and Expert Systems Applications, DEXA'97, Toulouse, Fr, Sep 1-2 1997, 459-464.
[59] Cheng H. D.. Automated Real-time Pavement Distress Detection Using Fuzzy Logic and Neural Networks[J]. SPIE Proceeding, 1994, 2946: 140～151.
[60] Chou JaChing, Cheng H. D.. Pavement Distress Classification Using Neural Networks[C]. Proceedings of the 1994 IEEE International Conference on Systems, Man and Cybernetics. Part 1(of 3), San Antonio, TX, USA, Oct 2-5 1994, VI: 397-401.
[61] Kaseko Mohamed S, Ritchie,Stephen G. Pavement Image Processing Using Neural Networks[C]. Proceedings of the 2nd International Conference on Applications of Advanced Technologies in Transportation Engineering, Minneapolis, MN, USA, Aug 18-21 1991, 238-242.
[62] Xiao Wangxin, Yan Xinping, Zhang Xue. Pavement Distress Image Automatic Classification Based on DENSITY-based Neural Network[C]. First International Conference on Rough Sets and Knowledge Technology, RSKT 2006, Chongqing, China, Jul 24-26 2006, 685-692.
[63] Kaseko M. S., Ritchie S. G.. A Neural Networks-Based Methodology for pavement Crack Detecion and Classification[J]. Transportation Research, 1993, 10(4): 275-291.
[64] Kaseko M. S., Lo Zhen-Ping. Ritchie S. G.. Comparison of Traditional and Neural Classifiers for Automated Crack Detection[J]. ASCE, 1994, 120(4): 552～569.
[65]熊和金.路面破损诊断的神经网络方法[J].公路交通科技, 2001, 18(1): 10-12.
[66] Huang Y., Xu B.. An Automatic Pavement Surface Distress Inspection System[J]. Journal of ASTM International, 2005, 2(10): 31-41.
[67] Huang Yaxiong, Xu Bugao. Automatic Inspection of Pavement Cracking Distress[J]. Journal of Electronic Imaging, 2006, 15(1): 13-17.
[68]皮燕妮,史忠科,黄金.智能车视觉导航的道路和前车检测系统[J].计算机工程, 2005, 31(25): 186-188.
[69]纪天明,贺跃,于同等.智能车辆导航系统中的实时道路检测[J].计算机应用, 2005, 25(12): 228-230, 232.
[70]李刚,潘玉利.路面快速检测技术与设备研究进展及分析[J].公路交通科技, 2005, 22(9):35-39.
[2] Yong Gen Huang, Howard Tillotson, Martin Snaith. Massively Parallel Computing Techniques Might Improve Highway Maintenance[J]. IEEE Concurrency, 1998, 6(1): 58-67.
[3] Cheng H. D., Miyojim M.. Automatic Pavement Distress Detection System[J]. Journal of Information Sciences, 1998, 108(1-4): 219-240.
[4] Cheng H. D., Miyojim M.. Novel System For Automatic Pavement Distress Detection[J]. Journal of Computing in Civil Engineering, 1998, 12(3): 145-152.
[5] Tomikawa T.. Study of Road Crack Detection by the Meta-genetic Algorithm[C]. IEEE AFRICON Conference, Cape Town, S Afr, Sep 28-Oct 1 1999: 543-548.
[6] Cuhadar A., Shalaby A., Tasdoken S.. Automatic Segmentation of Pavement Condition Data Using Wavelet Transform[C]. Canadian Conference on Electrical and Computer Engineering, Winipeg, Manitoba, May 12-15 2002: 1009-1014.
[7] De L. E., Flintsch G. W.. A Non-contact System to Detect and Quantify Segregation in Hot Mix Asphalt Pavements[C]. Applications of Advanced Technology in Transportation - Proceedings of the Ninth International Conference on Applications of Advanced Technology in Transportation, Chicago, IL, United States, Aug 13-16 2006: 93-98.
[8]潘玉利.路面管理系统[M].人民交通出版社, 2000.
[9] Fukuhara. Automatic Pavement-distress-survey System[J]. Journal of Transportation Engineering, 1990, 116(3): 280-286.
[10] Wang Kelvin C. P.. Designs and Implementations of Automated Systems for Pavement Surface Distress Survey[J]. Journal of Infrastructure Systems, 2000, 6(1): 24-32.
[11] Offrell P.. Automatic Crack Measurement in Sweden Pavement Surface Characteristics[C]. IVth International Symposium"SURF 2000", Nantes, France, May 22-24 2000: 497-506.
[12] Wang Kelvin C. P., Elliott R. P.. Investigation of Image Archiving for Pavement Surface Distress Survey[R]: A final report submitted to Mack-Blackwell Transportation Center. July, 1999.
[13]李晋惠.用图像处理的方法检测公路路面裂缝类病害[J].长安大学学报(自然科学版), 2004, 24(3): 24-29.
[14]李晋惠,楼伟.基于CCD的公路路面病害检测技术研究[J].西安工业大学学报, 2002, 22(2): 95-99.
[15]王荣本等.路面破损图像识别研究进展[J].吉林大学学报, 2002, 32(4):91-97.
[16]初秀民,王荣本,储江伟等.沥青路面破损图像分割方法研究[J].中国公路学报, 2003, 16(3):11-14.
[17]施树明,初秀民,王荣本.沥青路面破损图像测量方法研究[J].公路交通科技,2004, 21(7):12-16.
[18]储江伟,初秀民,王荣本.沥青路面破损图像自动检测系统设计[J].光学技术, 2003, 29(3): 316-319.
[19]候相深,王哲人,刘振鹏.路面损坏图像的自动采集与处理设备的技术探究[J].公路, 2003(2): 66-69.
[20]黄卫,肖旺新,路小波等.基于图像子块分布特性的路面破损图像特征提取.土木工程学报, 2005, 38(10): 54-60.
[21]李弼程,郭志刚,文超.图像的多层次模糊增强与边缘提取[J].模糊系统与数学, 2000, 14(4): 77-83.
[22]周德龙,赵志国.基于模糊集的图像增强算法研究[J].电子与信息学报, 2002, 24(7): 905-909.
[23]王保平,李宗领,谢维信.基于区域信息的模糊加权图像恢复方法[J].计算机工程, 2003, 29(19): 11-12,108.
[24]王保平,刘怀亮,李南京等.一种新的自适应图像模糊增强算法[J]. 2005, 32(2): 307-313.
[25]王保平,刘升虎,范九伦.基于模糊熵的自适应图像多层次模糊增强算法[J].电子学报, 2005, 33(4): 730-734.
[26]石振刚,高立群.一种基于模糊逻辑的图像多层次增强算法[J].控制工程, 2006, 13(5):463-465.
[27]刘玉臣,王国强,林建荣.基于模糊理论的路面裂缝图像增强方法[J].筑路机械与施工机械化, 2006, 23(2): 35-37.
[28]程丹松,黄建华,于志国等.基于模糊理论的医学图像增强方法[J].哈尔滨工业大学学报, 2007, 39(3): 435-437.
[29] Pal S. K., King R. A.. Image Enhancement Using Fuzzy Sets[J]. Electron. Lett., 1980, 16(9): 376-378.
[30] Pal S. K., King R. A.. Image Enhancement Using Smoothingwith Fuzzy Sets[J]. IEEE Trans. Syst. Man. Cybern., 1981, 11(7): 494-501.
[31] Pal S. K., King R. A.. On Edge Detection X-ray Iamges Using Fuzzy Sets[J]. IEEE Trans. Patt Anal and MachineIntell, 1983, 5(1): 67-69.
[32]付忠良.图像阈值选取方法-OTSU方法的推广[J].计算机应用, 2000, 20(5): 37-39.
[33]陈武凡.彩色图像边缘检测的新算法-广义模糊算子法[J].中国科学(A辑), 1995, 25(2): 219-224.
[34] (美)Castleman K. R.著.朱志刚译.数字图像处理[M].北京:电子工业出版社, 1998: 387-392.
[35]初秀民,王荣本.基于神经网络的沥青路面破损图像识别研究[J].武汉理工大学学报(交通科学与工程版), 2004, 28(3): 373-376.
[36]侯相深,王哲人,杨泽众.路面损坏的图像处理算法浅析[J].公路, 2003, 47(3): 41-44.
[37]初秀民,王荣本,储江伟等.基于不变矩特征的沥青路面破损图像识别[J].吉林大学学报(工学版), 2003, 33(1): 1-7.
[38]初秀民,王荣本,李斌等.路面破损图像几何畸变校正技术研究[J].公路交通科技, 2002, 19(4): 22-26.
[39] Zaremba M. B., Palenichka R. M., Missaoui, et al. Multi-scale Morphological Modeling of A Class of Structural Texture[J]. Machine Graphics and Vision, 2005, 14(2): 171-199.
[40] Guo Xiaoxin, Xu Zhiwen, Pang Yunjie. An Adaptive Soft Morphological Gradient Filter for Edge Detection[C]. IEEE Image and Graphics, Third International Conference, Hong Kong, China, Dec 18-20 2004, 64-67.
[41] Gao H., Siu W., Hou C.. Improved Techniques for Automatic Image Segmentation[J]. IEEE Trans.Circuits and Systems for Video Technology, 2001, 11(12): 1273-1280.
[42]姜涌,曹杰,杜亚玲等.基于形态学梯度矢量的图像边缘提取算法[J].南京航空航天大学学报, 2005, 37(6): 771-775.
[43]付永庆,王咏胜.一种基于数学形态学的灰度图像边缘检测算法[J].哈尔滨工程大学学报, 2005, 26(5): 685-687.
[44]雷艳敏,黄秋元.基于数学形态学的图像边缘检测[J].武汉理工大学学报(信息与管理工程版), 2005, 25(5): 25-26.
[45]王吉晖,金伟其,王霞等.基于数学形态学的像增强器缺陷的图像检测方法[J].光学技术, 2005, 31(3): 463-464, 467.
[46]陈虎,周朝辉,王守尊.基于数学形态学的图像去噪方法研究[J].工程图学学报, 2004, 25(2): 116-119.
[47]梁勇,李天牧.多方位形态学结构元素在图像边缘检测中的应用[J].云南大学学报(自然科学版), 1999, 21(5): 392-394.
[48] Poggio T., Voorhees H., Yuille A.. A Regularized Solution to Edge Detection[R]. Tech. Rep. MA, Rep. AIM-833, MIT Artificial Intell. Lab., May 1985.
[49] Nalwa V. S., Binford T. O.. On Detectiong Edge[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(6): 699-714.
[50]章毓晋.图像工程(上册)图像处理和分析[M],北京:清华大学出版社, 1999.
[51] Lee, Byoung Jik. Position-invariant Neural Network for Digital Pavement Crack Analysis[J]. Computer-Aided Civil and Infrastructure Engineering, 2004, 19(3): 105-118.
[52]匡蕴娟,张圣希.多种链编码在数字图像中的标定算法[J].计算机应用研究, 2007, 24(2): 160-162.
[53]顾国庆,许彦冰.数字图像区域标定的方法[J].上海理工大学学报, 2001, 23(4): 295-299.
[54]张娟,沙爱民,高怀钢等.基于数字图像处理的路面裂缝自动识别与评价系统[J].长安大学学报(自然科学版): 2004, 24(2): 18-22.
[55]程民德.图像识别导论[M].上海科学技术出版社, 1983.
[56]边肈祺,张学工等.模式识别(第二版)[M].清华大学出版社, 2000.
[57] Richard O Duda, Peter E Hart, David G Stork.模式分类(英文:第二版)[M].机械工业出版社, 2004.
[58] Meignen D., Bernadet M., Briand H.. One Application of Neural Networks for Detection of Defects Using Video Data Base: Identification of Road Distress[C]. Proceedings of the 1997 8th International Workshop on Database and Expert Systems Applications, DEXA'97, Toulouse, Fr, Sep 1-2 1997, 459-464.
[59] Cheng H. D.. Automated Real-time Pavement Distress Detection Using Fuzzy Logic and Neural Networks[J]. SPIE Proceeding, 1994, 2946: 140～151.
[60] Chou JaChing, Cheng H. D.. Pavement Distress Classification Using Neural Networks[C]. Proceedings of the 1994 IEEE International Conference on Systems, Man and Cybernetics. Part 1(of 3), San Antonio, TX, USA, Oct 2-5 1994, VI: 397-401.
[61] Kaseko Mohamed S, Ritchie,Stephen G. Pavement Image Processing Using Neural Networks[C]. Proceedings of the 2nd International Conference on Applications of Advanced Technologies in Transportation Engineering, Minneapolis, MN, USA, Aug 18-21 1991, 238-242.
[62] Xiao Wangxin, Yan Xinping, Zhang Xue. Pavement Distress Image Automatic Classification Based on DENSITY-based Neural Network[C]. First International Conference on Rough Sets and Knowledge Technology, RSKT 2006, Chongqing, China, Jul 24-26 2006, 685-692.
[63] Kaseko M. S., Ritchie S. G.. A Neural Networks-Based Methodology for pavement Crack Detecion and Classification[J]. Transportation Research, 1993, 10(4): 275-291.
[64] Kaseko M. S., Lo Zhen-Ping. Ritchie S. G.. Comparison of Traditional and Neural Classifiers for Automated Crack Detection[J]. ASCE, 1994, 120(4): 552～569.
[65]熊和金.路面破损诊断的神经网络方法[J].公路交通科技, 2001, 18(1): 10-12.
[66] Huang Y., Xu B.. An Automatic Pavement Surface Distress Inspection System[J]. Journal of ASTM International, 2005, 2(10): 31-41.
[67] Huang Yaxiong, Xu Bugao. Automatic Inspection of Pavement Cracking Distress[J]. Journal of Electronic Imaging, 2006, 15(1): 13-17.
[68]皮燕妮,史忠科,黄金.智能车视觉导航的道路和前车检测系统[J].计算机工程, 2005, 31(25): 186-188.
[69]纪天明,贺跃,于同等.智能车辆导航系统中的实时道路检测[J].计算机应用, 2005, 25(12): 228-230, 232.
[70]李刚,潘玉利.路面快速检测技术与设备研究进展及分析[J].公路交通科技, 2005, 22(9):35-39.