混凝土表面裂缝检测的多级聚类算法

董安国; 张仙艳; 薛宏智; 宋君

混凝土表面裂缝检测的多级聚类算法

长安大学理学院，陕西西安 710064

基金项目:

国家自然科学基金项目 11171043

中央高校基本科研业务费专项资金项目 CHD2011JC010

中央高校基本科研业务费专项资金项目 CHD2012TD015

详细信息

作者简介:
董安国(1964-), 男, 浙江象山人, 长安大学教授, 从事图像处理研究

中图分类号: U416.216
计量
- 文章访问数: 524
- HTML全文浏览量: 93
- PDF下载量: 1337
- 被引次数: 0
出版历程
- 收稿日期: 2013-07-01
- 刊出日期: 2013-12-25

Multi-level clustering algorithm for crack detection of concrete surface

School of Science, Chang'an University, Xi'an 710064, Shaanxi, China

More Information

Author Bio:
DONG An-guo(1964-), male, professor, +86-29-82334890, donganguo@chd.edu.cn

摘要

摘要: 为了检测混凝土表面裂缝及其宽度, 对含有裂缝的数字图像进行k-均值聚类, 提取出所有疑似裂缝的像素点, 进行了二值化处理。根据像素点的位置关系, 提取连通分量, 将连通分量作为聚类对象, 构造连通分量间的距离函数。利用谱聚类算法将连通分量聚类, 根据裂缝特征, 去掉伪裂缝部分, 得到完整的裂缝对象, 并通过局部旋转算法对裂缝的宽度进行了2次数值计算。分析结果表明: 与Canny、Sobel算子比较, 多级聚类算法在裂缝提取时能去掉较多的噪声, 抗噪能力强; 通过局部旋转算法计算裂缝宽度时, 计算值与实际值的平均相对误差分别为3.86%、2.40%, 算法精度高, 适用于各种类型裂缝宽度计算。
- 路面工程 /
- 裂缝检测 /
- 图像处理 /
- k-均值聚类 /
- 谱聚类
Abstract: In order to detect the crack and its width of concrete surface, the k-means clustering was applied for crack digital image, and binary image was got based on taking out entire suspected crack pixels from clustering results. The connected components of binary image were extracted according to the ubiety of pixels, the distance function of connected components was constructed considering connected components as clustering objects. Connected components could be clustered by spectral clustering algorithm, pseudo cracks were removed on the basis of crack features, and whole crack image was obtained. Numerical calculations of crack width were carried out twice by local rotation algorithm. Research result shows that multi-level clustering algorithm can get rid of more noises during extracting crack, and has stronger anti-noise ability compared with Canny operator and Sobel operator. When the crack width is calculated by local rotation algorithm, the average relative errors of calculated value and actual value are 3.86%and 2.40% respectively, so the algorithm has high accuracy and can be used for width calculations of all kinds of cracks.
- pavement engineering /
- crack detection /
- image processing /
- k-means clustering /
- spectral clustering

HTML全文

图 1 用相机拍摄到的裂缝

Figure 1. Cracks with camera

下载: 全尺寸图片幻灯片

图 2 聚类及二值化后的裂缝

Figure 2. Clustering and binary cracks

下载: 全尺寸图片幻灯片

图 3 用谱聚类提取后的裂缝

Figure 3. Cracks based on spectral clustering

下载: 全尺寸图片幻灯片

图 4 算子提取裂缝

Figure 4. Cracks based on operators

下载: 全尺寸图片幻灯片

图 5 复杂背景裂缝检测过程及方法对比

Figure 5. Process of crack detection with complicated background and method comparison

下载: 全尺寸图片幻灯片

图 6 裂缝示意

Figure 6. Crack sketch

下载: 全尺寸图片幻灯片

图 7 像素点拟合直线

Figure 7. Fitting line of pixels

下载: 全尺寸图片幻灯片

图 8 旋转后裂缝

Figure 8. Crack after rotating

下载: 全尺寸图片幻灯片

图 9 混凝土表面裂缝

Figure 9. Concrete surface cracks

下载: 全尺寸图片幻灯片

表 1 裂缝像素点坐标

Table 1. Coordinates of crack pixels

下载: 导出CSV

表 2 图 9(a)裂缝实际宽度与计算宽度

Table 2. Actual widths and calculated widths of crack in Fig. 9(a)

下载: 导出CSV

表 3 图 9(b)裂缝实际宽度与计算宽度

Table 3. Actual widths and calculated widths of crack in Fig. 9(b)

下载: 导出CSV

参考文献(14)

[1]	BHANDARKAR S M, LUO Xing-zhi, DANIELS R, et al. Detection of cracks in computer tomography images of logs[J]. Pattern Recognition Letters, 2005, 26(14): 2282-2294. doi: 10.1016/j.patrec.2005.04.004
[2]	CHENG H D, SHI X J, GLAZIER C. Real-time image thresholding based on sample space reduction and interpolation approach[J]. Journal of Computing in Civil Engineering, 2003, 17(4): 264-272. doi: 10.1061/(ASCE)0887-3801(2003)17:4(264)
[3]	邹勤, 李清泉, 毛庆洲, 等. 利用目标点最小生成树的路面裂缝检测[J]. 武汉大学学报: 信息科学版, 2011, 36(1): 71-75. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201101017.htm ZOU Qin, LI Qing-quan, MAO Qing-zhou, et al. Targetpoints MST for pavement crack detection[J]. Geomatics and Information Science of Wuhan University, 2011, 36(1): 71-75. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201101017.htm
[4]	王兴建, 秦国锋, 赵慧丽. 基于多级去噪模型的路面裂缝检测方法[J]. 计算机应用, 2010, 30(6): 1606-1609, 1612. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201006051.htm WANG Xing-jian, QIN Guo-feng, ZHAO Hui-li. Pavement crack detection method based on multilevel denosing model[J]. Journal of Computer Applications, 2010, 30(6): 1606-1609, 1612. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201006051.htm
[5]	段跃华, 张肖宁, 李智, 等. 基于工业CT的混凝土集料二维及三维轮廓表征方法[J]. 中国公路学报, 2011, 24(6): 9-15. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201106004.htm DUAN Yue-hua, ZHANG Xiao-ning, LI Zhi, et al. Methods about digital representation on surface profile of concrete aggregates from 2-D to 3-D based on X-ray computed tomography[J]. China Journal of Highway and Transport, 2011, 24(6): 9-15. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201106004.htm
[6]	万成, 张肖宁, 贺玲凤, 等. 沥青混合料动态模量数值预测方法[J]. 中国公路学报, 2012, 25(4): 16-28. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201204003.htm WAN Cheng, ZHANG Xiao-ning, HE Ling-feng, et al. Numerical prediction method for dynamic modulus of asphalt mixture[J]. China Journal of Highway and Transport, 2012, 25(4): 16-28. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201204003.htm
[7]	ABDEL-QADER I, ABUDAYYEH O, KELLY M E. Analysis of edge-detection techniques for crack identification in bridges[J]. Journal of Computing in Civil Engineering, 2003, 17(4): 255-263.
[8]	ROSALES M B, FILIPICH C P, BUEZAS F S. Crack detection in beam-like structures[J]. Engineering Structures, 2009, 31(10): 2257-2264.
[9]	ZHANG Hong, DONG An-guo, XU Zhi-gang, et al. Seeds moving algorithm and its application on bridge crack detection[C]//IEEE. 2010 3rd International Conference on Power Electronics and Intelligent Transportation System. Shenzhen: IEEE, 2010: 270-274. (in Chinese).
[10]	查旭东, 王文强. 基于图像处理技术的连续配筋混凝土路面裂缝宽度检测方法[J]. 长沙理工大学学报: 自然科学版, 2007, 4(1): 13-17. https://www.cnki.com.cn/Article/CJFDTOTAL-HNQG200701002.htm ZHA Xu-dong, WANG Wen-qiang. The testing method of crack width for continuously reinforced concrete pavement based on image processing technique[J]. Journal of Changsha University of Science and Technology: Natural Science, 2007, 4(1): 13-17. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-HNQG200701002.htm
[11]	卢晓霞. 基于图像处理的混凝土裂缝宽度检测技术的研究[D]. 成都: 电子科技大学, 2010. LU Xiao-xia. Concrete crack width detection technology based on image processing[D]. Chengdu: University of Electronic Science and Technology of China, 2010. (in Chinese).
[12]	MACQUEEN J. Some methods for classification and analysis of multivariate observations[C]//University of California Press. Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability. Berkeley: University of California Press, 1967: 281-297.
[13]	田铮, 李小斌, 句彦伟. 谱聚类的扰动分析[J]. 中国科学E辑: 信息科学, 2007, 37(4): 527-543. https://www.cnki.com.cn/Article/CJFDTOTAL-JEXK200704004.htm TIAN Zheng, LI Xiao-bin, GOU Yan-wei. Perturbation analysis of spectral clustering[J]. Science in China Series E: Information Sciences, 2007, 37(4): 527-543. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JEXK200704004.htm
[14]	REGE M, DONG Ming, FOTOUHI F. Bipartite isoperimetric graph partitioning for data co-clustering[J]. Data Mining and Knowledge Discovery, 2008, 16(3): 276-312.