一种基于多尺度脊边缘的沥青路面裂缝检测算法

王世芳, 车艳丽, 李楠, 徐志刚, 安毅生

中国公路学报 ›› 2017, Vol. 30 ›› Issue (4) : 32-41.

PDF全文下载(4226 KB)
PDF全文下载(4226 KB)
中国公路学报 ›› 2017, Vol. 30 ›› Issue (4) : 32-41.
道路工程

一种基于多尺度脊边缘的沥青路面裂缝检测算法

  • 王世芳1, 车艳丽2, 李楠2, 徐志刚2, 安毅生2
作者信息 +

Asphalt Pavement Crack Detection Algorithm Based on Multi-scale Ridges

  • WANG Shi-fang1, CHE Yan-li2, LI Nan2, XU Zhi-gang2, AN Yi-sheng2
Author information +
文章历史 +

摘要

为了提高沥青路面裂缝的检测精度,针对裂缝的复杂性和多态性,提出了一种普适性较好的基于多尺度脊边缘的沥青路面裂缝检测算法。首先,对路面不同形状裂缝的多种脊边缘特征进行分析,并对利用高斯函数及其导数检测脊边缘的原理进行了推导;其次,根据脊边缘的多尺度特性,采用多个尺度的高斯滤波器对图像中的多尺度脊边缘进行检测,并对各个尺度的检测结果进行像素级融合;然后,结合裂缝的长度、宽度、方向、连续性、线性度等特征去除伪裂缝;最后,利用最小生成树算法实现了检测图像上不同位置裂缝的连接,使得检测出的裂缝更加接近实际裂缝的形态。研究结果表明:提出的算法可以对不同形状特征、尺寸和位置的裂缝目标进行有效检测,具有较高的检测精度和较好的检测效果,且该算法抗噪性能好、通用性强,是一种具有工程应用前景的高效的沥青路面裂缝检测方法。

Abstract

Aimed at the complexity and polymorphism of pavement cracks, an asphalt pavement crack detection algorithm based on multi-scale ridges was proposed to improve the accuracy of the crack detection. Firstly, the ridge-like characteristics of pavement cracks were analyzed and the principle of ridge detection on the basis of the Gaussian function and its derivative was deduced. Secondly, the multi-scale ridges in the image were detected by a series of multi-scale Gaussian filters according to multi-scale characteristics and then the pixel-level image fusion was conducted on the detected ridges to mark all the probable cracks. Thirdly, pseudo-cracks were removed combined with the shape features including length, width, direction, continuity, linearity and other parameters. At last, based on the minimum spanning tree algorithm, the linear cracks on different positions of the image were connected, so detected cracks were similar with the actual ones. The results show that the proposed algorithm can effectively detect the crack objects with different shape features, size and position. The detection precision is high with good detection effects. At the same time, with good anti-noise performance and robustness at different types of pavement images, the algorithm, a promising method of pavement crack detection can be used in road maintenance engineering.

关键词

道路工程 / 路面裂缝检测 / 脊边缘 / 多尺度 / 像素融合

Key words

road engineering / pavement crack detection / ridge / multi-scale / pixel-level fusion

引用本文

导出引用
王世芳, 车艳丽, 李楠, 徐志刚, 安毅生. 一种基于多尺度脊边缘的沥青路面裂缝检测算法[J]. 中国公路学报, 2017, 30(4): 32-41
WANG Shi-fang, CHE Yan-li, LI Nan, XU Zhi-gang, AN Yi-sheng. Asphalt Pavement Crack Detection Algorithm Based on Multi-scale Ridges[J]. China Journal of Highway and Transport, 2017, 30(4): 32-41
中图分类号: U418.6   

参考文献

[1] SUBIRATS P,FABRE O,DUMOULIN J,et al.A Combined Wavelet-based Image Processing Method for Emergent Crack Detection on Pavement Surface Images[C]//IEEE.2004 12th European Signal Processing Conference.New York:IEEE,2004:257-260.
[2] ZHOU J,HUANG P S.Wavelet-based Pavement Distress Detection and Evaluation[J].Optical Engineering,2006,45(2):409-411.
[3] 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.
[4] ALEKSEYCHUK D.Detection of Crack-like Indications in Digital Radiography by Global Optimisation of a Probabilistic Estimation Function[D].Berlin:Technische University Dresden,2006.
[5] LI Q Q,ZOU Q,ZHANG D Q,et al.FoSA:F* Seed-growing Approach for Crack-line Detection from Pavement Images[J].Image & Vision Computing,2011,29(12):861-872.
[6] ZOU Q,CAO Y,LI Q Q,et al.Crack Tree:Automatic Crack Detection from Pavement Images[J].Pattern Recognition Letters,2012,33(3):227-238.
[7] KAUL V,YEZZI A,TSAI Y J.Erratum to “Detecting Curves with Unknown Endpoints and Arbitrary Topology Using Minimal Paths”[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(10):1952-1965.
[8] WANG H,ZHU N,WANG Q.Fractal Features Analysis and Classification for Texture of Pavement Surfaces[J].Journal of Harbin Institute of Technology,2005,37(6):816-818.
[9] SORNCHAREAN S,PHIPHOBMONGKOL S.Crack Detection on Asphalt Surface Image Using Enhanced Grid Cell Analysis[C]//IEEE.4th International Symposium on Electronic Design,Test and Applications.New York:IEEE,2008:49-54.
[10] TSAI Y C,KAUL V,MERSEREAU R M.Critical Assessment of Pavement Distress Segmentation Methods[J].Journal of Transportation Engineering,2010,136(1):11-19.
[11] AYENU-PRAH A,ATTOH-OKINE N.Evaluating Pavement Cracks with Bidimensional Empirical Mode Decomposition[J].EURASIP Journal on Advances in Signal Processing,2008(1):1-7.
[12] TANAKA N,UEMATSU K.A Crack Detection Method in Road Surface Images Using Morphology[C]//DBLP.IAPR Workshop on Machine Vision Applications.Chiba:DBLP,1998:154-157.
[13] WANG K C P,LI Q,GONG W.Wavelet-based Pavement Distress Image Edge Detection with a Trous Algorithm[J].Transportation Research Record,2007(2024):73-81.
[14] ZHANG A,LI Q,WANG K C P,et al.Matched Filtering Algorithm for Pavement Cracking Detection[J].Transportation Research Record,2013(2367):30-42.
[15] MA C X,ZHAO C X,HOU Y K.Pavement Distress Detection Based on Nonsubsampled Contourlet Transform[C]//IEEE.International Conference on Computer Science and Software Engineering.New York:IEEE,2008:28-31.
[16] 余生晨,刘大有,孙莉民.一阶方向导数极值法——一种检测边缘的新方法[J].计算机研究与发展,2000,37(2):244-247. YU Sheng-chen,LIU Da-you,SUN Li-min.Method Using Extremum of First Directional Derivative-A New Method for Edge Detection[J].Journal of Computer Research & Development,2000,37(2):244-247.
[17] 朱同林,彭嘉雄,吕铁英.基于左右导数算子类的边缘提取[J].红外与激光工程,1999,28(5):35-38. ZHU Tong-lin,PENG Jia-xiong,LU Tie-ying.Edges Detection Operators Based on Right and Left Derivatives[J].Infrared and Laser Engineering,1999,28(5):35-38.
[18] 徐志刚.基于多特征融合的路面破损图像自动识别技术研究[D].西安:长安大学,2012. XU Zhi-gang.Study on the Automatic Identification Technology for Pavement Distress Image Based on Multi-features Fusion[D].Xi'an:Chang'an University,2012.
[19] 徐志刚,赵祥模,宋焕生,等.基于直方图估计和形状分析的沥青路面裂缝识别算法[J].仪器仪表学报,2010,31(10):2260-2266. XU Zhi-gang,ZHAO Xiang-mo,SONG Huan-sheng,et al.Asphalt Pavement Crack Recognition Algorithm Based on Histogram Estimation and Shape Analysis[J].Chinese Journal of Scientific Instrument,2010,31(10):2260-2266.
[20] 李清泉,邹 勤,毛庆洲.基于最小代价路径搜索的路面裂缝检测[J].中国公路学报,2010,23(6):28-33. LI Qing-quan,ZOU Qin,MAO Qing-zhou.Pavement Crack Detection Based on Minimum Cost Path Searching[J].China Journal of Highway and Transport,2010,23(6):28-33.
[21] KAUL V,TSAI Y,YEZZI A J.Detection of Curves with Unknown Endpoints Using Minimal Path Techniques[C]//LABROSSE F,ZWIGGELAAR R,LIU Y,et al.Proceeding of the British Machine Vision Conference.Durham:BMVC,2010:1-12.

基金

陕西省自然科学基金项目(S2013JC9397);高节能电机及控制技术国家地方联合工程实验室基金项目(KFKT201510);安徽工程大学校青年基金项目(2015YQ15)
PDF全文下载(4226 KB)

2078

Accesses

0

Citation

Detail

段落导航
相关文章

/