针对路面影像斑点噪声强,路面裂缝对比度低、连续性差等特点,提出了一种基于最小代价路径搜索的路面裂缝检测方法。在裂缝成像亮度低于路面背景的前提下,该方法将裂缝提取问题转化为格状图顶点之间最小代价路径搜索的问题,首先通过对裂缝面元的处理,获取潜在的裂缝种子点,然后运用基于最小代价路径搜索的算法,实现裂缝种子点的生长和连接,并最终提取裂缝。试验结果表明:所提方法具有较高的精度和效率。
Abstract
Aimed at character of high speckle noises of pavement images, low contrast and bad continuity of pavement cracks, pavement crack detection approach based on minimum cost path searching was proposed. In this approach, the crack detection problem was formulated as a minimum cost path searching problem under assumption that cracks were imaged with a lower intensity than pavement background. Firstly, potential crack seed points were collected by processing of the crack block. Then, the crack seed points were linked into a whole crack through an algorithm on the basis of minimum cost path searching algorithm. Experiment results show that the proposed method has high accuracy and efficiency.
关键词
道路工程 /
裂缝检测 /
最小代价路径搜索 /
斑点噪声
{{custom_keyword}} /
Key words
road engineering /
crack detection /
minimum cost path searching /
speckle noise
{{custom_keyword}} /
中图分类号：
U418.6
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] PLAZA A,CERNADAS E,DURAN M L,et al.Multi-scale Detection of Curvilinear Structures with High Contour Accuracy[C]//Technical University of Lisbon.Proceedings of the 5th Iberoamerican Symposium on Pattern Recognition.Lisbon:Technical University of Lisbon,2000:405-412.
[2]ZHOU J,HUANG P S,CHIANG F P.Wavelet-based Pavement Distress Detection and Evaluation[J].Optical Engineering,2006,45(2):1-10.
[3]SUBIRATS P,DUMOULIN J,LEGEAY V,et al.Automation of Pavement Surface Crack Detection Using the Continuous Wavelet Transform[C]//IEEE.2006 International Conference on Image Processing.Atlanta:IEEE,2006:3037-3040.
[4]TANAKA N,UEMATSU K.A Crack Detection Method in Road Surface Images Using Morphology[C]//IKEUCHI K.Proceedings of the IAPR Workshop on Machine Vision Applications.Makuhari:International Association of Pattern Recognition,1998:154-157.
[5]YAN M,BO S,XU K,et al.Pavement Crack Detection and Analysis for High-grade Highway[C]//IEEE.Proceedings of the 8th International Conference on Electronic Measurement and Instruments.Xi'an:IEEE,2007:4548-4552.
[6]XU G,MA J,LIU F,et al.Automatic Recognition of Pavement Surface Crack Based on BP Neural Networks[C]//IEEE.Proceedings of International Conference on Computer and Electrical Engineering.Phuket:IEEE,2008:19-22.
[7]LIU F,XU G,YANG Y,et al.Novel Approach to Pavement Cracking Automatic Detection Based on Segment Extending[C]//IEEE.Proceedings of International Symposium on Knowledge Acquisition and Modeling.Wuhan:IEEE,2008:610-614.
[8]FISCHLER M A,TENENBAUM J M,WOLF H C.Detection of Roads and Linear Structures in Low-resolution Aerial Imagery Using a Multisource Knowledge Integration Technique[J].Computer Graphics and Image Processing,1981,15(3):201-223.
[9]MERLET N,ZERUBIA J.New Prospects in Line Detection by Dynamic Programming[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1996,18(4):426-431.
[10]CARLOTTO M J.Enhancement of Low-contrast Curvilinear Feature in Imagery[J].IEEE Transaction on Image Processing,2007,16(1):221-228.
[11]FORD JR L R.Network Flow Theory[R].Santa Monica:Rand Corporation,1956.
[12]LI Q,LIU X.Novel Approach to Pavement Image Segmentation Based on Neighboring Difference Histogram Method[C]//IEEE.Proceedings of Con-gress on Image and Signal Processing.Sanya:IEEE,2008:792-796.
[13]刘向龙,李清泉.基于金字塔结构的海量路面影像破损统计模型[J].武汉大学学报:信息科学版,2008,33(4):430-432,436.
LIU Xiang-long,LI Qing-quan.A Pyramid-based Cracks Statistical Modal for Massive Pavement Images[J].Geomatics and Information Science of Wuhan University,2008,33(4):430-432,436.
[14]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.
ZHANG Juan,SHA Ai-min,GAO Huai-gang,et al.Automatic Pavement Crack Recognition and Evaluation System Based on Digital Image Processing[J].Journal of Chang'an University:Natural Science Edition,2004,24(2):18-22.
[15]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.
LI Jin-hui.Pavement Crack Diseases Detecting by Image Processing Algorithm[J].Journal of Chang'an University:Natural Science Edition,2004,24(3):24-29.
[16]贾永红.数字图像处理[M].武汉:武汉大学出版社,2003:163-165.
JIA Yong-hong.Digital Image Processing[M].Wuhan:Wuhan University Press,2003:163-165.
[17]OTSU N.A Threshold Selection Method from Gray-level Histograms[J].IEEE Transaction on Systems,Man and Cybernetics,1979,9(1):62-66.
[18]WIEDEMANN C,EBNER H.Automatic Completion and Evaluation of Road Networks[J].International Archives of Photogrammetry and Remote Sensing,2000,33(B3):979-986.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金重点项目(40830530);中央高校基本科研业务费专项资金项目(6082031)
{{custom_fund}}
{{custom_fund}}
PDF全文下载(586 KB)
