摘要Cracking is one of the major distresses impacting pavement quality, serviceability, and lifespan. Thus, accurate, precise, and complete cracking detection is important in the maintenance, performance evaluation, structure, and material design of pavements. Given that the results of pavement crack image recognition tend to contain noises and intermittent crack segments, an automatic crack detection algorithm based on the connectivity checking of pixels and crack block levels was proposed. First, a pavement image was enhanced on the basis of a self-adaptive grayscale stretch. The image was then segmented into background and foreground (potential cracks) on the basis of self-adaptive OTSU segmentation and 8-direction Sobel gradients. The potential crack image was denoised through connectivity checking. Finally, 32 pixel×32 pixel crack blocks were detected and optimally connected to form the final crack image. Examples show that the results of the proposed algorithm maintain enhanced integrity and continuity for improving connectivity at both the pixel and block levels. Performance tests were also conducted on 10 pavement images (512 pixels×512 pixels) for global OTSU segmentation, 8-direction Sobel detection, Canny detection, and the proposed algorithm. The proposed algorithm achieved both the highest precision (86.60%) and recall (90.68%), which resulted in the best F score (F1=88.30%).
Abstract：Cracking is one of the major distresses impacting pavement quality, serviceability, and lifespan. Thus, accurate, precise, and complete cracking detection is important in the maintenance, performance evaluation, structure, and material design of pavements. Given that the results of pavement crack image recognition tend to contain noises and intermittent crack segments, an automatic crack detection algorithm based on the connectivity checking of pixels and crack block levels was proposed. First, a pavement image was enhanced on the basis of a self-adaptive grayscale stretch. The image was then segmented into background and foreground (potential cracks) on the basis of self-adaptive OTSU segmentation and 8-direction Sobel gradients. The potential crack image was denoised through connectivity checking. Finally, 32 pixel×32 pixel crack blocks were detected and optimally connected to form the final crack image. Examples show that the results of the proposed algorithm maintain enhanced integrity and continuity for improving connectivity at both the pixel and block levels. Performance tests were also conducted on 10 pavement images (512 pixels×512 pixels) for global OTSU segmentation, 8-direction Sobel detection, Canny detection, and the proposed algorithm. The proposed algorithm achieved both the highest precision (86.60%) and recall (90.68%), which resulted in the best F score (F1=88.30%).
基金资助:Supported by the National Natural Science Foundation of China (No.51108391);the Special Funds for Technological Innovation Projects of Scientific Research and Operating Expenses of Central Universities (No.A0920502051208-99)
彭博, 蒋阳升, 蒲云. 基于双层连通性检测的路面裂缝图像识别算法[J]. Journal of Highway and Transportation Research and Development, 2014, 8(4): 37-46.
PENG Bo, JIANG Yang-sheng, PU Yun. Pavement Crack Detection Algorithm Based on Bi-layer Connectivity Checking. Journal of Highway and Transportation Research and Development, 2014, 8(4): 37-46.
[1] ZHANG Juan, SHA Ai-min, SUN Chao-yun, et al. Pavement Crack Automatic Recognition Based on Phase-grouping Method[J]. China Journal of Highway Transport, 2008, 21(2):39-42. (in Chinese)
[2] ZHAO Ke. The Design and Research of Pavement Crack Identification System[D]. Xi'an:Chang'an University, 2009. (in Chinese)
[3] JITPRASITHSIRI S. Development of a New Digital Pavement Image Processing Algorithm for Unified Crack Index Computation[D]. Salt Lake:University of Utah, 1997.
[4] CHAMBON S, GOURRAUD C, MOLIARD J M, et al. Road Crack Extraction with Adapted Filtering and Markov Model-Based Segmentation-Introduction and Validation[C]//Proceedings of the International Conference on Computer Vision Theory and Applications. Angers:INSTICC Press, 2010:81-90.
[5] LI Jin-hui. Image Processing Algorithm for Detecting the Pavement Crack Diseases[J]. Computer Engineering and Applications, 2003, 39(35):211-213. (in Chinese)
[6] BO Shao-bo, YAN Mao-de, SUN Guo-jun, et al. Research on Crack Detection Image Processing Algorithm for Asphalt Pavement Surface[J]. Microcomputer Information, 2007, 23(4-3):280-282. (in Chinese)
[7] ZHOU J, HUANG P S, CHIANG F P. Wavelet-Based Pavement Distress Detection and Evaluation[J]. Optical Engineering, 2006, 45(2):1-10.
[8] WANG K C P, LI Qiang, GONG Wei-guo. Wavelet-Based Pavement Distress Image Edge Detection with ‘À Trous’ Algorithm[J]. Transportation Research Record:Journal of the Transportation Research Board, 2007, 2024:73-81.
[9] NEJAD F M, ZAKERI H. A Comparison of Multi-Resolution Methods for Detection and Isolation of Pavement Distress[J]. Expert Systems with Applications, 2011, 38(3):2857-2872.
[10] GAVILÀN M, BALCONES D, MARCOS O, et al. Adaptive Road Crack Detection System by Pavement Classification[J]. Sensors, 2011, 11(10):9628-9657.
[11] HUANG Y X, XU B G. Automatic Inspection of Pavement Cracking Distress[J]. Journal of Electronic Imaging, 2006, 15(1):013017.
[12] SUN Bo-cheng, QIU Yan-jun. Pavement Crack Diseases Recognition Based on Image Processing Algorithm[J]. Journal of Highway and Transportation Research and Development, 2008, 25(2):64-68. (in Chinese)
[13] CHU Yan-li. Cracking Feature Extraction Based on Gray Image and Texture Characteristics[J]. Highway, 2010(7):131-136. (in Chinese)
[14] LI Gang, HE Yu-yao. A Novel Image Detection and Classification for Pavement Crack under Non-uniform Illumination[J]. Acta Photonica Sinica, 2010, 39(8):1405-1408. (in Chinese)
[15] LI L, CHAN P, RAO A, et al. Flexible Pavement Distress Evaluation Using Image Analysis[C]//The 2nd International Conference on Applications of Advanced Technologies in Transportation Engineering. Washington, D.C.:Transportation Research Board, 1991:473-477.
[16] DAVIS J, GOADRICH M. The Relationship between Precision-Recall and ROC Curves[C]//Proceedings of the 23rd International Conference on Machine Learning. New York:ACM, 2006:233-240.
[17] OTSU N. A Threshold Selection Method from Gray-Level Histograms[J]. IEEE Trans. Systems Man Cybernet, 1979, 9(1):62-66.
[18] CANNY J. A Computational Approach to Edge Detection[J]. IEEE Trans. Pattern Anal. Mach. Intell., 1986, 8(6):679-698.
[1]
李宁, 马骉, 李瑞, 司伟. 基于PUMA的单级和多级加载模式下级配碎石性能研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 1-12.
[2]
许海亮, 任合欢, 何兆才, 何炼. 车路耦合条件下沥青混凝土路面变形特性时域分析[J]. Journal of Highway and Transportation Research and Development, 2019, 13(2): 13-19.
[3]
杜健欢, 艾长发, 黄超, 郭玉金, 蒋运兵. 界面水对沥青复合小梁疲劳性能的影响试验[J]. Journal of Highway and Transportation Research and Development, 2019, 13(1): 1-7.
[4]
姚国强, 言志信, 龙哲, 翟聚云. 基于岩质边坡相似材料的锚固界面剪应力分布规律研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(1): 8-15.
[5]
刘泽, 何矾, 黄天棋, 蒋梅东. 车辆荷载在挡土墙上引起的附加土压力研究[J]. Journal of Highway and Transportation Research and Development, 2019, 13(1): 16-23.
[6]
邱欣, 徐静娴, 陶钰强, 杨青. 路面结冰条件判别标准及SVM预测分析研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 1-9.
[7]
高伟, 崔巍, 李秀凤. 半刚性基层表面抗冲刷性能试验与分析[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 10-17.
[8]
张向东, 任昆. 煤渣改良土路基的动弹性模量及临界动应力试验研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 25-32.
[9]
刘栋, 尚小亮, 杨西海. 垃圾焚烧炉渣中可溶盐对水泥稳定材料性能的影响[J]. Journal of Highway and Transportation Research and Development, 2018, 12(4): 18-24.
[10]
李龙海, 杨茹. 多次加铺的复合道面疲劳寿命分析[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 7-15.
[11]
蔡旭, 李翔, 吴旷怀, 黄文柯. 基于旋转压实的水泥稳定再生集料设计方法研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 1-6.
[12]
李金路, 冯子强, 吴佳杰, 魏姗姗, 葛智. 环境及疲劳荷载作用下碳纳米管水泥基复合材料压敏性能研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 16-21.
[13]
田小革, 韩海峰, 李新伟, 吴栋, 魏东. 半刚性路面中双层半刚性基层的倒装效应[J]. Journal of Highway and Transportation Research and Development, 2018, 12(3): 22-27.
[14]
邢磊, 雷柏龄, 陈忠达, 戴学臻. 彩色沥青路面胶凝材料的制备技术[J]. Journal of Highway and Transportation Research and Development, 2018, 12(2): 1-6.
[15]
方薇, 陈向阳, 杨果林. 带齿格栅加筋挡墙工作机理的数值模拟研究[J]. Journal of Highway and Transportation Research and Development, 2018, 12(2): 7-13.
2014, Vol. 8 
