In order to solve the problems of crack diseases on of surface of roads and bridges caused by load, fatigue and corrosion effects, material aging and delayed maintenance, further improve the efficiency of daily maintenance, the paper studied the application of machine vision technique and image processing technique in road and bridge crack disease detection. With the combination of contrastive analysis and data validation, a comparative study focusing on the disease feature extraction, feature recognition and quantitative calculation algorithm realized by machine vision technique was conducted. The results showed that: ①using revised Faster R-CNN and deeply separable convolutional network could effectively reduce parameters, thus achieve the balance between the speed and precision of the algorithm; ②the combination of wavelet transform filtering and K-dimensional tree could precisely realize continuous features extraction of crack diseases; ③based on the statistical characteristics of cracks, disease classification could be realized quickly. Based on the above research results, an automatic detection method for road and bridge crack diseases was proposed and developed. Through the example verification and model optimization on 8 expressways in Guangdong Province, the automatic detection of road and bridge crack diseases was realized with an accuracy of 95%, which greatly improved the detection efficiency and helped to improve the safe operation level of road and bridge.
洪卫星，吴 羡，陈贵海，郭丹桂，毛明洁
. Automatic Detection Technology of Road and
Bridge Surface Cracks Based on Machine Vision[J]. Transport Research, 2021
, 7(4)
: 114
-122
.
DOI: 10.16503/j.cnki.2095-9931.2021.04.014
[1] 张涛，刘玉婷，杨亚宁，等. 基于机器视觉的表面缺陷检测研究综述[J]. 科学技术与工程，2020，20（35）：14366-14376.
[2] 宰柯楠. 道路裂缝图像识别的算法研究[D]. 郑州：郑州大学，2017.
[3] MARR D. Vision: A computational investigation into the human representation and processing of visual information[M]. Cambridge, US: The MIT Press, 2010.
[4] 张维峰，刘萌，杨明慧. 基于数字图像处理的桥梁裂缝检测技术[J]. 现代交通技术，2008，5（5）：34-36.
[5] 曾华燕，徐建闽. 完善广州市智能交通系统配套保障体系的探讨[J]. 交通运输系统工程与信息，2006，6（1）：42-46.
[6] 丁威. 基于图像的桥梁裂缝检测理论与实践[D]. 广州：华南理工大学，2020.
[7] ZAKERI H, NEJAD F M, FAHIMIFAR A. Image based techniques for crack detection, classification and quantification in asphalt pavement: A review[J]. Archives of Computational Methods in Engineering, 2017, 24(4): 935-977.
[8] YAO M, ZHAO Z Y, YAO X, et al. Fusing complementary images for pavement cracking measurements[J]. Measurement Science & Technology, 2015, 26(2): 025005
[9] 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.
[10] PERAKA P, BILIGIRI K P. Pavement asset management systems and technologies: A review [J]. Automation in Construction, 2020, 119: 10336.
[11] KOCH C, GEORGIEVA K, KASIREDDY V, et al. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure[J]. Advanced Engineering Informatics, 2015, 29(2): 196-210.
[12] CORD A, CHAMBON S. Automatic road defect detection by textural pattern recognition based on AdaBoost[J]. Computer-Aided Civil and Infrastructure Engineering, 2012, 27(4): 244-259.
[13] 张凯，栾瑾. 道路综合检测车在公路检测中的应用[J]. 公路交通科技（应用技术版），2020（6）：37-38，41.
[14] 张显安. ARAN多功能检测车在路面检测中的应用及探讨[J]. 企业导报，2012（24）：265-266.
[15] 朱罡，薛敏. 浅谈JG-1型激光三维路面状况检测系统的应用[J]. 山西建筑，2007，33（23）：280-281.
[16] 孙波成. 基于数字图像处理的沥青路面裂缝识别技术研究[D]. 成都：西南交通大学，2015.
[17] 毛国栋. 水泥混凝土路面检测技术[J]. 交通世界，2017（25）：28-29.
[18] 王成. 基于深度学习与多尺度分析的路面裂缝检测的研究与应用[D]. 武汉：武汉理工大学，2019.
[19] 陈超，齐峰. 卷积神经网络的发展及其在计算机视觉领域中的应用综述[J]. 计算机科学，2019，46（3）：63-73.
[20] 卢蓓葳. 关于加强公路养护管理信息化建设的思考[J]. 科技视界，2018（22）：213-214.
[21] 周禹，韩帅，周昌勇，等. 基于机器视觉的道桥检测技术研究与应用[J]. 公路交通科技（应用技术版），2018（6）：110-112.
[22] 杨延，童远斌，马俊勇，等. 路面裂缝检测的机器视觉系统组成与设计思想[J]. 建设机械技术与管理，2016，29（8）：64-66.
