[1]郎洪,陆键,陈圣迪,等.考虑病害三维特征的沥青路面车辙异常检验方法[J].东南大学学报(自然科学版),2020,50(3):454-462.[doi:10.3969/j.issn.1001-0505.2020.03.007]
 Lang Hong,Lu Jian,Chen Shengdi,et al.Asphalt pavement rutting anomaly inspection method considering 3D characteristics of distress[J].Journal of Southeast University (Natural Science Edition),2020,50(3):454-462.[doi:10.3969/j.issn.1001-0505.2020.03.007]
点击复制

考虑病害三维特征的沥青路面车辙异常检验方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
50
期数:
2020年第3期
页码:
454-462
栏目:
交通运输工程
出版日期:
2020-05-20

文章信息/Info

Title:
Asphalt pavement rutting anomaly inspection method considering 3D characteristics of distress
作者:
郎洪1陆键1陈圣迪2娄月新1
1同济大学道路与交通工程教育部重点实验室, 上海 201804; 2上海海事大学交通运输学院, 上海 201306
Author(s):
Lang Hong1 Lu Jian1 Chen Shengdi2 Lou Yuexin1
1Key Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 201804, China
2College of Transportation Engineering, Shanghai Maritime University, Shanghai 201306, China
关键词:
车辙异常检验 三维线激光技术 图像处理 状态评估
Keywords:
rutting anomaly inspection three-dimensional line laser technology image processing condition assessment
分类号:
U416.2
DOI:
10.3969/j.issn.1001-0505.2020.03.007
摘要:
针对复杂路况下车辙深度异常或横断面数据不完整的问题,提出了基于病害三维特征的路面车辙异常检验方法.首先,对三维图像中激光点异常值进行筛选及修正,利用横断面深度数据应用包络线算法提取最大车辙.考虑到裂缝、坑槽和拥包对车辙提取存在误判,利用三维高程数据建立病害种子检测模型以自动提取裂缝、坑槽和拥包种子点.测试结果表明,车辙深度相对误差小于7%,车辙深度测量重复性小于4%,包络线算法结果与人工测量值的相关系数高达0.999 2.在车辙异常检验中,裂缝种子识别模型准确率和召回率的均值分别为92.18%和84.79%,且F值为88.33%,优于支持向量机及改进的Canny方法.坑槽及拥包种子识别模型检测正确率大于95%.所提方法不仅能高效地提取车辙深度,而且能准确地检验造成车辙检测异常的其他病害.
Abstract:
To solve the problem of abnormal rut depth or incomplete cross-section data under complex road conditions, a rutting anomaly inspection method based on the three-dimensional(3D)characteristics of the disease was proposed. Firstly, the outliers of laser points on 3D images were filtered and corrected, and the maximum ruts were extracted by using the envelope algorithm based on the cross-section elevation data. Considering the misclassification of rutting extraction by cracks, potholes and shoving, a disease seed detection model was established by using 3D elevation data to automatically extract seeds of cracks, potholes and shoving. The experimental results show that the relative error of the rut depth is less than 7%. The repeatability of the rut depth measurement is less than 4%. The correlation coefficient between the results of the envelope algorithm and the manual measurement values is as high as 0.999 2. In the rutting anomaly detection, the average accuracy and the recall rate of the crack recognition model are 92.18% and 84.79%, respectively, and the F-value 88.33% is better than those of the support vector machine and the improved Canny algorithm. The detection accuracy of the recognition model of potholes and shoving is more than 95%. The proposed method can not only effectively extract the rut depth efficiently, but also accurately detect other diseases in abnormal rutting.

参考文献/References:

[1] 黄晓明,张晓冰,邓学钧.沥青路面车辙形成规律环道试验研究[J].东南大学学报(自然科学版),2000,30(5):96-101.
  Huang X M, Zhang X B, Deng X J. Asphalt pavement rutting prediction of high-grade highway[J].Journal of Southeast University(Natural Science Edition), 2000, 30(5): 96-101.(in Chinese)
[2] Serigos P A, Prozzi J A, de Fortier Smit A, et al. Evaluation of 3D automated systems for the measurement of pavement surface cracking[J]. Journal of Transportation Engineering, 2016, 142(6): 05016003. DOI:10.1061/(asce)te.1943-5436.0000841.
[3] 马建,赵祥模,贺拴海,等.路面检测技术综述[J].交通运输工程学报,2017,17(5):121-137.
  Ma J, Zhao X M, He S H, et al. Review of pavement detection technology[J].Journal of Traffic and Transportation Engineering, 2017, 17(5): 121-137.(in Chinese)
[4] Mallela R, Wang H. Harmonising automated rut depth measurements-stage 2[R]. Waterloo Quay, Wellington, New Zealand: Land Transport New Zealand, 2006.
[5] 马荣贵,沙爱民,宋宏勋.路面车辙多路传感器检测误差分析[J].长安大学学报(自然科学版),2007,27(3):34-36,41. DOI:10.19721/j.cnki.1671-8879.2007.03.008.
Ma R G, Sha A M, Song H X. Error analysis in road rut measurement with multi-sensors[J]. Journal of Chang’an University(Natural Science Edition), 2007, 27(3): 34-36, 41. DOI:10.19721/j.cnki.1671-8879.2007.03.008. (in Chinese)
[6] Hong Z M, Ai Q S, Chen K. Line-laser-based visual measurement for pavement 3D rut depth in driving state[J]. Electronics Letters, 2018, 54(20): 1172-1174. DOI:10.1049/el.2018.5437.
[7] 李清泉,雷波,毛庆洲,等.利用激光三角法进行快速车辙检测[J].武汉大学学报(信息科学版),2010,35(3):302-307. DOI:10.13203/j.whugis2010.03.029.
Li Q Q, Lei B, Mao Q Z, et al. A fast method for pavement ruts measuring with laser triangulation[J]. Geomatics and Information Science of Wuhan University, 2010, 35(3): 302-307. DOI:10.13203/j.whugis2010.03.029. (in Chinese)
[8] 李莉,孙立军,谭生光,等.用于路面车辙检测的线结构光图像处理流程[J].同济大学学报(自然科学版),2013,41(5):710-715.
  Li L, Sun L J, Tan S G, et al. Line-structured light image processing procedure for pavement rut detection[J].Journal of Tongji University(Natural Science), 2013, 41(5): 710-715.(in Chinese)
[9] Wang K C P. Elements of automated survey of pavements and a 3D methodology[J]. Journal of Modern Transportation, 2011, 19(1): 51-57. DOI:10.1007/bf03325740.
[10] 张德津,李清泉,何莉.一种新的激光车辙深度测量方法研究[J].光学学报,2013,33(1):115-121. DOI:10.3788/aos201333.0112005.
Zhang D J, Li Q Q, He L. A new method for laser rut depth measurement[J].Acta Optica Sinica, 2013, 33(1): 115-121. DOI:10.3788/aos201333.0112005. (in Chinese)
[11] 郭鑫鑫,惠冰.基于三维线激光技术的多点激光车辙检测误差分析[J].筑路机械与施工机械化,2016,33(9):113-118.
  Guo X X, Hui B. Assessment of rut depth measurement accuracy of point-based rut bar systems using 3D line laser imaging technology[J].Road Machinery & Construction Mechanization, 2016, 33(9): 113-118.(in Chinese)
[12] 李甜甜.基于三维线激光技术的路面车辙检测技术研究[D].西安:长安大学,2016.
  Li T T. Research on pavement rutting detection technique based on 3D line laser technology[D]. Xi’an: Changan University, 2016.(in Chinese)
[13] Huang Y R, Copenhaver T, Hempel P. Texas department of transportation 3D transverse profiling system for high-speed rut measurement[J].Journal of Infrastructure Systems, 2013, 19(2): 221-230. DOI:10.1061/(asce)is.1943-555x.0000088.
[14] 中华人民共和国交通运输部.JTG/T E61—2014公路路面技术状况自动化检测规程[S].北京:人民交通出版社,2014.
[15] Huang J P, Liu W Y, Sun X M. A pavement crack detection method combining 2D with 3D information based on dempster-shafer theory[J]. Computer-Aided Civil and Infrastructure Engineering, 2014, 29(4): 299-313. DOI:10.1111/mice.12041.
[16] 彭博,蒋阳升,陈成,等.基于1 mm精度路面三维图像的裂缝自动并行识别算法[J].东南大学学报(自然科学版),2015,45(6):1190-1196.
  Peng B, Jiang Y S, Chen C, et al. Automatic parallel cracking detection algorithm based on 1 mm resolution 3D pavement images[J]. Journal of Southeast University(Natural Science Edition), 2015, 45(6): 1190-1196.(in Chinese)
[17] 中华人民共和国交通运输部.JTG 5210—2018公路技术状况评定标准[S].北京:人民交通出版社,2018.
[18] Gao C, Zhu H J, Guo Y C. Analysis and improvement of SUSAN algorithm[J]. Signal Processing, 2012, 92(10): 2552-2559. DOI:10.1016/j.sigpro.2012.03.002.
[19] 中华人民共和国交通运输部.JJG(交通)076—2010车载式路面激光车辙仪[S].北京:人民交通出版社,2010.
[20] Chang C C, Lin C J. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1-27. DOI:10.1145/1961189.1961199.
[21] 刘晟,王卫星,王珊珊,等.模糊航空图像中的道路自动检测方法[J].交通运输工程学报,2015,15(4):110-117. DOI:10.19818/j.cnki.1671-1637.2015.04.014.
Liu S, Wang W X, Wang S S, et al. Automatic detection method of roads from fuzzy aerial images[J].Journal of Traffic and Transportation Engineering, 2015, 15(4): 110-117. DOI:10.19818/j.cnki.1671-1637.2015.04.014. (in Chinese)
[22] Zhang A, Wang K C P, Li B X, et al. Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(10): 805-819. DOI:10.1111/mice.12297.

备注/Memo

备注/Memo:
收稿日期: 2019-11-17.
作者简介: 郎洪(1994—),男,博士生;陆键(联系人),男,博士,教授,博士生导师,jianjohnlu@tongji.edu.cn.
基金项目: 国家重点研发计划资助项目(2017YFC0803902).
引用本文: 郎洪,陆键,陈圣迪,等.考虑病害三维特征的沥青路面车辙异常检验方法[J].东南大学学报(自然科学版),2020,50(3):454-462. DOI:10.3969/j.issn.1001-0505.2020.03.007.
更新日期/Last Update: 2020-05-20