|Table of Contents|

Automatic tracking method of pavement performance decay based on deep learning(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2022年6期
Page:
53-65
Research Field:
桥梁工程·交通基础设施智能化运维技术专栏
Publishing date:

Info

Title:
Automatic tracking method of pavement performance decay based on deep learning
Author(s):
LI Yi-shun1;  LIU Cheng-long1; 2;  CAO Jing1; 2;  LI Feng3;  DU Yu-chuan1; 2
(1. Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University,Shanghai 201804, China; 2. Shanghai Engineering Research Center of Urban Infrastructure Renewal, Shanghai 200032, China; 3. School of Transportation Science and Engineering,Beihang Univeristy, Beijing 100191, China)
Keywords:
road engineering;  distress matching tracking;  deep learning;  pavement distress;  pavement deterioration law
PACS:
U411
DOI:
10.19721/j.cnki.1671-8879.2022.06.006
Abstract:
To establish continuous tracking and deterioration analysis of each single distress under the normal service state of the pavement, a spatiotemporal tracing method of pavement distress which established spatiotemporal correlations with high-frequency distress inspection data was proposed. The continuous tracking of the deterioration state of the distress level was established. Firstly, the computer vision algorithm was introduced to realize the recognition and lane-level positioning of six types of pavement distress, and then the three-level distress matching architecture of ‘scene-orientation-feature’ was introduced to realize the continuous tracking of the collected distress at different times. Specifically, it included spatial scene clustering based on improved DBSCAN, direction angle classification based on K-means clustering to distinguish upstream and downstream collected data, and single distress matching based on SIFT feature matching network. More than 7 000 images of the Hong Kong-Zhuhai-Macao Bridge, Shanghai Donghai Bridge and other bridges, tunnels and roads annotated with distress had been accumulated to train the distress detection algorithm. In order to verify the tracking methods, the high-frequency inspection data of a loop S32 in Shanghai(Shanghai-Jiaxing-Huzhou)was used to conduct experiments. The data included one-month daily inspection data on two-way 160 km expressways. The above matching tracking framework was verified by defining the maximum distance within a group, the minimum distance between groups, and the difference in azimuth distribution. The results show that the accuracy of distress matching is 84.74%. The deterioration period of distress under the action of heavy rain is as short as 2 d. In addition, the proposed method can also be used for damage assessment and status tracking of roadside safety facilities and signs, helping to accurately assess the service performance degradation status of transportation infrastructure.3 tabs, 13 figs, 34 refs.

References:

[1] LEE J,NAM B,ABDEL-ATY M.Effects of pavement surface conditions on traffic crash severity[J].Journal of Transportation Engineering,2015,141(10):04015020.
[2]M X,Y C,G J.Incorporating dynamic traffic distribution into pavement maintenance optimization model[J].Sustainability,Multidisciplinary Digital Publishing Institute,2019,11(9):2488.
[3]ISSA I M,ZOLLINGER D G.Developing a distress-based traffic equivalency to efficiently evaluate the effect of traffic loads on pavement performance[J].International Journal of Pavement Engineering,2021:1-9.
[4]DONG M,HAO Y,ZHANG C X,et al.Failure mechanism analysis of asphalt-aggregate systems subjected to direct shear loading[J].Materials and Structures,2017,50(5):218.
[5]沙爱民,蔡若楠,高 杰,等.基于级联卷积神经网络的公路路基病害识别[J].长安大学学报(自然科学版),2019,39(2):1-9.
SHA Ai-min,CAI Ruo-nan,GAO Jie,et al.Subgrade distresses recognition based on convolutional neural network[J].Journal of Chang’an University(Natural Science Edition),2019,39(2):1-9.
[6]董瑞琨,孙立军,彭 勇.路面预防性养护时机确定方法探讨[J].中国安全科学学报,2004,14(3):31-35.
DONG Rui-kun,SUN Li-jun,PENG Yong.Probe into determination of the appropriate time of pavement preventive maintenance(PPM)[J].China Safety Science Journal,2004,14(3):31-35.
[7]MATEOS A,MILLAN M A,HARVEY J T,et al.Mechanisms of asphalt cracking and concrete-asphalt debonding in concrete overlay on asphalt pavements[J].Construction and Building Materials,2021,301:124086.
[8]SENGüL C E,AKSOY A,ISKENDER E.Evaluation of stripping problem in terms of additive types and ratios in asphalt pavements[J].Teknik Dergi,2022,33(4):12183-12202.
[9]杨 扬,王连发,张宇峰,等.基于多特征融合的混凝土结构表面病害图像分类算法[J].长安大学学报(自然科学版),2021,41(3):64-74.
YANG Yang,WANG Lian-fa,ZHANG Yu-feng,et al.Multi-feature fusion based classification algorithm of surface disease image of concrete structure[J].Journal of Chang’an University(Natural Science Edition),2021,41(3):64-74.
[10]KAPELA R,SNIATALA P,TURKOT A,et al.Asphalt surfaced pavement cracks detection based on histograms of oriented gradients[C]//IEEE.Proceedings of the 22nd International Conference Mixed Design of Integrated Circuits & Systems(MIXDES).New York:IEEE,2015:579-584.
[11]吕 岩,曲仕茹.基于SIFT的路面裂缝配准及拼接算法[J].公路交通科技,2012,29(2):23-28.
LU Yan,QU Shi-ru.An algorithm of pavement crack image registration and mosaic based on SIFT algorithm[J].Journal of Highway and Transportation Research and Development,2012,29(2):23-28.
[12]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.
[13]CHEN C,SEO H,JUN C H,et al.Pavement crack detection and classification based on fusion feature of LBP and PCA with SVM[J].International Journal of Pavement Engineering,2022,23(9):3274-3283.
[14]OUMA Y O,HAHN M.Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy C-means clustering and morphological reconstruction[J].Automation in Construction,2017,83:196-211.
[15]EISENBACH M,STRICKER R,SEICHTER D,et al.How to get pavement distress detection ready for deep learning? A systematic approach[C]//IEEE.Proceedings of the 2017 International Joint Conference on Neural Networks(IJCNN).New York:IEEE,2017:2039-2047.
[16]LI B X,WANG K C P,ZHANG A,et al.Automatic classification of pavement crack using deep convolutional neural network[J].International Journal of Pavement Engineering,2020,21(4):457-463.
[17]沙爱民,童 峥,高 杰.基于卷积神经网络的路表病害识别与测量[J].中国公路学报,2018,31(1):1-10.
SHA Ai-min,TONG Zheng,GAO Jie.Recognition and measurement of pavement disasters based on convolutional neural networks[J].China Journal of Highway and Transport,2018,31(1):1-10.
[18]MAEDA H,SEKIMOTO Y,SETO T,et al.Road damage detection and classification using deep neural networks with smartphone images:Road damage detection and classification[J].Computer-Aided Civil and Infrastructure Engineering,2018,33(12):1127-1141.
[19]DU Y C,PAN N,XU Z H,et al.Pavement distress detection and classification based on YOLO network[J].International Journal of Pavement Engineering,2021,22(13):1659-1672.
[20]SONG L,WANG X.Faster region convolutional neural network for automated pavement distress detection[J].Road Materials and Pavement Design,2021,22(1):23-41.
[21]GUAN J C,YANG X,DING L,et al.Automated pixel-level pavement distress detection based on stereo vision and deep learning[J].Automation in Construction,2021,129:103788.
[22]LI Y,LIU C,SHEN Y,et al.A dedicated deep convolutional neural network for multipavement distress detection[J].Journal of Transportation Engineering,2021,147(4):04021057.
[23]ZHU J Q,ZHONG J T,MA T,et al.Pavement distress detection using convolutional neural networks with images captured via UAV[J].Automation in Construction,2022,133:103991.
[24]TANG W H,HUANG S,ZHAO Q M,et al.An iteratively optimized patch label inference network for automatic pavement distress detection[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(7):8652-8661.
[25]武建民,刘大彬,李福聪,等.基于时间序列分析法的沥青路面使用性能预测[J].长安大学学报(自然科学版),2015,35(3):1-7.
WU Jian-min,LIU Da-bin,LI Fu-cong,et al.Performance prediction of asphalt pavement maintenance based on time series analysis[J].Journal of Chang’an University(Natural Science Edition),2015,35(3):1-7.
[26]吴 敏,王端宜,雷超旭.沥青路面性能预测模型研究[J].广东公路交通,2009,35(1):5-9.
WU Min,WANG Duan-yi,LEI Chao-xu.Pavement performance prediction model for asphalt pavement[J].Guangdong Highway Communications,2009,35(1):5-9.
[27]DAMIRCHILO F,HOSSEINI A,MELLAT P M,et al.Machine learning approach to predict international roughness index using long-term pavement performance data[J].Journal of Transportation Engineering,2021,147(4):04021058.
[28]GUO R H,FU D L,SOLLAZZO G.An ensemble learning model for asphalt pavement performance prediction based on gradient boosting decision tree[J].International Journal of Pavement Engineering,2022,23(10):3633-3646.
[29]陈 旺,郑木莲,高 骞,等.海绵城市透水路面渗透性能衰减规律[J].长安大学学报(自然科学版),2021,41(3):12-21.
CHEN Wang,ZHENG Mu-lian,GAO Qian,et al.Attenuation law of permeable pavement in sponge city[J].Journal of Chang’an University(Natural Science Edition),2021,41(3):12-21.
[30]董 昭.加速磨耗试验与沥青路面材料抗滑性能衰变规律研究[D].西安:长安大学,2011.
DONG Zhao.Study on accelerated polishing test and the regularity of skid resistance degradation of asphalt pavement material[D].Xi’an:Chang’an University,2011.
[31]王抒音,谭忆秋,包秀宁,等.用冻融循环劈裂比评价沥青混合料抗水损害能力[J].哈尔滨建筑大学学报,2002(5):123-126.
WANG Shu-yin,TAN Yi-qiu,BAO Xiu-ning,et al.Evaluation of asphalt mixture for resistance to water damage based on freeze-thaw cycle split ratio[J].Journal of Harbin University of Civil Engineering and Architecture,2002(5):123-126.
[32]李 晶,刘 宇,张肖宁.沥青老化微观机理分析[J].硅酸盐通报,2014,33(6):1275-1281.
LI Jing,LIU Yu,ZHANG Xiao-ning.Microscopic analysis on the aging mechanism of asphalt[J].Bulletin of the Chinese Ceramic Society,2014,33(6):1275-1281.
[33]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal speed and accuracy of object detection[EB/OL].(2020-04-23)[2022-10-10].https://arxiv.org/abs/2004.10934
[34]PAN X G,SHI J P,LUO P,et al.Spatial as deep:Spatial CNN for traffic scene understanding[EB/OL].(2017-12-17)[2022-10-10].https://arxiv.org/abs/1712.06080

Memo

Memo:
-
Last Update: 2022-12-20