Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin

被引:7
|
作者
Wang, Weidong [1 ,2 ,3 ]
Xu, Xinyue [1 ,2 ,3 ]
Peng, Jun [1 ,2 ,3 ]
Hu, Wenbo [1 ,2 ,3 ]
Wu, Dingze [1 ,2 ,3 ]
机构
[1] Cent South Univ, Sch Civil Engn, Changsha 410075, Peoples R China
[2] Cent South Univ, MOE, Key Lab Engn Struct Heavy Haul Railway, Changsha 410075, Peoples R China
[3] Cent South Univ, Ctr Railway Infrastruct Smart Monitoring & Managem, Changsha 410075, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 07期
基金
中国国家自然科学基金;
关键词
road engineering; pavement-distress detection; digital twin; integrated data; physical engine; deep-object detection network; CONVOLUTIONAL NEURAL-NETWORKS; CRACK DETECTION; FRAMEWORK;
D O I
10.3390/app13074549
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The automated detection of distress such as cracks or potholes is a key basis for assessing the condition of pavements and deciding on their maintenance. A fine-grained pavement distress-detection algorithm based on integrated data using a digital twin is proposed to solve the challenges of the insufficiency of high-quality negative samples in specific scenarios An asphalt pavement background model is created based on UAV-captured images, and a lightweight physical engine is used to randomly render 5 types of distress and 3 specific scenarios to the background model, generating a digital twin model that can provide virtual distress data. The virtual data are combined with real data in different virtual-to-real ratios (0:1 to 5:1) to form an integrated dataset and used to fully train deep object detection networks for fine-grained detection. The results show that the YOLOv5 network with the virtual-to-real ratio of 3:1 achieves the best average precision for 5 types of distress (asphalt pavement MAP: 75.40%), with a 2-fold and 1.5-fold improvement compared to models developed without virtual data and with traditional data augmentation, respectively, and achieves over 40% recall in shadow, occlusion and blur. The proposed approach could provide a more reliable and refined automated method for pavement analysis in complex scenarios.
引用
收藏
页数:23
相关论文
共 50 条
  • [21] DATA ON CONSOLIDATION OF FINE-GRAINED SEDIMENTS
    CHILINGA.GV
    RIEKE, HH
    JOURNAL OF SEDIMENTARY PETROLOGY, 1968, 38 (03): : 811 - &
  • [22] Mix design for fine-grained exposed aggregate PCC pavement
    Lee, Seung Woo
    Cho, Yoon-Ho
    Chon, Beom Jun
    Park, Cheolwoo
    PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-TRANSPORT, 2011, 164 (01) : 3 - 11
  • [23] Fine-Grained Vibration Based Sensing Using a Smartphone
    Ali, Kamran
    Liu, Alex X.
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2022, 21 (11) : 3971 - 3985
  • [24] Fine-grained Emotion Role Detection Based on Retweet Information
    Yu, Zhiwen
    Yi, Fei
    Ma, Chao
    Wang, Zhu
    Guo, Bin
    Chen, Liming
    ACM TRANSACTIONS ON INTERNET TECHNOLOGY, 2019, 19 (01)
  • [25] Fine-grained Android Malware Detection based on Deep Learning
    Li, Dongfang
    Wang, Zhaoguo
    Xue, Yibo
    2018 IEEE CONFERENCE ON COMMUNICATIONS AND NETWORK SECURITY (CNS), 2018,
  • [26] Fine-grained task scheduling using adaptive data structures
    Hoffmann, Ralf
    Rauber, Thomas
    EURO-PAR 2008 PARALLEL PROCESSING, PROCEEDINGS, 2008, 5168 : 253 - 262
  • [27] A Fine-Grained Network Congestion Detection Based on Flow Watermarking
    Mo, Lusha
    Lv, Gaofeng
    Wang, Baosheng
    APPLIED SCIENCES-BASEL, 2022, 12 (16):
  • [28] A Study on Mispronunciation Detection Based on Fine-grained Speech Attribute
    Guo, Minghao
    Rui, Cai
    Wang, Wei
    Lin, Binghuai
    Zhang, Jinsong
    Xie, Yanlu
    2019 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2019, : 1197 - 1201
  • [29] Retail credit scoring using fine-grained payment data
    Tobback, Ellen
    Martens, David
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY, 2019, 182 (04) : 1227 - 1246
  • [30] Hybrid Approaches to Fine-Grained Emotion Detection in Social Media Data
    Schoene, Annika Marie
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 13732 - 13733