Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms

To address the challenges posed by the vast scale of highway maintenance in China and the high costs associated with traditional inspection vehicles. This study focuses on a routine maintenance project for national and provincial roads in Shanxi Province, with an emphasis on the selection and design...

Full description

Saved in:
Bibliographic Details
Main Authors: Hong Zhang, Yuanshuai Dong, Yun Hou, Xiangjun Cheng, Peiwen Xie, Keming Di
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/4/72
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714992762322944
author Hong Zhang
Yuanshuai Dong
Yun Hou
Xiangjun Cheng
Peiwen Xie
Keming Di
author_facet Hong Zhang
Yuanshuai Dong
Yun Hou
Xiangjun Cheng
Peiwen Xie
Keming Di
author_sort Hong Zhang
collection DOAJ
description To address the challenges posed by the vast scale of highway maintenance in China and the high costs associated with traditional inspection vehicles. This study focuses on a routine maintenance project for national and provincial roads in Shanxi Province, with an emphasis on the selection and design of hardware for lightweight, portable pavement inspection devices. A monocular camera was used to capture pavement surface images, resulting in a dataset of 85,511 training samples. Additionally, the YOLOv5 object detection algorithm, combined with convolutional deep learning techniques, was employed to classify and identify pavement surface distresses in the collected images. Through multiple iterations of model tuning and validation, the proposed detection system achieved a false negative rate of 1.13%, a recall rate of 97.35%, and a precision rate of 98.30%. Its high accuracy provides a technical reference for the development and design of portable pavement distress detection devices.
format Article
id doaj-art-5d66b4a17d7c4ffa80c11f451ddf5942
institution DOAJ
issn 2412-3811
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-5d66b4a17d7c4ffa80c11f451ddf59422025-08-20T03:13:32ZengMDPI AGInfrastructures2412-38112025-03-011047210.3390/infrastructures10040072Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection AlgorithmsHong Zhang0Yuanshuai Dong1Yun Hou2Xiangjun Cheng3Peiwen Xie4Keming Di5Department of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaDepartment of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaChina Highway Engineering Consulting Corporation, Beijing 100089, ChinaChina Highway Engineering Consulting Corporation, Beijing 100089, ChinaChina Highway Engineering Consulting Corporation DATA Co., Ltd., Beijing 100089, ChinaShanxi Provincial Highway Bureau Linfen Branch, Linfen 041000, ChinaTo address the challenges posed by the vast scale of highway maintenance in China and the high costs associated with traditional inspection vehicles. This study focuses on a routine maintenance project for national and provincial roads in Shanxi Province, with an emphasis on the selection and design of hardware for lightweight, portable pavement inspection devices. A monocular camera was used to capture pavement surface images, resulting in a dataset of 85,511 training samples. Additionally, the YOLOv5 object detection algorithm, combined with convolutional deep learning techniques, was employed to classify and identify pavement surface distresses in the collected images. Through multiple iterations of model tuning and validation, the proposed detection system achieved a false negative rate of 1.13%, a recall rate of 97.35%, and a precision rate of 98.30%. Its high accuracy provides a technical reference for the development and design of portable pavement distress detection devices.https://www.mdpi.com/2412-3811/10/4/72pavement engineeringasphalt pavement maintenancepavement surface inspectiondeep learningobject detection
spellingShingle Hong Zhang
Yuanshuai Dong
Yun Hou
Xiangjun Cheng
Peiwen Xie
Keming Di
Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms
Infrastructures
pavement engineering
asphalt pavement maintenance
pavement surface inspection
deep learning
object detection
title Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms
title_full Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms
title_fullStr Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms
title_full_unstemmed Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms
title_short Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms
title_sort research on asphalt pavement surface distress detection technology coupling deep learning and object detection algorithms
topic pavement engineering
asphalt pavement maintenance
pavement surface inspection
deep learning
object detection
url https://www.mdpi.com/2412-3811/10/4/72
work_keys_str_mv AT hongzhang researchonasphaltpavementsurfacedistressdetectiontechnologycouplingdeeplearningandobjectdetectionalgorithms
AT yuanshuaidong researchonasphaltpavementsurfacedistressdetectiontechnologycouplingdeeplearningandobjectdetectionalgorithms
AT yunhou researchonasphaltpavementsurfacedistressdetectiontechnologycouplingdeeplearningandobjectdetectionalgorithms
AT xiangjuncheng researchonasphaltpavementsurfacedistressdetectiontechnologycouplingdeeplearningandobjectdetectionalgorithms
AT peiwenxie researchonasphaltpavementsurfacedistressdetectiontechnologycouplingdeeplearningandobjectdetectionalgorithms
AT kemingdi researchonasphaltpavementsurfacedistressdetectiontechnologycouplingdeeplearningandobjectdetectionalgorithms