No Cover Image

Journal article 192 views

The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing

Yuchen Liu Orcid Logo, Fang Liu Orcid Logo, Yucheng Huang Orcid Logo, Jing Hu Orcid Logo, Wei Zhang, Yue Hou Orcid Logo

IEEE Transactions on Intelligent Transportation Systems, Volume: 26, Issue: 7, Pages: 10512 - 10522

Swansea University Author: Yue Hou Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1109/tits.2025.3544240

Abstract

Most advanced methods for road surface defect detection may have the issue of large network structures, making them impractical for implementation on mobile embedded systems. In this study, A lightweight road surface defect real-time intelligent detection system based on cloud-edge collaboration is...

Full description

Published in: IEEE Transactions on Intelligent Transportation Systems
ISSN: 1524-9050 1558-0016
Published: Institute of Electrical and Electronics Engineers (IEEE) 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa70724
first_indexed 2025-10-18T18:18:22Z
last_indexed 2025-12-05T18:10:28Z
id cronfa70724
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-12-04T08:41:56.6717332</datestamp><bib-version>v2</bib-version><id>70724</id><entry>2025-10-18</entry><title>The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing</title><swanseaauthors><author><sid>92bf566c65343cb3ee04ad963eacf31b</sid><ORCID>0000-0002-4334-2620</ORCID><firstname>Yue</firstname><surname>Hou</surname><name>Yue Hou</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-10-18</date><deptcode>ACEM</deptcode><abstract>Most advanced methods for road surface defect detection may have the issue of large network structures, making them impractical for implementation on mobile embedded systems. In this study, A lightweight road surface defect real-time intelligent detection system based on cloud-edge collaboration is proposed. The system comprises a lightweight feature-enhanced YOLO network (YOLO-LFE), a multi-object tracking network called ByteTrack, and is deployed on intelligent edge devices, enabling real-time defect detection and storage of uploaded defect information through edge computing modules and cloud systems. Built upon the latest YOLOv8 architecture, a lightweight MobileNetV3 network is first introduced as the backbone feature extraction component, resulting in a noteworthy decrease in parameters and computational intricacy. Subsequently, the Enhanced Spatial Pyramid Pooling (ESPP) method built upon the human visual perception system is applied to swap out the Spatial Pyramid Pooling Fusion (SPPF) method, thereby enhancing the model&#x2019;s capability to capture features from tiny entities. Finally, an enhanced progressive feature fusion network is designed to further address the semantic gap issue during subsequent fusion of primary features. Experimental results on a self-made dataset and the public RDD2022 dataset show that the proposed detection model maintains high accuracy while requiring fewer parameters and less computational resources. Compared to YOLOv8, the model reduces the number of parameters by 32.5% and decreases computational requirements by 37%. This makes it more suitable for deployment on embedded devices. Additionally, the system has been field-tested on vehicles, thereby validating the effectiveness of the entire system.</abstract><type>Journal Article</type><journal>IEEE Transactions on Intelligent Transportation Systems</journal><volume>26</volume><journalNumber>7</journalNumber><paginationStart>10512</paginationStart><paginationEnd>10522</paginationEnd><publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1524-9050</issnPrint><issnElectronic>1558-0016</issnElectronic><keywords/><publishedDay>1</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-07-01</publishedDate><doi>10.1109/tits.2025.3544240</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>10.13039/501100001809-Natural Science Foundation of China (Grant Number: 52208360) 10.13039/501100017684-Transportation Science and Technology Project of Jiangsu Province (Grant Number: 2023Z07-1)</funders><projectreference/><lastEdited>2025-12-04T08:41:56.6717332</lastEdited><Created>2025-10-18T19:14:48.4263188</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering</level></path><authors><author><firstname>Yuchen</firstname><surname>Liu</surname><orcid>0009-0007-4598-3409</orcid><order>1</order></author><author><firstname>Fang</firstname><surname>Liu</surname><orcid>0009-0001-5892-990x</orcid><order>2</order></author><author><firstname>Yucheng</firstname><surname>Huang</surname><orcid>0000-0003-1728-2246</orcid><order>3</order></author><author><firstname>Jing</firstname><surname>Hu</surname><orcid>0000-0001-7134-2532</orcid><order>4</order></author><author><firstname>Wei</firstname><surname>Zhang</surname><order>5</order></author><author><firstname>Yue</firstname><surname>Hou</surname><orcid>0000-0002-4334-2620</orcid><order>6</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2025-12-04T08:41:56.6717332 v2 70724 2025-10-18 The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing 92bf566c65343cb3ee04ad963eacf31b 0000-0002-4334-2620 Yue Hou Yue Hou true false 2025-10-18 ACEM Most advanced methods for road surface defect detection may have the issue of large network structures, making them impractical for implementation on mobile embedded systems. In this study, A lightweight road surface defect real-time intelligent detection system based on cloud-edge collaboration is proposed. The system comprises a lightweight feature-enhanced YOLO network (YOLO-LFE), a multi-object tracking network called ByteTrack, and is deployed on intelligent edge devices, enabling real-time defect detection and storage of uploaded defect information through edge computing modules and cloud systems. Built upon the latest YOLOv8 architecture, a lightweight MobileNetV3 network is first introduced as the backbone feature extraction component, resulting in a noteworthy decrease in parameters and computational intricacy. Subsequently, the Enhanced Spatial Pyramid Pooling (ESPP) method built upon the human visual perception system is applied to swap out the Spatial Pyramid Pooling Fusion (SPPF) method, thereby enhancing the model’s capability to capture features from tiny entities. Finally, an enhanced progressive feature fusion network is designed to further address the semantic gap issue during subsequent fusion of primary features. Experimental results on a self-made dataset and the public RDD2022 dataset show that the proposed detection model maintains high accuracy while requiring fewer parameters and less computational resources. Compared to YOLOv8, the model reduces the number of parameters by 32.5% and decreases computational requirements by 37%. This makes it more suitable for deployment on embedded devices. Additionally, the system has been field-tested on vehicles, thereby validating the effectiveness of the entire system. Journal Article IEEE Transactions on Intelligent Transportation Systems 26 7 10512 10522 Institute of Electrical and Electronics Engineers (IEEE) 1524-9050 1558-0016 1 7 2025 2025-07-01 10.1109/tits.2025.3544240 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University 10.13039/501100001809-Natural Science Foundation of China (Grant Number: 52208360) 10.13039/501100017684-Transportation Science and Technology Project of Jiangsu Province (Grant Number: 2023Z07-1) 2025-12-04T08:41:56.6717332 2025-10-18T19:14:48.4263188 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Yuchen Liu 0009-0007-4598-3409 1 Fang Liu 0009-0001-5892-990x 2 Yucheng Huang 0000-0003-1728-2246 3 Jing Hu 0000-0001-7134-2532 4 Wei Zhang 5 Yue Hou 0000-0002-4334-2620 6
title The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
spellingShingle The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
Yue Hou
title_short The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
title_full The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
title_fullStr The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
title_full_unstemmed The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
title_sort The Real-Time Pavement Distress Detection System Based on Edge-Cloud Collaborative Computing
author_id_str_mv 92bf566c65343cb3ee04ad963eacf31b
author_id_fullname_str_mv 92bf566c65343cb3ee04ad963eacf31b_***_Yue Hou
author Yue Hou
author2 Yuchen Liu
Fang Liu
Yucheng Huang
Jing Hu
Wei Zhang
Yue Hou
format Journal article
container_title IEEE Transactions on Intelligent Transportation Systems
container_volume 26
container_issue 7
container_start_page 10512
publishDate 2025
institution Swansea University
issn 1524-9050
1558-0016
doi_str_mv 10.1109/tits.2025.3544240
publisher Institute of Electrical and Electronics Engineers (IEEE)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering
document_store_str 0
active_str 0
description Most advanced methods for road surface defect detection may have the issue of large network structures, making them impractical for implementation on mobile embedded systems. In this study, A lightweight road surface defect real-time intelligent detection system based on cloud-edge collaboration is proposed. The system comprises a lightweight feature-enhanced YOLO network (YOLO-LFE), a multi-object tracking network called ByteTrack, and is deployed on intelligent edge devices, enabling real-time defect detection and storage of uploaded defect information through edge computing modules and cloud systems. Built upon the latest YOLOv8 architecture, a lightweight MobileNetV3 network is first introduced as the backbone feature extraction component, resulting in a noteworthy decrease in parameters and computational intricacy. Subsequently, the Enhanced Spatial Pyramid Pooling (ESPP) method built upon the human visual perception system is applied to swap out the Spatial Pyramid Pooling Fusion (SPPF) method, thereby enhancing the model’s capability to capture features from tiny entities. Finally, an enhanced progressive feature fusion network is designed to further address the semantic gap issue during subsequent fusion of primary features. Experimental results on a self-made dataset and the public RDD2022 dataset show that the proposed detection model maintains high accuracy while requiring fewer parameters and less computational resources. Compared to YOLOv8, the model reduces the number of parameters by 32.5% and decreases computational requirements by 37%. This makes it more suitable for deployment on embedded devices. Additionally, the system has been field-tested on vehicles, thereby validating the effectiveness of the entire system.
published_date 2025-07-01T05:31:32Z
_version_ 1851098075908538368
score 11.089386

Similar Items