No Cover Image

Journal article 474 views

Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks

Zhuo Liu, Shuo Pan, Zhiwei Gao, Ning Chen, Feng Li, Linbing Wang, Yue Hou

Automation in Construction, Volume: 146, Start page: 104674

Swansea University Author: Yue Hou

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

Check full text

DOI (Published version): 10.1016/j.autcon.2022.104674

Abstract

Automatic monitoring of pavement structure health has always been a significant problem for transportation engineers. Although the generative adversarial network (GAN) has proven to be an effective tool for improving pavement distress recognition accuracy, it may lead to increased computational cost...

Full description

Published in: Automation in Construction
ISSN: 0926-5805
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62096
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-12-01T08:52:55Z
last_indexed 2023-01-13T19:23:19Z
id cronfa62096
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-01-10T09:05:48.9893588</datestamp><bib-version>v2</bib-version><id>62096</id><entry>2022-12-01</entry><title>Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks</title><swanseaauthors><author><sid>92bf566c65343cb3ee04ad963eacf31b</sid><firstname>Yue</firstname><surname>Hou</surname><name>Yue Hou</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-12-01</date><deptcode>CIVL</deptcode><abstract>Automatic monitoring of pavement structure health has always been a significant problem for transportation engineers. Although the generative adversarial network (GAN) has proven to be an effective tool for improving pavement distress recognition accuracy, it may lead to increased computational cost, which inconsistent with the requirements of engineering practice. This paper describes a lightweight GAN structure for automatic pavement distress identification with high computation efficiency and low computation cost. Squeeze and expand (SE), multiscale convolution (MC), and depthwise separable convolution (DSC) were selected as alternative lightweight methods, and two series of comparative experiments were conducted. The results showed that the GAN-based model with SE implemented on its fully connected layer, MC&amp;DSC implemented on its transpose convolution layers in the generator, and MC implemented on its convolution layers in the discriminator could reduce the largest proportion of model parameters (94.8%) while achieving satisfactory classification accuracy (85.4%).</abstract><type>Journal Article</type><journal>Automation in Construction</journal><volume>146</volume><journalNumber/><paginationStart>104674</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0926-5805</issnPrint><issnElectronic/><keywords>Automatic intelligent recognition; Pavement distresses; Lightweight GAN; Multiscale convolution; Depthwise separable convolution</keywords><publishedDay>1</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-02-01</publishedDate><doi>10.1016/j.autcon.2022.104674</doi><url/><notes/><college>COLLEGE NANME</college><department>Civil Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CIVL</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This work was supported by the Opening Project Fund of Materials Service Safety Assessment Facilities (MSAF- 2021-109), Key Science and Technology Projects in the Transportation Industry in 2021 (2021-ZD2-047), 2021 Science and Technology Innovation Project of Shandong Hi-Speed Group (SDGS-2021-0472-2), and the National Natural Science Foundation of China (Grant no. 51708026).</funders><projectreference/><lastEdited>2023-01-10T09:05:48.9893588</lastEdited><Created>2022-12-01T08:51:01.9508529</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>Zhuo</firstname><surname>Liu</surname><order>1</order></author><author><firstname>Shuo</firstname><surname>Pan</surname><order>2</order></author><author><firstname>Zhiwei</firstname><surname>Gao</surname><order>3</order></author><author><firstname>Ning</firstname><surname>Chen</surname><order>4</order></author><author><firstname>Feng</firstname><surname>Li</surname><order>5</order></author><author><firstname>Linbing</firstname><surname>Wang</surname><order>6</order></author><author><firstname>Yue</firstname><surname>Hou</surname><order>7</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2022-12-01T14:06:47.8842992</uploaded><type>Output</type><contentLength>1904853</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2023-11-26T00:00:00.0000000</embargoDate><documentNotes>&#xA9;2022 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2023-01-10T09:05:48.9893588 v2 62096 2022-12-01 Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks 92bf566c65343cb3ee04ad963eacf31b Yue Hou Yue Hou true false 2022-12-01 CIVL Automatic monitoring of pavement structure health has always been a significant problem for transportation engineers. Although the generative adversarial network (GAN) has proven to be an effective tool for improving pavement distress recognition accuracy, it may lead to increased computational cost, which inconsistent with the requirements of engineering practice. This paper describes a lightweight GAN structure for automatic pavement distress identification with high computation efficiency and low computation cost. Squeeze and expand (SE), multiscale convolution (MC), and depthwise separable convolution (DSC) were selected as alternative lightweight methods, and two series of comparative experiments were conducted. The results showed that the GAN-based model with SE implemented on its fully connected layer, MC&DSC implemented on its transpose convolution layers in the generator, and MC implemented on its convolution layers in the discriminator could reduce the largest proportion of model parameters (94.8%) while achieving satisfactory classification accuracy (85.4%). Journal Article Automation in Construction 146 104674 Elsevier BV 0926-5805 Automatic intelligent recognition; Pavement distresses; Lightweight GAN; Multiscale convolution; Depthwise separable convolution 1 2 2023 2023-02-01 10.1016/j.autcon.2022.104674 COLLEGE NANME Civil Engineering COLLEGE CODE CIVL Swansea University Another institution paid the OA fee This work was supported by the Opening Project Fund of Materials Service Safety Assessment Facilities (MSAF- 2021-109), Key Science and Technology Projects in the Transportation Industry in 2021 (2021-ZD2-047), 2021 Science and Technology Innovation Project of Shandong Hi-Speed Group (SDGS-2021-0472-2), and the National Natural Science Foundation of China (Grant no. 51708026). 2023-01-10T09:05:48.9893588 2022-12-01T08:51:01.9508529 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Zhuo Liu 1 Shuo Pan 2 Zhiwei Gao 3 Ning Chen 4 Feng Li 5 Linbing Wang 6 Yue Hou 7 Under embargo Under embargo 2022-12-01T14:06:47.8842992 Output 1904853 application/pdf Accepted Manuscript true 2023-11-26T00:00:00.0000000 ©2022 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND) true eng https://creativecommons.org/licenses/by-nc-nd/4.0/
title Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
spellingShingle Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
Yue Hou
title_short Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
title_full Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
title_fullStr Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
title_full_unstemmed Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
title_sort Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks
author_id_str_mv 92bf566c65343cb3ee04ad963eacf31b
author_id_fullname_str_mv 92bf566c65343cb3ee04ad963eacf31b_***_Yue Hou
author Yue Hou
author2 Zhuo Liu
Shuo Pan
Zhiwei Gao
Ning Chen
Feng Li
Linbing Wang
Yue Hou
format Journal article
container_title Automation in Construction
container_volume 146
container_start_page 104674
publishDate 2023
institution Swansea University
issn 0926-5805
doi_str_mv 10.1016/j.autcon.2022.104674
publisher Elsevier BV
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 Automatic monitoring of pavement structure health has always been a significant problem for transportation engineers. Although the generative adversarial network (GAN) has proven to be an effective tool for improving pavement distress recognition accuracy, it may lead to increased computational cost, which inconsistent with the requirements of engineering practice. This paper describes a lightweight GAN structure for automatic pavement distress identification with high computation efficiency and low computation cost. Squeeze and expand (SE), multiscale convolution (MC), and depthwise separable convolution (DSC) were selected as alternative lightweight methods, and two series of comparative experiments were conducted. The results showed that the GAN-based model with SE implemented on its fully connected layer, MC&DSC implemented on its transpose convolution layers in the generator, and MC implemented on its convolution layers in the discriminator could reduce the largest proportion of model parameters (94.8%) while achieving satisfactory classification accuracy (85.4%).
published_date 2023-02-01T04:21:27Z
_version_ 1763754416176889856
score 11.017797

Similar Items