Crack Detection on Concrete Surfaces Using Deep Encoder-Decoder Convolutional Neural Network: A Comparison Study Between U-Net and DeepLabV3

Maintenance of infrastructures is a crucial activity to ensure safety using crack detection methods on concrete structures. However, most practice of crack detection is carried out manually, which is unsafe, highly subjective, and time-consuming. Therefore, a more accurate and efficient system needs...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of the Civil Engineering Forum Ročník 7; číslo 3; s. 323 - 334
Hlavní autori: Hadinata, Patrick Nicholas, Simanta, Djoni, Eddy, Liyanto, Nagai, Kohei
Médium: Journal Article
Jazyk:English
Japanese
Vydavateľské údaje: Universitas Gadjah Mada 31.08.2021
Predmet:
Civil Engineering
convolutional neural network
Convolutional Neural Network; U-Net; DeepLabV3+; Crack Detection; Maintenance of Infrastructures
crack detection
deeplabv3
Engineering (General). Civil engineering (General)
maintenance of infrastructures
TA1-2040
u-net
ISSN:2581-1037, 2549-5925
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Maintenance of infrastructures is a crucial activity to ensure safety using crack detection methods on concrete structures. However, most practice of crack detection is carried out manually, which is unsafe, highly subjective, and time-consuming. Therefore, a more accurate and efficient system needs to be implemented using artificial intelligence. Convolutional neural network (CNN), a subset of artificial intelligence, is used to detect cracks on concrete surfaces through semantic image segmentation. The purpose of this research is to compare the effectiveness of cutting-edge encoder-decoder architectures in detecting cracks on concrete surfaces using U-Net and DeepLabV3+ architectures with potential in biomedical, and sparse multiscale image segmentations, respectively. Neural networks were trained using cloud computing with a high-performance Graphics Processing Unit NVIDIA Tesla V100 and 27.4 GB of RAM. This study used internal and external data. Internal data consisted of simple cracks and were used as the training and validation data. Meanwhile, external data consisted of more complex cracks, which were used for further testing. Both architectures were compared based on four evaluation metrics in terms of accuracy, F1, precision, and recall. U-Net achieved segmentation accuracy = 96.57%, F1 = 87.55%, precision = 88.15%, and recall = 88.94%, while DeepLabV3+ achieved segmentation accuracy = 96.47%, F1 = 85.29%, precision = 92.07%, and recall = 81.84%. Experiment results (internal and external data) indicated that both architectures were accurate and effective in segmenting cracks. Additionally, U-Net and DeepLabV3+ exceeded the performance of previously tested architecture, namely FCN.
AbstractList Maintenance of infrastructures is a crucial activity to ensure safety using crack detection methods on concrete structures. However, most practice of crack detection is carried out manually, which is unsafe, highly subjective, and time-consuming. Therefore, a more accurate and efficient system needs to be implemented using artificial intelligence. Convolutional neural network (CNN), a subset of artificial intelligence, is used to detect cracks on concrete surfaces through semantic image segmentation. The purpose of this research is to compare the effectiveness of cutting-edge encoder-decoder architectures in detecting cracks on concrete surfaces using U-Net and DeepLabV3+ architectures with potential in biomedical, and sparse multiscale image segmentations, respectively. Neural networks were trained using cloud computing with a high-performance Graphics Processing Unit NVIDIA Tesla V100 and 27.4 GB of RAM. This study used internal and external data. Internal data consisted of simple cracks and were used as the training and validation data. Meanwhile, external data consisted of more complex cracks, which were used for further testing. Both architectures were compared based on four evaluation metrics in terms of accuracy, F1, precision, and recall. U-Net achieved segmentation accuracy = 96.57%, F1 = 87.55%, precision = 88.15%, and recall = 88.94%, while DeepLabV3+ achieved segmentation accuracy = 96.47%, F1 = 85.29%, precision = 92.07%, and recall = 81.84%. Experiment results (internal and external data) indicated that both architectures were accurate and effective in segmenting cracks. Additionally, U-Net and DeepLabV3+ exceeded the performance of previously tested architecture, namely FCN.
Author Liyanto Eddy
Kohei Nagai
Patrick Nicholas Hadinata
Djoni Simanta
Author_xml – sequence: 1
  givenname: Patrick Nicholas
  surname: Hadinata
  fullname: Hadinata, Patrick Nicholas
– sequence: 2
  givenname: Djoni
  surname: Simanta
  fullname: Simanta, Djoni
– sequence: 3
  givenname: Liyanto
  surname: Eddy
  fullname: Eddy, Liyanto
– sequence: 4
  givenname: Kohei
  surname: Nagai
  fullname: Nagai, Kohei
BackLink https://cir.nii.ac.jp/crid/1870302168320919680$$DView record in CiNii
BookMark eNptUctu1DAUjVCRKKUrfsALdijF79jsyrRApREsyrC1buzrym0aj5wMqP_AR-NkYIOQLB_73nOOH-dlczLmEZvmNaMXnDOp3917jBdacWOeNadcSdsqy9XJsjasZVR0L5rzaUo9lbKTylJz2vzaFPAP5Apn9HPKI6ljk0dfaoHcHkoEjxPZTWm8qyTck-vR54ClvcIVF_KPPBwWLQzkCx7KCvPPXB7ek8vaf9xDSVP1vZ0P4Yl8qD3EkezayiIwhtV3C_138ap5HmGY8PwPnjW7j9ffNp_b7ddPN5vLbet5p03Lre9BgA1aI3BplApSKGV6pBgk8h5sFJr3CroQPBdBmyiCkSxSbepOnDU3R9-Q4d7tS3qE8uQyJLcWcrlzUObkB3RdZMyADkJ0QkYM0Hccrbb11AhcmOrFjl6-5GkqGJ1PMyzfMRdIg2PUrem4JR23plM1b__R_L3D_9lvjuwxpWq-zMx0VFDO6nM4tcxqQ8VvPm2d9g
CitedBy_id crossref_primary_10_1109_TGRS_2023_3315212
crossref_primary_10_1088_1742_6596_3071_1_012013
crossref_primary_10_2478_bipca_2021_0027
crossref_primary_10_3390_land14081544
crossref_primary_10_1109_ACCESS_2025_3536554
crossref_primary_10_3390_app13042398
crossref_primary_10_1016_j_compag_2025_110735
crossref_primary_10_3390_polym17091245
ContentType Journal Article
Contributor Department of Civil Engineering, Universitas Katolik Parahyangan
Contributor_xml – sequence: 1
  fullname: Department of Civil Engineering, Universitas Katolik Parahyangan
DBID RYH
AAYXX
CITATION
DOA
DOI 10.22146/jcef.65288
DatabaseName CiNii Complete
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2549-5925
EndPage 334
ExternalDocumentID oai_doaj_org_article_7f118a6d33734fedab72e969485fa238
10_22146_jcef_65288
GroupedDBID ADBBV
ALMA_UNASSIGNED_HOLDINGS
BCNDV
GROUPED_DOAJ
OK1
RYH
AAYXX
CITATION
ID FETCH-LOGICAL-c2768-29cba3a9d66ea24855d43558be0ed4e2ba9f362b5a7ddc23d68f3d841f0683d63
IEDL.DBID DOA
ISSN 2581-1037
IngestDate Fri Oct 03 12:47:02 EDT 2025
Sat Nov 29 03:36:08 EST 2025
Tue Nov 18 22:29:02 EST 2025
Fri Jun 27 00:49:16 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
Japanese
License http://creativecommons.org/licenses/by-sa/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2768-29cba3a9d66ea24855d43558be0ed4e2ba9f362b5a7ddc23d68f3d841f0683d63
ORCID 0000-0002-9552-8777
OpenAccessLink https://doaj.org/article/7f118a6d33734fedab72e969485fa238
PageCount 12
ParticipantIDs doaj_primary_oai_doaj_org_article_7f118a6d33734fedab72e969485fa238
crossref_citationtrail_10_22146_jcef_65288
crossref_primary_10_22146_jcef_65288
nii_cinii_1870302168320919680
PublicationCentury 2000
PublicationDate 2021-08-31
PublicationDateYYYYMMDD 2021-08-31
PublicationDate_xml – month: 08
  year: 2021
  text: 2021-08-31
  day: 31
PublicationDecade 2020
PublicationTitle Journal of the Civil Engineering Forum
PublicationYear 2021
Publisher Universitas Gadjah Mada
Publisher_xml – name: Universitas Gadjah Mada
SSID ssib044745908
ssj0002246475
Score 2.1549814
Snippet Maintenance of infrastructures is a crucial activity to ensure safety using crack detection methods on concrete structures. However, most practice of crack...
SourceID doaj
crossref
nii
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 323
SubjectTerms Civil Engineering
convolutional neural network
Convolutional Neural Network; U-Net; DeepLabV3+; Crack Detection; Maintenance of Infrastructures
crack detection
deeplabv3
Engineering (General). Civil engineering (General)
maintenance of infrastructures
TA1-2040
u-net
Title Crack Detection on Concrete Surfaces Using Deep Encoder-Decoder Convolutional Neural Network: A Comparison Study Between U-Net and DeepLabV3
URI https://cir.nii.ac.jp/crid/1870302168320919680
https://doaj.org/article/7f118a6d33734fedab72e969485fa238
Volume 7
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2549-5925
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002246475
  issn: 2581-1037
  databaseCode: DOA
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2549-5925
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044745908
  issn: 2581-1037
  databaseCode: M~E
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Pa9swFBYj9LAdRtttLGs7dMhpoMWWFEneLU1SdtjCYMvIzcj6AdmKE7wk0Ev_gv3RfU_2shwGvQyMhM2zJes99J7Ep-8RMshk0BBZRBaNi0xWQrCiiorp3GUxz6OO0aZkE3o-N8tl8eUo1Rdiwlp64HbghhreMFZ5IbSQMXhbaR4KhaQm0YK_wdk308XRYgosSUotMZn3YbcFadNkYt3lI4MYLqHbw3ocE1sPf7gQ36sRT_lX_rqnxOIPTqderY6czs0ped5Fi3Tc9vKMPAn1OXl2xCH4gvyeNNb9pNOwTaCqmsI1WdcQDG4D_bprImKuaEIGgFDY0FmNx9gbNg2pRuF9Z3_QFJJ1pCqhwz_QMZ0cMhVSBB3e0esW2kUXDKSorX367idbfRcvyeJm9m3ykXUpFpjjsNBgvHCVFbbwSgWb2M28RML1KmTBy8ArW0RwcdXIau8dF16ZKLyRecyUgTvxivTqdR1eE-q0cCpzweUjLaOFdYuEqdNACARaslz1ybs_I1u6jn8c02DclrAOSWooUQ1lUkOfDA7Cm5Z2499i16iigwhyZacHYEFlZ0HlYxbUJ1egYOgTlrnBKZDn8HccQqlCmezN_2jkgjzliIZJu9GXpLdtduGKnLj9dvWreZuMF8rP97MHtojwAg
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Crack+Detection+on+Concrete+Surfaces+Using+Deep+Encoder-Decoder+Convolutional+Neural+Network%3A+A+Comparison+Study+Between+U-Net+and+DeepLabV3&rft.jtitle=Journal+of+the+civil+engineering+forum+%28Online%29&rft.au=Patrick+Nicholas+Hadinata&rft.au=Djoni+Simanta&rft.au=Liyanto+Eddy&rft.au=Kohei+Nagai&rft.date=2021-08-31&rft.pub=Universitas+Gadjah+Mada&rft.issn=2581-1037&rft.eissn=2549-5925&rft.volume=7&rft.issue=3&rft.spage=323&rft.epage=334&rft_id=info:doi/10.22146%2Fjcef.65288&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_7f118a6d33734fedab72e969485fa238
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2581-1037&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2581-1037&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2581-1037&client=summon