Pixel-Level Fatigue Crack Segmentation in Large-Scale Images of Steel Structures Using an Encoder–Decoder Network

Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset ma...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sensors (Basel, Switzerland) Jg. 21; H. 12; S. 4135
Hauptverfasser: Dong, Chuanzhi, Li, Liangding, Yan, Jin, Zhang, Zhiming, Pan, Hong, Catbas, Fikret Necati
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 16.06.2021
MDPI
Schlagworte:
ISSN:1424-8220, 1424-8220
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset maintenance, and management of existing structures and prevent the early permit post and improve life cycles. In current research and engineering practices, visual inspection is the most widely implemented approach for fatigue crack inspection. However, the inspection accuracy of this method highly relies on the subjective judgment of the inspectors. Furthermore, it needs large amounts of cost, time, and labor force. Non-destructive testing methods can provide accurate detection results, but the cost is very high. To overcome the limitations of current fatigue crack detection methods, this study presents a pixel-level fatigue crack segmentation framework for large-scale images with complicated backgrounds taken from steel structures by using an encoder-decoder network, which is modified from the U-net structure. To effectively train and test the images with large resolutions such as 4928 × 3264 pixels or larger, the large images were cropped into small images for training and testing. The final segmentation results of the original images are obtained by assembling the segment results in the small images. Additionally, image post-processing including opening and closing operations were implemented to reduce the noises in the segmentation maps. The proposed method achieved an acceptable accuracy of automatic fatigue crack segmentation in terms of average intersection over union (mIOU). A comparative study with an FCN model that implements ResNet34 as backbone indicates that the proposed method using U-net could give better fatigue crack segmentation performance with fewer training epochs and simpler model structure. Furthermore, this study also provides helpful considerations and recommendations for researchers and practitioners in civil infrastructure engineering to apply image-based fatigue crack detection.
AbstractList Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset maintenance, and management of existing structures and prevent the early permit post and improve life cycles. In current research and engineering practices, visual inspection is the most widely implemented approach for fatigue crack inspection. However, the inspection accuracy of this method highly relies on the subjective judgment of the inspectors. Furthermore, it needs large amounts of cost, time, and labor force. Non-destructive testing methods can provide accurate detection results, but the cost is very high. To overcome the limitations of current fatigue crack detection methods, this study presents a pixel-level fatigue crack segmentation framework for large-scale images with complicated backgrounds taken from steel structures by using an encoder-decoder network, which is modified from the U-net structure. To effectively train and test the images with large resolutions such as 4928 × 3264 pixels or larger, the large images were cropped into small images for training and testing. The final segmentation results of the original images are obtained by assembling the segment results in the small images. Additionally, image post-processing including opening and closing operations were implemented to reduce the noises in the segmentation maps. The proposed method achieved an acceptable accuracy of automatic fatigue crack segmentation in terms of average intersection over union (mIOU). A comparative study with an FCN model that implements ResNet34 as backbone indicates that the proposed method using U-net could give better fatigue crack segmentation performance with fewer training epochs and simpler model structure. Furthermore, this study also provides helpful considerations and recommendations for researchers and practitioners in civil infrastructure engineering to apply image-based fatigue crack detection.
Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset maintenance, and management of existing structures and prevent the early permit post and improve life cycles. In current research and engineering practices, visual inspection is the most widely implemented approach for fatigue crack inspection. However, the inspection accuracy of this method highly relies on the subjective judgment of the inspectors. Furthermore, it needs large amounts of cost, time, and labor force. Non-destructive testing methods can provide accurate detection results, but the cost is very high. To overcome the limitations of current fatigue crack detection methods, this study presents a pixel-level fatigue crack segmentation framework for large-scale images with complicated backgrounds taken from steel structures by using an encoder-decoder network, which is modified from the U-net structure. To effectively train and test the images with large resolutions such as 4928 × 3264 pixels or larger, the large images were cropped into small images for training and testing. The final segmentation results of the original images are obtained by assembling the segment results in the small images. Additionally, image post-processing including opening and closing operations were implemented to reduce the noises in the segmentation maps. The proposed method achieved an acceptable accuracy of automatic fatigue crack segmentation in terms of average intersection over union (mIOU). A comparative study with an FCN model that implements ResNet34 as backbone indicates that the proposed method using U-net could give better fatigue crack segmentation performance with fewer training epochs and simpler model structure. Furthermore, this study also provides helpful considerations and recommendations for researchers and practitioners in civil infrastructure engineering to apply image-based fatigue crack detection.Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset maintenance, and management of existing structures and prevent the early permit post and improve life cycles. In current research and engineering practices, visual inspection is the most widely implemented approach for fatigue crack inspection. However, the inspection accuracy of this method highly relies on the subjective judgment of the inspectors. Furthermore, it needs large amounts of cost, time, and labor force. Non-destructive testing methods can provide accurate detection results, but the cost is very high. To overcome the limitations of current fatigue crack detection methods, this study presents a pixel-level fatigue crack segmentation framework for large-scale images with complicated backgrounds taken from steel structures by using an encoder-decoder network, which is modified from the U-net structure. To effectively train and test the images with large resolutions such as 4928 × 3264 pixels or larger, the large images were cropped into small images for training and testing. The final segmentation results of the original images are obtained by assembling the segment results in the small images. Additionally, image post-processing including opening and closing operations were implemented to reduce the noises in the segmentation maps. The proposed method achieved an acceptable accuracy of automatic fatigue crack segmentation in terms of average intersection over union (mIOU). A comparative study with an FCN model that implements ResNet34 as backbone indicates that the proposed method using U-net could give better fatigue crack segmentation performance with fewer training epochs and simpler model structure. Furthermore, this study also provides helpful considerations and recommendations for researchers and practitioners in civil infrastructure engineering to apply image-based fatigue crack detection.
Author Yan, Jin
Zhang, Zhiming
Li, Liangding
Catbas, Fikret Necati
Pan, Hong
Dong, Chuanzhi
AuthorAffiliation 2 Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA; leoriohope@knights.ucf.edu
1 Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816, USA; catbas@ucf.edu
3 Palo Alto Research Center, Palo Alto, CA 94304, USA; jyan@parc.com
5 Department of Civil and Environmental Engineering, North Dakota State University, Fargo, ND 58105, USA; hong.pan@ndsu.edu
4 School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ 85281, USA; zzhan506@asu.edu
AuthorAffiliation_xml – name: 3 Palo Alto Research Center, Palo Alto, CA 94304, USA; jyan@parc.com
– name: 1 Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816, USA; catbas@ucf.edu
– name: 4 School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ 85281, USA; zzhan506@asu.edu
– name: 5 Department of Civil and Environmental Engineering, North Dakota State University, Fargo, ND 58105, USA; hong.pan@ndsu.edu
– name: 2 Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA; leoriohope@knights.ucf.edu
Author_xml – sequence: 1
  givenname: Chuanzhi
  orcidid: 0000-0001-6010-2859
  surname: Dong
  fullname: Dong, Chuanzhi
– sequence: 2
  givenname: Liangding
  surname: Li
  fullname: Li, Liangding
– sequence: 3
  givenname: Jin
  orcidid: 0000-0002-2288-8114
  surname: Yan
  fullname: Yan, Jin
– sequence: 4
  givenname: Zhiming
  orcidid: 0000-0002-7678-605X
  surname: Zhang
  fullname: Zhang, Zhiming
– sequence: 5
  givenname: Hong
  surname: Pan
  fullname: Pan, Hong
– sequence: 6
  givenname: Fikret Necati
  orcidid: 0000-0001-9255-9976
  surname: Catbas
  fullname: Catbas, Fikret Necati
BookMark eNplksFuEzEQhi1URNvAgTewxAUOSz22d-O9IKHQQqQIkFLOlteeLE43drF3C9x4B96QJ8FtCqLlYo_G3_-PNTPH5CDEgIQ8BfZSiJadZA7AJYj6ATkCyWWlOGcH_8SH5DjnLWNcCKEekUMhOVNNC0ckf_TfcKhWeIUDPTOj7yeki2TsBV1jv8MwllwM1Ae6MqnHam3NgHS5Mz1mGjd0PWJRrsc02XFKJfcp-9BTE-hpsNFh-vXj5xu8ieh7HL_GdPGYPNyYIeOT23tGzs9OzxfvqtWHt8vF61VlpWzGyrSdadsa5IaJpsWOKzANSNeJuYCuYcDQCOYkIAjbcgcKwKi5a1VnjWRiRpZ7WxfNVl8mvzPpu47G65tETL02afR2QO2KBDljDhora1l3xrH53Dkrupor2xavV3uvy6nbobOlL8kMd0zvvgT_WffxSisupCzHjDy_NUjxy4R51DufLQ6DCRinrHktVZlgA6Kgz-6h2zilUDp1TdWg5qqFQp3sKZtizgk32vr9rEp9P2hg-no39N_dKIoX9xR_vv8_-xuZcroS
CitedBy_id crossref_primary_10_1016_j_measurement_2025_116867
crossref_primary_10_1016_j_istruc_2022_06_013
crossref_primary_10_1177_14759217241261089
crossref_primary_10_1002_adem_202201430
crossref_primary_10_1007_s13369_022_07171_z
crossref_primary_10_1016_j_engstruct_2025_121191
crossref_primary_10_3390_s22218580
crossref_primary_10_1007_s11760_025_03913_2
crossref_primary_10_1080_15732479_2024_2390461
crossref_primary_10_1016_j_tafmec_2025_105166
crossref_primary_10_1007_s11760_023_02905_4
crossref_primary_10_1002_cepa_2585
crossref_primary_10_1016_j_ijfatigue_2025_109179
crossref_primary_10_3390_s22186852
crossref_primary_10_1177_13694332231213460
crossref_primary_10_3390_app11209555
crossref_primary_10_1016_j_autcon_2024_105354
crossref_primary_10_3390_s21217405
crossref_primary_10_1007_s00170_021_08047_6
crossref_primary_10_1155_2024_4863177
crossref_primary_10_1016_j_aei_2025_103186
crossref_primary_10_1016_j_autcon_2024_105955
crossref_primary_10_1016_j_autcon_2021_104022
crossref_primary_10_1016_j_autcon_2024_105896
crossref_primary_10_3390_asi7010011
crossref_primary_10_1016_j_autcon_2022_104666
crossref_primary_10_1016_j_ymssp_2022_109631
crossref_primary_10_3390_rs16162910
crossref_primary_10_1007_s11831_025_10279_8
crossref_primary_10_1016_j_conbuildmat_2024_134950
crossref_primary_10_1016_j_ymssp_2022_109607
crossref_primary_10_3390_s24113685
crossref_primary_10_1007_s11803_023_2156_1
crossref_primary_10_1177_09544097241262866
Cites_doi 10.1109/CVPR.2017.243
10.1007/978-3-319-24574-4_28
10.3390/s20061790
10.1111/mice.12412
10.1177/1475921718764873
10.1016/j.dcan.2021.03.003
10.1002/stc.2075
10.1007/s12652-020-01803-8
10.1016/j.eng.2018.11.027
10.1016/j.conbuildmat.2020.119397
10.1177/14759217211006485
10.1016/j.engfracmech.2019.02.022
10.3390/app11020518
10.1177/0361198119839988
10.1016/j.ymssp.2020.106688
10.1177/1475921720940068
10.1177/1369433220986638
10.1016/j.autcon.2018.11.028
10.1109/TPAMI.2016.2572683
10.1177/1475921720935585
10.1109/CVPR.2016.90
10.1111/mice.12353
10.1109/CVPR.2016.308
10.1109/TIE.2019.2945265
10.1016/j.measurement.2020.107498
10.1111/mice.12256
10.1111/mice.12440
10.1177/1475921720972416
10.20944/preprints201906.0023.v1
10.1061/(ASCE)BE.1943-5592.0001598
10.1002/9781118411124
10.1007/s13349-020-00431-2
10.1080/15732479.2019.1650078
10.1016/j.autcon.2019.04.005
10.1016/j.engstruct.2020.111224
10.3390/s19081843
10.1061/(ASCE)ST.1943-541X.0002321
10.1115/1.4029947
10.1016/j.eng.2018.11.030
10.1109/ACCESS.2020.2995276
10.1177/1475921718806895
10.1061/(ASCE)BE.1943-5592.0001507
ContentType Journal Article
Copyright 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2021 by the authors. 2021
Copyright_xml – notice: 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2021 by the authors. 2021
DBID AAYXX
CITATION
3V.
7X7
7XB
88E
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
FYUFA
GHDGH
K9.
M0S
M1P
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
PRINS
7X8
5PM
DOA
DOI 10.3390/s21124135
DatabaseName CrossRef
ProQuest Central (Corporate)
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
ProQuest Hospital Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni Edition)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest One Community College
ProQuest Central Korea
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Health & Medical Complete (Alumni)
Health & Medical Collection (Alumni Edition)
Medical Database
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Central China
ProQuest Central
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Health & Medical Research Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList CrossRef
Publicly Available Content Database


MEDLINE - Academic
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1424-8220
ExternalDocumentID oai_doaj_org_article_d8bce200d16c4545bad077ddc3b528c9
PMC8234482
10_3390_s21124135
GroupedDBID ---
123
2WC
53G
5VS
7X7
88E
8FE
8FG
8FI
8FJ
AADQD
AAHBH
AAYXX
ABDBF
ABUWG
ACUHS
ADBBV
ADMLS
AENEX
AFFHD
AFKRA
AFZYC
ALMA_UNASSIGNED_HOLDINGS
BENPR
BPHCQ
BVXVI
CCPQU
CITATION
CS3
D1I
DU5
E3Z
EBD
ESX
F5P
FYUFA
GROUPED_DOAJ
GX1
HH5
HMCUK
HYE
IAO
ITC
KQ8
L6V
M1P
M48
MODMG
M~E
OK1
OVT
P2P
P62
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQQKQ
PROAC
PSQYO
RNS
RPM
TUS
UKHRP
XSB
~8M
3V.
7XB
8FK
AZQEC
DWQXO
K9.
PKEHL
PQEST
PQUKI
PRINS
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c446t-a9ba99514f0369eb281a614db3731b6010ea30d41e13c92d1811a87d98bca403
IEDL.DBID BENPR
ISICitedReferencesCount 36
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000666398000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1424-8220
IngestDate Tue Oct 14 19:00:56 EDT 2025
Tue Nov 04 01:56:34 EST 2025
Fri Sep 05 08:45:16 EDT 2025
Tue Oct 07 07:18:22 EDT 2025
Sat Nov 29 07:21:37 EST 2025
Tue Nov 18 22:02:32 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 12
Language English
License Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c446t-a9ba99514f0369eb281a614db3731b6010ea30d41e13c92d1811a87d98bca403
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-2288-8114
0000-0001-9255-9976
0000-0002-7678-605X
0000-0001-6010-2859
OpenAccessLink https://www.proquest.com/docview/2545187891?pq-origsite=%requestingapplication%
PMID 34208691
PQID 2545187891
PQPubID 2032333
ParticipantIDs doaj_primary_oai_doaj_org_article_d8bce200d16c4545bad077ddc3b528c9
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8234482
proquest_miscellaneous_2548413613
proquest_journals_2545187891
crossref_citationtrail_10_3390_s21124135
crossref_primary_10_3390_s21124135
PublicationCentury 2000
PublicationDate 20210616
PublicationDateYYYYMMDD 2021-06-16
PublicationDate_xml – month: 6
  year: 2021
  text: 20210616
  day: 16
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Sensors (Basel, Switzerland)
PublicationYear 2021
Publisher MDPI AG
MDPI
Publisher_xml – name: MDPI AG
– name: MDPI
References Kong (ref_13) 2018; 33
Spencer (ref_11) 2019; 5
Dong (ref_20) 2020; 16
Chen (ref_24) 2020; 141
Dung (ref_29) 2019; 99
ref_36
ref_12
Dong (ref_21) 2020; 224
ref_33
ref_32
ref_31
Aslam (ref_41) 2020; 12
Dong (ref_19) 2019; 18
Megid (ref_7) 2019; 211
Wang (ref_27) 2020; 8
ref_39
ref_16
ref_38
ref_15
Dong (ref_18) 2019; 24
Liu (ref_37) 2019; 104
Dong (ref_5) 2020; 10
Mei (ref_42) 2020; 256
Choi (ref_44) 2020; 67
Xu (ref_10) 2019; 18
Yang (ref_34) 2018; 33
ref_47
ref_46
Campbell (ref_6) 2020; 25
ref_45
Bao (ref_14) 2019; 5
ref_43
ref_40
ref_1
Long (ref_30) 2017; 39
Bang (ref_35) 2019; 34
ref_3
ref_2
ref_28
ref_26
ref_9
ref_8
Xu (ref_22) 2018; 25
Dellenbaugh (ref_23) 2020; 25
Chen (ref_25) 2017; 32
ref_4
Hoskere (ref_17) 2019; 145
References_xml – ident: ref_43
  doi: 10.1109/CVPR.2017.243
– ident: ref_36
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref_9
  doi: 10.3390/s20061790
– volume: 33
  start-page: 1090
  year: 2018
  ident: ref_34
  article-title: Automatic pixel-level crack detection and measurement using fully convolutional network
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12412
– volume: 18
  start-page: 653
  year: 2019
  ident: ref_10
  article-title: Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images
  publication-title: Struct. Health Monit.
  doi: 10.1177/1475921718764873
– ident: ref_26
  doi: 10.1016/j.dcan.2021.03.003
– volume: 25
  start-page: 1
  year: 2018
  ident: ref_22
  article-title: Identification framework for cracks on a steel structure surface by a restricted Boltzmann machines algorithm based on consumer-grade camera images
  publication-title: Struct. Control Health Monit.
  doi: 10.1002/stc.2075
– volume: 12
  start-page: 4205
  year: 2020
  ident: ref_41
  article-title: Localization and segmentation of metal cracks using deep learning
  publication-title: J. Ambient Intell. Humaniz. Comput.
  doi: 10.1007/s12652-020-01803-8
– volume: 5
  start-page: 234
  year: 2019
  ident: ref_14
  article-title: The State of the Art of Data Science and Engineering in Structural Health Monitoring
  publication-title: Engineering
  doi: 10.1016/j.eng.2018.11.027
– volume: 256
  start-page: 119397
  year: 2020
  ident: ref_42
  article-title: A cost effective solution for pavement crack inspection using cameras and deep neural networks
  publication-title: Constr. Build. Mater.
  doi: 10.1016/j.conbuildmat.2020.119397
– ident: ref_47
  doi: 10.1177/14759217211006485
– volume: 211
  start-page: 198
  year: 2019
  ident: ref_7
  article-title: Monitoring fatigue cracks on eyebars of steel bridges using acoustic emission: A case study
  publication-title: Eng. Fract. Mech.
  doi: 10.1016/j.engfracmech.2019.02.022
– ident: ref_38
  doi: 10.3390/app11020518
– ident: ref_28
  doi: 10.1177/0361198119839988
– volume: 141
  start-page: 106688
  year: 2020
  ident: ref_24
  article-title: Data Consistency Assessment Function (DCAF)
  publication-title: Mech. Syst. Signal Process.
  doi: 10.1016/j.ymssp.2020.106688
– ident: ref_39
  doi: 10.1177/1475921720940068
– ident: ref_40
  doi: 10.1177/1369433220986638
– volume: 24
  start-page: 617
  year: 2019
  ident: ref_18
  article-title: A completely non-contact recognition system for bridge unit influence line using portable cameras and computer vision
  publication-title: Smart Struct. Syst.
– volume: 99
  start-page: 52
  year: 2019
  ident: ref_29
  article-title: Autonomous concrete crack detection using deep fully convolutional neural network
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2018.11.028
– volume: 39
  start-page: 640
  year: 2017
  ident: ref_30
  article-title: Fully Convolutional Networks for Semantic Segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2572683
– ident: ref_12
  doi: 10.1177/1475921720935585
– ident: ref_33
  doi: 10.1109/CVPR.2016.90
– volume: 33
  start-page: 783
  year: 2018
  ident: ref_13
  article-title: Vision-based fatigue crack detection of steel structures using video feature tracking
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12353
– ident: ref_32
  doi: 10.1109/CVPR.2016.308
– volume: 67
  start-page: 8016
  year: 2020
  ident: ref_44
  article-title: SDDNet: Real-Time Crack Segmentation
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2019.2945265
– ident: ref_3
  doi: 10.1016/j.measurement.2020.107498
– ident: ref_4
– ident: ref_31
– volume: 32
  start-page: 271
  year: 2017
  ident: ref_25
  article-title: A texture-based video processing methodology using Bayesian data fusion for autonomous crack detection on metallic surfaces
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12256
– volume: 34
  start-page: 713
  year: 2019
  ident: ref_35
  article-title: Encoder–decoder network for pixel-level road crack detection in black-box images
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12440
– ident: ref_15
  doi: 10.1177/1475921720972416
– ident: ref_16
  doi: 10.20944/preprints201906.0023.v1
– ident: ref_46
– volume: 25
  start-page: 1
  year: 2020
  ident: ref_23
  article-title: Development of a distortion-induced fatigue crack characterization methodology using digital image correlation
  publication-title: J. Bridg. Eng.
  doi: 10.1061/(ASCE)BE.1943-5592.0001598
– ident: ref_1
  doi: 10.1002/9781118411124
– volume: 10
  start-page: 1001
  year: 2020
  ident: ref_5
  article-title: A portable monitoring approach using cameras and computer vision for bridge load rating in smart cities
  publication-title: J. Civ. Struct. Health Monit.
  doi: 10.1007/s13349-020-00431-2
– volume: 16
  start-page: 51
  year: 2020
  ident: ref_20
  article-title: Structural displacement monitoring using deep learning-based full field optical flow methods
  publication-title: Struct. Infrastruct. Eng.
  doi: 10.1080/15732479.2019.1650078
– volume: 104
  start-page: 129
  year: 2019
  ident: ref_37
  article-title: Computer vision-based concrete crack detection using U-net fully convolutional networks
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2019.04.005
– volume: 224
  start-page: 111224
  year: 2020
  ident: ref_21
  article-title: Investigation of vibration serviceability of a footbridge using computer vision-based methods
  publication-title: Eng. Struct.
  doi: 10.1016/j.engstruct.2020.111224
– ident: ref_45
– ident: ref_8
  doi: 10.3390/s19081843
– volume: 145
  start-page: 040190621
  year: 2019
  ident: ref_17
  article-title: Vision-based modal survey of civil infrastructure using unmanned aerial vehicles
  publication-title: J. Struct. Eng.
  doi: 10.1061/(ASCE)ST.1943-541X.0002321
– ident: ref_2
  doi: 10.1115/1.4029947
– volume: 5
  start-page: 199
  year: 2019
  ident: ref_11
  article-title: Advances in computer vision-based civil infrastructure inspection and monitoring
  publication-title: Engineering
  doi: 10.1016/j.eng.2018.11.030
– volume: 8
  start-page: 94204
  year: 2020
  ident: ref_27
  article-title: Machine vision-based monitoring methodology for the fatigue cracks in U-Rib-to-deck weld seams
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2995276
– volume: 18
  start-page: 1491
  year: 2019
  ident: ref_19
  article-title: Marker free monitoring of the grandstand structures and modal identification using computer vision methods
  publication-title: Struct. Health Monit.
  doi: 10.1177/1475921718806895
– volume: 25
  start-page: 1
  year: 2020
  ident: ref_6
  article-title: Benchmark for evaluating performance in visual inspection of fatigue cracking in steel bridges
  publication-title: J. Bridg. Eng.
  doi: 10.1061/(ASCE)BE.1943-5592.0001507
SSID ssj0023338
Score 2.5149815
Snippet Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further...
SourceID doaj
pubmedcentral
proquest
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
StartPage 4135
SubjectTerms Accuracy
Algorithms
Bridges
computer vision
Crack propagation
Datasets
Decision making
Decision theory
Decision trees
Deep learning
fatigue crack
Infrastructure
Machine learning
Metal fatigue
Neural networks
Nondestructive testing
Propagation
semantic segmentation
steel structures
Stress concentration
Support vector machines
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NjtMwEB6hFQc4IH5FYEEGceBibRyntX2EZSuQqmql7mFv0finS8Wuu2paxJF34A15EsZOWjUSEhduSTyJnJlJZj55_A3AO6lVjW5c8soK5DWdcIvScqG8cZKCbLCZZ3aqZjN9eWnOD1p9pZqwjh64U9yJ19YFMqUXY1dTuLfoS6W8d9KOKu3y1j3KenZgqodakpBXxyMkCdSftARz0gLSaBB9Mkn_ILMc1kUeBJrJQ3jQZ4jsQzezR3AnxMdw_4A38Am058sf4ZpPU8EPm5Bur7aBna7RfWPzcHXTbyeKbBnZNFV68zlZIrAvN_TzaNlqweabQHfOM3fslgA3y5UDDCM7i2mT-_r3z1-fQj5is65Q_ClcTM4uTj_zvnsCdwTxNhyNRUP5U72gIGUIQGuBFIu9lUoKm3BYQFn6WgQhnak8hXqBmkxECse6lM_gKK5ieA6MnmEo2Gm0pasJIiJqa_TCqlAb1AtZwPudUhvXM4unBhfXDSGMpP9mr_8C3u5Fbzs6jb8JfUyW2QskBux8gfyi6f2i-ZdfFHC8s2vTf5ZtQ2h4JLTSRhTwZj9MH1RaJcEYVtsso2kWlOYUoAb-MJjQcCQuv2Zqbl1JwrvVi__xBi_hXpUKaFKjpPExHJFPhFdw133fLNv16-zvfwA_AQjf
  priority: 102
  providerName: Directory of Open Access Journals
Title Pixel-Level Fatigue Crack Segmentation in Large-Scale Images of Steel Structures Using an Encoder–Decoder Network
URI https://www.proquest.com/docview/2545187891
https://www.proquest.com/docview/2548413613
https://pubmed.ncbi.nlm.nih.gov/PMC8234482
https://doaj.org/article/d8bce200d16c4545bad077ddc3b528c9
Volume 21
WOSCitedRecordID wos000666398000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: DOA
  dateStart: 20010101
  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: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: M~E
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Health Medical collection
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: 7X7
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: BENPR
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: PIMPY
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3LjtMwFLWYDgtmwRsRGCqDWLCxpo7T2l4hZmjFSJ0qorMoq8ivloqZZKZpESvEP_CHfAnXrhsmEmLDJsrjJrF0Yt977JtzEXrNBM-UGfRIqqkiGRwQrZgmlFtpGDhZp4PO7JhPJmI2k3mccKtjWuVuTAwDta2MnyM_AiLTp4ILSd9eXRNfNcqvrsYSGnto3yuVZR20fzyc5B8bysWAgW31hBiQ-6MarPxCUr_lhYJYfyvCbOdH3nA4o3v_29T76G4MNfG77bfxAN1y5UN0cEOA8BGq8-U3d0HGPnMIjwCkxcbhk5UyX_DULS7jf0klXpZ47FPGyRQgdfj0EkahGldzPF07uHMaRGg3wNxxSEHAqsTD0v8tv_r14-d7F_bwZJtx_hidj4bnJx9ILMNADHDFNVFSKwmBWDYHbyeBiQuqwKlbzTij2hM6p1jPZtRRZmRqIWagSgDWQhuV9dgT1Cmr0j1FGJ4hwWsKpXsmA66plNBSzDV3mVRizhL0ZodKYaJEua-UcVEAVfEAFg2ACXrVmF5tdTn-ZnTsoW0MvJR2OFGtFkXsmYWFZjoYKywdmAyQ08r2OLfWMN1PhZEJOtyhXMT-XRd_IE7Qy-Yy9Ey_3KJKV22CjYBWQLyUIN76oFoNal8pl5-DxrdIGRDn9Nm_X_4c3Ul9jo2vpTQ4RB1A271At83X9bJeddEen_GwFd3YMbphzgG2Z9-HcC4_Pcs__QZQJh1C
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3NbtQwEB6VLRLlwG8RgQIGgcQlahJ7N_YBIWi76qrpaqXdQzlFtuNdVm2Tkuzyc-MdeA5eiidhnD8aCXHrgVsSO4mTfJmZL558A_CS8pBJPfDcQPnSZbjiKkmV64eJ0BSdrFGlzmwUjsf85ERMNuBn8y-MTatsbGJpqJNM22_ku0hk-j4PufDfXnxybdUoO7valNCoYHFkvn1Byla8Ge3j830VBMOD2d6hW1cVcDVSn5UrhZIC4wo2R-MtkFhyX6KPShQNqa8sPzGSegnzjU-1CBJ0gb7kOHSutGQexcNeg02GWOc92JyMjicfWoZHkfBV8kWUCm-3QHZl5636HadX1gboBLTddMxL_m14-z-7M3fgVh1Ik3cV8u_Chknvwc1L8or3oZgsv5ozN7J5UWSIEFysDdnLpT4lU7M4r_-6SskyJZFNiHenCFhDRudoYwuSzcl0ZXDPaSmxu85xW5lgQWRKDlKrBZD_-v5j35RLZFzl02_D7Cou-gH00iw1D4HgMQTGBFwqTzNk0lJyJfhchYYJyefUgdcNCGJdC7DbOiBnMRIxi5e4xYsDL9quF5XqyN86vbdIajtYofByQ5Yv4truxAkO06AlTPyBZggUJRMvDJNEU9UPuBYO7DSgimvrVcR_EOXA87YZ7Y6dTJKpydZlH46jwGjQgbCD386Aui3p8mOpYM4DyhgPHv375M_gxuHsOIqj0fjoMWwFNpvIVo0a7EAPn7x5Atf159WyyJ_W7yGB-Irx_RvMvXHH
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFL0qLUKw4FlEoIBBILGJJok9E3uBEHQ6YtRhFGm6KKvIdpxhRJuUZIbHjn_ga_gdvoTrvGgkxK4Ldnk4iZMc33tPfHMuwDPKQyb1yHMD5UuX4YqrJFWuHyZCU3SyRlU6s7NwPufHxyLagp_tvzA2rbK1iZWhTnJtv5EPkMgMfR5y4Q_SJi0iGk9enX1ybQUpO9PaltOoIXJovn1B-la-nI7xXT8PgsnB0f5bt6kw4GqkQWtXCiUFxhgsRUMukGRyX6K_ShQNqa8sVzGSegnzjU-1CBJ0h77keBtcack8iqe9BDsYkTMcYjvR9F30vmN7FMlfLWVEqfAGJTItO4c17DnAqk5AL7jtp2ae83WTG__xU7oJ15sAm7yuR8Qt2DLZbbh2TnbxDpTR6qs5cWc2X4pMEJrLjSH7hdQfycIsT5u_sTKyysjMJsq7CwSyIdNTtL0lyVOyWBs8clFJ724K3FYlXhCZkYPMagQUv77_GJtqiczrPPtdOLqIm74L21memXtA8BwCYwUulacZMmwpuRI8VaFhQvKUOvCiBUSsG2F2Wx_kJEaCZrETd9hx4GnX9KxWI_lbozcWVV0DKyBebciLZdzYozjBbhq0kIk_0gxBo2TihWGSaKqGAdfCgb0WYHFj1cr4D7oceNLtRntkJ5lkZvJN1YZjLzBKdCDsYbnXof6ebPWhUjbnAWWMB_f_ffHHcAVBHc-m88MHcDWwSUa2mNRoD7bxxZuHcFl_Xq_K4lEzJAnEFwzv39J-eoc
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=Pixel-Level+Fatigue+Crack+Segmentation+in+Large-Scale+Images+of+Steel+Structures+Using+an+Encoder%E2%80%93Decoder+Network&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Dong%2C+Chuanzhi&rft.au=Li%2C+Liangding&rft.au=Yan%2C+Jin&rft.au=Zhang%2C+Zhiming&rft.date=2021-06-16&rft.issn=1424-8220&rft.eissn=1424-8220&rft.volume=21&rft.issue=12&rft.spage=4135&rft_id=info:doi/10.3390%2Fs21124135&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_s21124135
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon