Show simple item record

dc.contributor.author
Quqa, Said
dc.contributor.author
Martakis, Panagiotis
dc.contributor.author
Movsessian, Artur
dc.contributor.author
Pai, Sai
dc.contributor.author
Reuland, Yves
dc.contributor.author
Chatzi, Eleni
dc.date.accessioned
2022-02-02T10:44:35Z
dc.date.available
2021-11-15T03:53:28Z
dc.date.available
2021-11-15T12:20:07Z
dc.date.available
2022-02-02T10:44:35Z
dc.date.issued
2022-02
dc.identifier.issn
2190-5452
dc.identifier.issn
2190-5479
dc.identifier.other
10.1007/s13349-021-00537-1
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/515111
dc.description.abstract
The advent of parallel computing capabilities, further boosted through the exploitation of graphics processing units, has resulted in the surge of new, previously infeasible, algorithmic schemes for structural health monitoring (SHM) tasks, such as the use of convolutional neural networks (CNNs) for vision-based SHM. This work proposes a novel approach for crack recognition in digital images based on coupling of CNNs and suited image processing techniques. The proposed method is applied on a dataset comprising images of the welding joints of a long-span steel bridge, collected via high-resolution consumer-grade digital cameras. The studied dataset includes photos taken in sub-optimal light and exposure conditions, with several noise contamination sources such as handwriting scripts, varying material textures, and, in some cases, under presence of external objects. The reference pixels representing the cracks, together with the crack width and length, are available and used for training and validating the proposed model. Although the proposed framework requires some knowledge of the "damaged areas", it alleviates the need for precise labeling of the cracks in the training dataset. Validation of the model by means of application on an unlabeled image set reveals promising results in terms of accuracy and robustness to noise sources.
en_US
dc.language.iso
en
en_US
dc.publisher
Springer
en_US
dc.subject
Vision based
en_US
dc.subject
Damage identification
en_US
dc.subject
Machine learning
en_US
dc.subject
Crack detection
en_US
dc.subject
Steel bridge
en_US
dc.subject
Structural health monitoring
en_US
dc.title
Two-step approach for fatigue crack detection in steel bridges using convolutional neural networks
en_US
dc.type
Journal Article
dc.date.published
2021-11-05
ethz.journal.title
Journal of Civil Structural Health Monitoring
ethz.journal.volume
12
en_US
ethz.journal.issue
1
en_US
ethz.pages.start
127
en_US
ethz.pages.end
140
en_US
ethz.grant
Real-time Earthquake Risk Reduction for Europe
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Heidelberg
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02605 - Institut für Baustatik u. Konstruktion / Institute of Structural Engineering::03890 - Chatzi, Eleni / Chatzi, Eleni
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02605 - Institut für Baustatik u. Konstruktion / Institute of Structural Engineering::03890 - Chatzi, Eleni / Chatzi, Eleni
ethz.grant.agreementno
821115
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.date.deposited
2021-11-15T03:54:40Z
ethz.source
WOS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2022-02-02T10:44:42Z
ethz.rosetta.lastUpdated
2023-02-07T00:07:58Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Two-step%20approach%20for%20fatigue%20crack%20detection%20in%20steel%20bridges%20using%20convolutional%20neural%20networks&rft.jtitle=Journal%20of%20Civil%20Structural%20Health%20Monitoring&rft.date=2022-02&rft.volume=12&rft.issue=1&rft.spage=127&rft.epage=140&rft.issn=2190-5452&2190-5479&rft.au=Quqa,%20Said&Martakis,%20Panagiotis&Movsessian,%20Artur&Pai,%20Sai&Reuland,%20Yves&rft.genre=article&rft_id=info:doi/10.1007/s13349-021-00537-1&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record