Show simple item record

dc.contributor.author
Rezaie, Amir
dc.contributor.author
Achanta, Radhakrishna
dc.contributor.author
Godio, Michele
dc.contributor.author
Beyer, Katrin
dc.date.accessioned
2020-09-07T07:27:29Z
dc.date.available
2020-09-07T04:48:34Z
dc.date.available
2020-09-07T07:27:29Z
dc.date.issued
2020-11-20
dc.identifier.issn
0950-0618
dc.identifier.other
10.1016/j.conbuildmat.2020.120474
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/438722
dc.description.abstract
Reliable methods for detecting pixels that represent cracks from laboratory images taken for digital image correlation (DIC) are required for two main reasons. Firstly, the segmented crack maps are used as an input for some DIC methods that are based on discontinuous fields. Secondly, detected crack patterns can serve as inputs for predictive empirical models to obtain the level of damage to a body. The aim of this paper is to compare the performance of two approaches for crack segmentation on grayscale images acquired from two experimental campaigns on stone masonry walls. In the first approach, a threshold is applied to the maximum principal strain map calculated using post-processed DIC results. In the second approach, a deep convolutional neural network is used. The two methods are compared in terms of standard segmentation criteria, namely precision, dice coefficient and sensitivity. It is shown that the precision and dice coefficient obtained from the deep learning approach are much higher than those obtained from the threshold method (by almost 47% and 34%, respectively). However, the sensitivity computed from the deep learning method is slightly (~4%) lower than the threshold method. These results show that the deep learning method can better preserve the geometry of detected crack patterns, and the prediction in terms of pixels belonging to a crack is finally more accurate than the threshold method. © 2020 Elsevier Ltd
en_US
dc.language.iso
en
en_US
dc.publisher
Elsevier
en_US
dc.subject
Crack segmentation
en_US
dc.subject
Digital image correlation
en_US
dc.subject
Deep learning
en_US
dc.subject
Threshold method
en_US
dc.subject
Masonry
en_US
dc.title
Comparison of crack segmentation using digital image correlation measurements and deep learning
en_US
dc.type
Journal Article
dc.date.published
2020-09-03
ethz.journal.title
Construction and Building Materials
ethz.journal.volume
261
en_US
ethz.journal.abbreviated
Constr. build. mater.
ethz.pages.start
120474
en_US
ethz.size
12 p.
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2020-09-07T04:48:42Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-09-07T07:27:50Z
ethz.rosetta.lastUpdated
2021-02-15T17:01:15Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Comparison%20of%20crack%20segmentation%20using%20digital%20image%20correlation%20measurements%20and%20deep%20learning&rft.jtitle=Construction%20and%20Building%20Materials&rft.date=2020-11-20&rft.volume=261&rft.spage=120474&rft.issn=0950-0618&rft.au=Rezaie,%20Amir&Achanta,%20Radhakrishna&Godio,%20Michele&Beyer,%20Katrin&rft.genre=article&rft_id=info:doi/10.1016/j.conbuildmat.2020.120474&
 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