Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Comparison of crack segmentation using digital image correlation measurements and deep learning
EPFL Ecole Polythecnique Federale de Lausanne, Switzerland.
Swiss Data Science Center, Switzerland; ETH Zurich, Switzerland.
RISE Research Institutes of Sweden, Materials and Production, Applied Mechanics. (Building and Infrastructure)ORCID iD: 0000-0002-9586-8667
EPFL Ecole Polythecnique Federale de Lausanne, Switzerland.
2020 (English)In: Construction and Building Materials, ISSN 0950-0618, E-ISSN 1879-0526, Vol. 261, article id 120474Article in journal (Refereed) Published
Abstract [en]

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 bet-ter 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.

Place, publisher, year, edition, pages
Elsevier Ltd , 2020. Vol. 261, article id 120474
Keywords [en]
Crack segmentation, Digital image correlation, Deep learning, Threshold method, Masonry
National Category
Building Technologies Computer Sciences
Identifiers
URN: urn:nbn:se:ri:diva-48270DOI: 10.1016/j.conbuildmat.2020.120474Scopus ID: 2-s2.0-85090025169OAI: oai:DiVA.org:ri-48270DiVA, id: diva2:1464052
Available from: 2020-09-04 Created: 2020-09-04 Last updated: 2023-04-28Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Godio, Michele

Search in DiVA

By author/editor
Godio, Michele
By organisation
Applied Mechanics
In the same journal
Construction and Building Materials
Building TechnologiesComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 91 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf