Published December 5, 2020 | Version 20.0
Dataset Open

Dataset of cracks on DIC images

Authors/Creators

  • 1. Laboratory of Earthquake Engineering and Structural Dynamics (EESD), School of Architecture, Civil and Environmental Engineering (ENAC), École Polytechnique Fédérale de Lausanne (EPFL), 1015 Lausanne, Switzerland.
  • 2. Swiss Data Science Center, EPFL and ETH Zurich, Switzerland
  • 3. RISE Research Institutes of Sweden, Brinellgatan 4, 504 62 Borås, Sweden
  • 4. Laboratory of Earthquake Engineering and Structural Dynamics (EESD), School of Architecture, Civil and Environmental Engineering (ENAC), École Polytechnique Fédérale de Lausanne (EPFL), 1015 Lausanne, Switzerland

Description

This dataset contains crack images and corresponding annotated ground truth masks. This data was used to train, validate, and test a deep convolutional neural network to detect crack pixels on images taken as input for the digital image correlation (DIC) method. 

For more information about the trained network, please refer to our publication at this link.  

The source codes to reproduce the results are shared at this link.

Please cite the following articles:

[1] Rezaie, A., Achanta, R., Godio, M., & Beyer, K. (2020). Comparison of crack segmentation using digital image correlation measurements and deep learning. Construction and Building Materials, 261, 120474. doi:https://doi.org/10.1016/j.conbuildmat.2020.120474

[2] Rezaie, A., Godio, M., & Beyer, K. (2021). Investigating the cracking of plastered stone masonry walls under shear–compression loading. Construction and Building Materials, 306, 124831.
doi:https://doi.org/10.1016/j.conbuildmat.2021.124831

Files

DIC_crack_dataset.zip

Files (33.0 MB)

Name Size Download all
md5:68c20e1286f092a0aa38f1e290090585
33.0 MB Preview Download

Additional details

Related works

Is supplement to
Journal article: 10.1016/j.conbuildmat.2020.120474 (DOI)
Journal article: 10.1016/j.conbuildmat.2021.124831 (DOI)
Dataset: 10.5281/zenodo.5052675 (DOI)

Funding

Swiss National Science Foundation
Equivalent frame models for the in-plane and out-of-plane response of unreinforced masonry buildings 200021_175903