SDNET2018: An annotated image data set for non-contact concrete crack detection using deep convolutional neural networks

Authors

Sattar Dorafshan, Utah State UniversityFollow
Robert J. Thomas, Clarkson UniversityFollow
Marc Maguire, Utah State UniversityFollow

Date of this Version

2018

Citation

Data in Brief 21 (2018) 1664–1668

Comments

© 2018 The Authors.

Open access

https://doi.org/10.1016/j.dib.2018.11.015

Abstract

SDNET2018 is an annotated image data set for training, validation, and benchmarking of artificial intelligence based crack detection algorithms for concrete. SDNET2018 contains over 56,000 images of cracked and non-cracked concrete bridge decks, walls, and pavements. The dataset includes cracks as narrow as 0.06 mm and as wide as 25 mm. The data set also includes images with a variety of obstructions, including shadows, surface roughness, scaling, edges, holes, and background debris. SDNET2018 will be useful for the continued development of concrete crack detection algorithms based on deep convolutional neural networks (DCNNs), which are a subject of continued research in the field of structural health monitoring. The authors present benchmark results for crack detection using SDNET2018 and a crack detection algorithm based on the AlexNet DCNN architecture. SDNET2018 is freely available at https://doi.org/10.15142/T3TD19.