Computer vision-based concrete crack detection using U-net fully convolutional networks

By Zhenqing Liu, Yiwen Cao, Yize Wang, Wei Wang. Automation in Construction, 2019

744 citations recorded by the source corpus.

Abstract For the first time, U-Net is adopted to detect the concrete cracks in the present study. Focal loss function is selected as the evaluation function, and the Adam algorithm is applied for optimization. The trained U-Net is able of identifying the crack locations from the input raw images under various conditions (such as illumination, messy background, width of cracks, etc.) with high effectiveness and robustness. In addition, U-Net based concrete crack detection method proposed in the present study is compared with the DCNN-based method, and U-Net is found to be more elegant than DCNN with more robustness, more effectiveness and more accurate detection. Furthermore, by examining the fundamental parameters representing the performance of the method, the present U-Net is found to reach higher accuracy with smaller training set than the previous FCNs.

Subfields: Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/3a151fceb298560d14480f4f77ec0ef2691bc52c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

1. D. Dais
2. Vasilis Sarhosis
3. E. Smyrou
4. İ. Bal

Citations in the corpus

• Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning (2021, methodology): “Another showcase for U-net was presented by Liu et al. [30] for concrete crack detection, where the U-net performed better than the other FCN methods [23,24] while being trained on significantly smaller training sets.”