Automated Ground Truth Generation for Learning-Based Crack Detection on Concrete Surfaces
Source abstract
Abstract
This article introduces an automated data-labeling approach for generating crack ground truths (GTs) within concrete images. The main algorithm includes generating first-round GTs, pre-training a deep learning-based model, and generating second-round GTs. On the basis of the generated second-round GTs of the training data, a learning-based crack detection model can be trained in a self-supervised manner. The pre-trained deep learning-based model is effective for crack detection after it is re-trained using the second-round GTs. The main contribution of this study is the proposal of an automated GT generation process for training a crack detection model at the pixel level. Experimental results show that the second-round GTs are similar to manually marked labels. Accordingly, the cost of implementing learning-based methods is reduced significantly because data labeling by humans is not necessitated.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Concrete Corrosion and Durability · Geophysical Methods and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, National United University, Miaoli 360301, Taiwan
Funding
Ministry of Science and Technology, Taiwan
References (43)
Show source-provided references
1. Image-based concrete crack detection in tunnels using deep fully convolutional networks10.1016/j.conbuildmat.2019.117367 ↗
2. Infrared thermography for detecting defects in concrete structures10.3846/jcem.2018.6186 ↗
3. Detection of crack propagation in concrete with embedded ultrasonic sensors10.1016/j.engfracmech.2015.07.058 ↗
4. Cho, S., Park, S., Cha, G., and Oh, T. (2018). Development of image processing for crack detection on concrete structures through terrestrial laser scanning associated with the octree structure. Appl. Sci., 8.10.3390/app8122373 ↗
5. Automatic concrete cracks detection and mapping of terrestrial laser scan data10.1016/j.nrjag.2013.12.002 ↗
6. Adaptive wavelet neural network for terrestrial laser scanner-based crack detection10.1016/j.autcon.2018.06.017 ↗
7. Detection of surface crack in concrete using measurement technique with laser displacement sensor10.1109/TIM.2016.2541358 ↗
8. Application of computer vision to crack detection of concrete structure
9. Xu, H., Tian, Y., Lin, S., and Wang, S. (2013, January 23–25). Research of image segmentation algorithm applied to concrete bridge cracks. Proceedings of the 2013 IEEE Third International Conference on Information Science and Technology (ICIST), Yangzhou, China.10.1109/ICIST.2013.6747851 ↗
10. An automatic approach for accurate edge detection of concrete crack utilizing 2D geometric features of crack10.1007/s11265-013-0813-8 ↗
11. Concrete crack detection by multiple sequential image filtering10.1111/j.1467-8667.2011.00716.x ↗
12. Prasanna, P., Dana, K., Gucunski, N., and Basily, B. (2012, January 12–15). Computer-vision based crack detection and analysis. Proceedings of the Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems, San Diego, CA, USA.10.1117/12.915384 ↗
13. Deep learning-based crack damage detection using convolutional neural networks10.1111/mice.12263 ↗
14. NB-CNN: Deep learning-based crack detection using convolutional neural network and Naïve Bayes data fusion10.1109/TIE.2017.2764844 ↗
15. Kim, B., and Cho, S. (2018). Automated vision-based detection of cracks on concrete surfaces using a deep learning technique. Sensors, 18.10.3390/s18103452 ↗
16. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
17. Autonomous concrete crack detection using deep fully convolutional neural network10.1016/j.autcon.2018.11.028 ↗
18. Simonyan, K., and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv.
19. Islam, M.M., and Kim, J.M. (2019). Vision-based autonomous crack detection of concrete structures using a fully convolutional encoder-decoder network. Sensors, 19.10.3390/s19194251 ↗
20. Zhang, J., Lu, C., Wang, J., Wang, L., and Yue, X.G. (2019). Concrete cracks detection based on FCN with dilated convolution. Appl. Sci., 9.10.3390/app9132686 ↗
21. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
22. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
23. Deepcrack: Learning hierarchical convolutional features for crack detection10.1109/TIP.2018.2878966 ↗
24. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
25. Computer vision-based concrete crack detection using U-net fully convolutional networks10.1016/j.autcon.2019.04.005 ↗
26. APLCNet: Automatic Pixel-Level Crack Detection Network Based on Instance Segmentation10.1109/ACCESS.2020.3033661 ↗
27. Automatic crack detection and measurement of concrete structure using convolutional encoder-decoder network10.1109/ACCESS.2020.3011106 ↗
28. Zou, Y., Zhang, Z., Zhang, H., Li, C.L., Bian, X., Huang, J.B., and Pfister, T. (2020). Pseudoseg: Designing pseudo labels for semantic segmentation. arXiv.
29. Self-supervised structure learning for crack detection based on cycle-consistent generative adversarial networks10.1061/(ASCE)CP.1943-5487.0000883 ↗
30. Mendeley Data (2021, July 30). Concrete Crack Images for Classification. Available online: https://data.mendeley.com/datasets/5y9wdsg2zt/2.
31. Interactive foreground extraction using iterated graph cuts
32. Boykov, Y.Y., and Jolly, M.P. (2001, January 7–14). Interactive graph cuts for optimal boundary & region segmentation of objects in ND images. Proceedings of the Eighth IEEE International Conference on Computer Vision, Vancouver, BC, Canada.
33. Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement10.1023/B:VLSI.0000028532.53893.82 ↗
34. Novel image enhancement technique using CLAHE and wavelet transforms
35. Histogram modified local contrast enhancement for mammogram images10.1016/j.asoc.2011.05.003 ↗
36. Zimmermann, H.J. (2011). Fuzzy Set Theory and Its Applications, Springer. [4th ed.].
37. CrackTree: Automatic crack detection from pavement images10.1016/j.patrec.2011.11.004 ↗
38. Oliveira, H., and Correia, P.L. (2014, January 27–30). CrackIT—An image processing toolbox for crack detection and characterization. Proceedings of the 2014 IEEE International Conference on Image Processing, Paris, France.10.1109/ICIP.2014.7025160 ↗
39. Automatic road crack detection using random structured forests10.1109/TITS.2016.2552248 ↗
40. DeepCrack: A deep hierarchical feature learning architecture for crack segmentation10.1016/j.neucom.2019.01.036 ↗
41. Image-based crack detection using crack width transform (CWT) algorithm10.1109/ACCESS.2018.2875889 ↗
42. Automatic pixel-level pavement crack detection using information of multi-scale neighborhoods10.1109/ACCESS.2018.2829347 ↗
43. A threshold selection method from gray-level histograms10.1109/TSMC.1979.4310076 ↗