Accurate Classification of Tunnel Lining Cracks Using Lightweight ShuffleNetV2-1.0-SE Model with DCGAN-Based Data Augmentation and Transfer Learning
Source abstract
Abstract
Cracks in tunnel lining surfaces directly threaten structural integrity; therefore, regular inspection of cracks is essential. Lightweight convolutional neural networks (LCNNs) have recently offered a promising alternative to conventional manual inspection. However, the effectiveness of LCNNs is still adversely affected by the lack of sufficient crack images, which limits the potential detection performance. In this paper, transfer learning was used to optimize deep convolutional generative adversarial networks (DCGANs) for crack image synthesis to significantly improve the accuracy of LCNNs. In addition, an improved LCNN model named ShuffleNetV2-1.0-SE was proposed, incorporating the squeeze–excitation (SE) attention mechanism into ShuffleNetV2-1.0 and realizing highly accurate classification results while maintaining lightness. The results show that the DCGAN-based data enhancement method can significantly improve the classification accuracy of ShuffleNetV2-1.0-SE for tunnel lining cracks. ShuffleNetV2-1.0-SE achieves an accuracy of 98.14% on the enhanced dataset, which is superior to multiple advanced LCNN models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Geotechnical Engineering and Underground Structures · Concrete Corrosion and Durability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Civil Engineering, Chongqing Jiaotong University, No. 66, Xuefu Road, Nan’an District, Chongqing 400074, China
State Key Laboratory of Mountain Bridge and Tunnel Engineering, No. 66, Xuefu Road, Nan’an District, Chongqing 400074, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Chongqing City of China
References (40)
Show source-provided references
1. Deep learning based image recognition for crack and leakage defects of metro shield tunnel10.1016/j.tust.2018.04.002 ↗
2. A fast detection method via region-based fully convolutional neural networks for shield tunnel lining defects10.1111/mice.12367 ↗
3. Image-based concrete crack detection in tunnels using deep fully convolutional networks10.1016/j.conbuildmat.2019.117367 ↗
4. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure10.1016/j.aei.2015.01.008 ↗
5. A systematic review of convolutional neural network-based structural condition assessment techniques10.1016/j.engstruct.2020.111347 ↗
6. A framework of structural damage detection for civil structures using a combined multi-scale convolutional neural network and echo state network10.1007/s00366-021-01584-4 ↗
7. Artificial intelligence image recognition method based on convolutional neural network algorithm10.1109/ACCESS.2020.3006097 ↗
8. Pavement crack detection based on transformer network10.1016/j.autcon.2022.104646 ↗
9. Automated assessment of cracks on concrete surfaces using adaptive digital image processing10.12989/sss.2014.14.4.719 ↗
10. A threshold selection method from gray-level histograms10.1109/TSMC.1979.4310076 ↗
11. ImageNet classification with deep convolutional neural networks
12. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
13. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
14. 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 ↗
15. DeepCrack: A deep hierarchical feature learning architecture for crack segmentation10.1016/j.neucom.2019.01.036 ↗
16. Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features10.1155/2020/6412562 ↗
17. Zhang, L., Yang, F., Zhang, Y.D., and Zhu, Y.J. (2016, January 25–28). Road Crack Detection Using Deep Convolutional Neural Network. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.10.1109/ICIP.2016.7533052 ↗
18. Deep transfer learning for image-based structural damage recognition10.1111/mice.12363 ↗
19. Structural damage-causing concrete cracking detection based on a deep-learning method10.1016/j.conbuildmat.2022.127562 ↗
20. Andrew, G., and Menglong, Z.J.M. (2017). Efficient convolutional neural networks for mobile vision applications. arXiv.
21. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–23). Mobilenetv2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
22. Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
23. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–23). Shufflenet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
24. Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018, January 8–14). Shufflenet v2: Practical Guidelines for Efficient CNN Architecture Design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_8 ↗
25. Efficientnet: Rethinking model scaling for convolutional neural networks
26. Automatic bridge crack detection using boundary refinement based on real-time segmentation network10.1002/stc.2991 ↗
27. MobileCrack: Object Classification in Asphalt Pavements Using an Adaptive Lightweight Deep Learning10.1061/JPEODX.0000245 ↗
28. The classification and localization of crack using lightweight convolutional neural network with CBAM10.1016/j.engstruct.2022.115291 ↗
29. A Generative adversarial learning strategy for enhanced lightweight crack delineation networks10.1016/j.aei.2022.101575 ↗
30. Pavement crack detection algorithm based on generative adversarial network and convolutional neural network under small samples10.1016/j.measurement.2022.111219 ↗
31. A deeper generative adversarial network for grooved cement concrete pavement crack detection10.1016/j.engappai.2022.105808 ↗
32. Virtual generation of pavement crack images based on improved deep convolutional generative adversarial network10.1016/j.engappai.2021.104376 ↗
33. Establishment and evaluation of conditional GAN-based image dataset for semantic segmentation of structural cracks10.1016/j.engstruct.2023.116058 ↗
34. Automatic tunnel lining crack detection via deep learning with generative adversarial network-based data augmentation10.1016/j.undsp.2022.07.003 ↗
35. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv.
36. Generative adversarial networks10.1145/3422622 ↗
37. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
38. Özgenel, Ç.F., and Sorguç, A.G. (2018, January 20–25). Performance Comparison of Pretrained Convolutional Neural Networks on Crack Detection in Buildings. Proceedings of the International Symposium on Automation and Robotics in Construction, Berlin, Germany.10.22260/ISARC2018/0094 ↗
39. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
40. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7–13). Delving Deep into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.123 ↗