Enhancing Pavement Distress Detection Using a Morphological Constraints-Based Data Augmentation Method
Source abstract
Abstract
Pavement distress data in a single section usually presents a long-tailed distribution, with potholes, sealed cracks, and other distresses normally located at the tail. This distribution will seriously affect the performance and robustness of big data-driven deep learning detection models. Conventional data augmentation algorithms only expand the amount of data by image transformation and fail to enlarge the data diversity. Due to such a drawback, this paper proposes a novel two-stage pavement distress image augmentation pattern, in which a mask is generated randomly according to the geometric features of the distress in the first stage; and in the second stage, a distress-free pavement image with the fused mask is transformed into a pavement distress image. Furthermore, two convolutional networks, M-DCGAN and MDTMN, are designed to complete the generation task in two stages separately. In comparison with other generation algorithms, the quality and diversity of the generation results of proposed algorithms are better than other algorithms. In addition, distress detection tests are conducted which indicate that the expanded dataset can raise the IoU from 48.83% to 83.65% at maximum, and the augmented data by the proposed algorithm contributes more to the detection performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Geophysical Methods and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Engineering, Chang’an University, Xi’an 710064, China
School of Computer Science, Xi’an Polytechnic University, Xi’an 710048, China
College of Transportation Engineering, Chang’an University, Xi’an 710064, China
Funding
Key projects of Shaanxi Provincial Department of Science and Technology · Postdoctoral Science Foundation of China · Central Universities Basic Research Special Funds · Natural Science Foundation of Shaanxi Province
References (38)
Show source-provided references
1. Automatic Pixel-level pavement sealed crack detection using Multi-fusion U-Net network10.1016/j.measurement.2023.112475 ↗
2. Pavement distress detection using convolutional neural networks with images captured via UAV10.1016/j.autcon.2021.103991 ↗
3. CurSeg: A pavement crack detector based on a deep hierarchical feature learning segmentation framework10.1049/itr2.12173 ↗
4. Pixel-level pavement crack segmentation with encoder-decoder network10.1016/j.measurement.2021.109914 ↗
5. An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection10.1109/TITS.2021.3084809 ↗
6. Autonomous Crack and Bughole Detection for Concrete Surface Image Based on Deep Learning10.1109/ACCESS.2021.3088292 ↗
7. Faster region convolutional neural network for automated pavement distress detection10.1080/14680629.2019.1614969 ↗
8. Road surface damage detection based on hierarchical architecture using lightweight auto-encoder network10.1016/j.autcon.2021.103833 ↗
9. Image processing-based automatic detection of asphalt pavement rutting using a novel metaheuristic optimized machine learning approach10.1007/s00500-021-06086-5 ↗
10. A cost effective solution for pavement crack inspection using cameras and deep neural networks10.1016/j.conbuildmat.2020.119397 ↗
11. Automated pavement crack detection and segmentation based on two-step convolutional neural network10.1111/mice.12622 ↗
12. Crack Detection and Segmentation Using Deep Learning with 3D Reality Mesh Model for Quantitative Assessment and Integrated Visualization10.1061/(ASCE)CP.1943-5487.0000890 ↗
13. Hu, R., and Singh, A. (2021, January 11–17). Unit: Multimodal multitask learning with a unified transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00147 ↗
14. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France.
15. Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., and Fergus, R. (2013, January 17–19). Regularization of neural networks using dropconnect. Proceedings of the International Conference on Machine Learning, Atlanta, GA, USA.
16. Moreno-Barea, F.J., Strazzera, F., Jerez, J.M., Urda, D., and Franco, L. (2018, January 18–21). Forward Noise Adjustment Scheme for Data Augmentation. Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI), Bangalore, India.10.1109/SSCI.2018.8628917 ↗
17. A survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
18. Regularizing Deep Networks with Semantic Data Augmentation
19. Liu, S., Zhang, J., Chen, Y., Liu, Y., Qin, Z., and Wan, T. (2019, January 12–17). Pixel level data augmentation for semantic image segmentation using generative adversarial networks. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8683590 ↗
20. Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv.
21. Generative adversarial networks10.1145/3422622 ↗
22. Diffusion models beat gans on image synthesis
23. Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
24. Globally and locally consistent image completion10.1145/3072959.3073659 ↗
25. Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.244 ↗
26. Taylor, L., and Nitschke, G. (2018, January 18–21). Improving deep learning with generic data augmentation. Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI), Bangalore, India.10.1109/SSCI.2018.8628742 ↗
27. Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., and Le, Q.V. (2018). Autoaugment: Learning augmentation policies from data. arXiv.10.1109/CVPR.2019.00020 ↗
28. Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2020, January 7–12). Random erasing data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.
29. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
30. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
31. Glenn, J. (2023, March 08). YOLOv5 Release v6.1. Available online: https://github.com/ultralytics/yolov5/releases/tag/v6.1.
32. Gao, Z., Peng, B., Li, T., and Gou, C. (2019, January 14–19). Generative adversarial networks for road crack image segmentation. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.10.1109/IJCNN.2019.8851910 ↗
33. Jackson, P.T., Abarghouei, A.A., Bonner, S., Breckon, T.P., and Obara, B. (2019, January 15–20). Style augmentation: Data augmentation via style randomization. Proceedings of the CVPR Workshops, Long Beach, CA, USA.
34. A novel approach to data augmentation for pavement distress segmentation10.1016/j.compind.2020.103225 ↗
35. Virtual generation of pavement crack images based on improved deep convolutional generative adversarial network10.1016/j.engappai.2021.104376 ↗
36. Brock, A., Donahue, J., and Simonyan, K. (2018). Large scale GAN training for high fidelity natural image synthesis. arXiv.
37. Pixel-level pavement crack detection using enhanced high-resolution semantic network10.1080/10298436.2021.1985491 ↗
38. Visualizing data using t-SNE