Pavement Distress Detection Using Three-Dimension Ground Penetrating Radar and Deep Learning
Source abstract
Abstract
Three-dimensional ground penetrating radar (3D GPR) is a non-destructive examination technology for pavement distress detection, for which its horizontal plane images provide a unique perspective for the task. However, a 3D GPR collects thousands of horizontal plane images per kilometer of the investigated pavement. The existing detection methods using GPR images are time-consuming and risky for subjective judgment. To solve the problem, this study used deep learning methods and 3D GPR horizontal plane images to detect pavement structural distress, including cracks, repairs, voids, poor interlayer bonding, and mixture segregation. In this study, two deep learning methods, called CP-YOLOX and SViT, were used to achieve the aim. A dataset for anomalous waveform localization (3688 images) was first created by pre-processing 3D-GPR horizontal plane images. A CP-YOLOX model was then trained to localize anomalous waveforms. Five SViT models with different numbers of encoders were adopted to perform the classification of anomalous waveforms using the localization results from the CP-YOLOX model. The numerical experiment results showed that 3D GPR horizontal plane images have the potential to be an assistant for pavement structural distress detection. The CP-YOLOX model achieved 87.71% precision, 80.64% mAP, and 33.57 sheets/s detection speed in locating anomalous waveforms. The optimal SViT achieved 63.63%, 68.12%, and 75.57% classification accuracies for the 5-category, 4-category, and 3-category datasets, respectively. The proposed models outperformed other deep learning methods on distress detection using 3D GPR horizontal plane images. In the future, more radar images should be collected to improve the accuracy of SViT.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geophysical Methods and Applications · Infrastructure Maintenance and Monitoring · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Civil Engineering and Architecture, East China Jiaotong University, Nanchang 330013, China
School of Transportation and Logistics, East China Jiaotong University, Nanchang 330013, China
Funding
Natural Science Foundation of Jiangxi Province of China · Science and technology project of Jiangxi Provincial Department of Education · Key R & D projects of Xinjiang Uygur Autonomous Region · Fundamental Research Funds for the Central Universities, CHD
References (42)
Show source-provided references
1. An overview of ground-penetrating radar signal processing techniques for road inspections10.1016/j.sigpro.2016.05.016 ↗
2. Application of ground penetrating radar methods in soil studies: A review10.1016/j.geoderma.2019.02.024 ↗
3. Tong, Z. (2018). Research on Pavement Distress Inspection Based on Deep Learning and Ground Penetrating Radar, Chang’an University.
4. Gradation of limestone-aggregate-based porous asphalt concrete under dynamic crushing test: Composition, fragmentation and stability10.1016/j.conbuildmat.2022.126532 ↗
5. Review of moisture measurements in civil engineering with ground penetrating radar —Applied methods and signal features10.1016/j.conbuildmat.2021.122250 ↗
6. Luo, C.X. (2018). Research on the Application of Road Nondestructive Testing Technology Based on Three-Dimensional Ground Penetrating Radar, South China University of Technology.
7. Artificial Neural Networks and Machine Learning techniques applied to Ground Penetrating Radar: A review10.1016/j.aci.2018.10.001 ↗
8. Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning10.1109/JSTARS.2014.2332872 ↗
9. Zhou, H., Feng, X., Zhang, Y., Nilot, E., Zhang, M., Dong, Z., and Qi, J. (2018, January 18–21). Combination of Support Vector Machine and H-Alpha Decomposition for Subsurface Target Classification of GPR. Proceedings of the 17th International Conference on Ground Penetrating Radar (GPR), Rapperswil, Switzerland.10.1109/ICGPR.2018.8441522 ↗
10. BlindNet backdoor: Attack on deep neural network using blind watermark10.1007/s11042-021-11135-0 ↗
11. MedicalGuard: U-Net Model Robust against Adversarially Perturbed Images
12. Data Correction For Enhancing Classification Accuracy By Unknown Deep Neural Network Classifiers
13. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
14. Deep learning10.1038/nature14539 ↗
15. Vaswani, A., Shazeer, N., and Parmar, N. (2017, January 4–9). Attention is all you need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
16. Dosovitskiy, A., Beyer, L., and Kolesnikov, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
17. Advances of deep learning applications in ground-penetrating radar: A survey10.1016/j.conbuildmat.2020.120371 ↗
18. Detection and localization of rebar in concrete by deep learning using ground penetrating radar10.1016/j.autcon.2020.103279 ↗
19. Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm10.1016/j.conbuildmat.2020.121949 ↗
20. Liu, Z., Wu, W., Gu, X., Li, S., Wang, L., and Zhang, T. (2021). Application of Combining YOLO Models and 3D GPR Images in Road Detection and Maintenance. Remote Sens., 13.10.3390/rs13061081 ↗
21. Recognition and Measurement of Pavement Disasters Based on Convolutional Neural Networks
22. Automatic Identification of Pavement Objects and Cracks Using the Convolutional Auto-encoder
23. Pavement Distress Detection Based on Faster R-CNN and Morphological Operations
24. Subgrade distresses recognition based on convolutional neural network
25. Recognition, location, measurement, and 3D reconstruction of concealed cracks using convolutional neural networks10.1016/j.conbuildmat.2017.04.097 ↗
26. Autonomous pavement distress detection using ground penetrating radar and region-based deep learning10.1016/j.measurement.2020.108077 ↗
27. Pavement-distress detection using ground-penetrating radar and network in networks10.1016/j.conbuildmat.2019.117352 ↗
28. Long, Z.J. (2018). Reverse-Time Migration Applied to Ground Penetrating Rader and Intelligent Recognition of Subsurface Targets, Xiamen University.
29. GPR B-SCAN Image Hyperbola Detection Method Based on Deep Learning
30. Triplanar Imaging of 3-D GPR Data for Deep-Learning-Based Underground Object Detection10.1109/JSTARS.2019.2953505 ↗
31. Cognitive GPR for Subsurface Object Detection Based on Deep Reinforcement Learning10.1109/JIOT.2021.3059281 ↗
32. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv.
33. Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14–19). CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
34. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
35. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
36. 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.
37. Ge, Z., Liu, S., Li, Z., Yoshie, O., and Sun, J. (2021, January 20–25). Ota: Optimal transport assignment for object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00037 ↗
38. Hendrycks, D., and Gimpel, K. (2016). Gaussian error linear units (gelus). arXiv.
39. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2020, January 7–12). Distance-IoU loss: Faster and better learning for bounding box regression. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.6999 ↗
40. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
41. Li, Y., Huang, H., Xie, Q., Yao, L., and Chen, Q. (2018). Research on a surface defect detection algorithm based on MobileNet-SSD. Appl. Sci., 8.10.3390/app8091678 ↗
42. 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 ↗