Small-sample data-driven lightweight convolutional neural network for asphalt pavement defect identification
Source abstract
Abstract
Automatic detection technology provides a reliable method for civil engineering distress detection. However, to overcome limitations of computational resources and the significant cost of image acquisition, this study proposes a simplified network parameter-based pavement crack classification network (PCCNet) to achieve efficient and robust crack classification. Firstly, a lightweight classification model is developed based on a shuffle unit and inverted residual architecture, designed to deliver high-performance pavement crack classification with limited computing resources. Secondly, a novel training method is proposed to accurately identify pavement defects on small-sample pavement images datasets. Additionally, the interpretability of neural network in pavement defect detection is enhanced by visualizing training process. The results demonstrate that the model achieved a classification accuracy of 97.89 % on the augmented pavement image dataset and a classification accuracy of over 83 % on multi-source asphalt pavement images. Furthermore, visualizing intermediate features further enhanced the high-precision recognition ability of the lightweight model.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (63)
Show source-provided references
1. Image-based retrieval of concrete crack properties for bridge inspection10.1016/j.autcon.2013.06.011 ↗
2. Tran.Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network10.1016/j.autcon.2018.07.008 ↗
3. I.G. Heggie, Vickers, Piers. Commercial Management and Financing of Roads. Washington, DC, USA: World Bank, 1998.10.1596/0-8213-4237-1 ↗
4. Road Funds and Road Maintenance: An Asian Perspective. Asian Develop. Bank, Mandaluyong, Philippines, 2003.
5. Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection10.1016/j.conbuildmat.2017.09.110 ↗
6. Image-based pothole detection system for ITS service and road management system10.1155/2015/968361 ↗
7. Measuring rutting dimension and lateral position using 3D line scanning laser and inertial measuring unit10.1016/j.autcon.2019.103056 ↗
8. C. Jiang. A. Crack Detection and diagnosis methodology for automated pavement condition evaluation, Georgia Institute of Technology, (2016).
9. Image based techniques for crack detection, classification and quantification in asphalt pavement: a review10.1007/s11831-016-9194-z ↗
10. Depth detection of subsurface voids in concrete-filled steel tubular (CFST) structure using percussion and decision tree10.1016/j.measurement.2020.107869 ↗
11. Y. Shi, L. Cui, Z. Qi et al.Automatic road crack detection using random structured forests.IEEE Transactions on Intelligent Transportation Systems,2016:17 (12),pp.3434-3445.https://10.1109/TITS.2016.2552248.10.1109/TITS.2016.2552248 ↗
12. N.-D. Hoang.An artificial intelligence method for asphalt pavement pothole detection using least squares support vector machine and neural network with steerable filter-based feature extraction.Advances in Civil Engineering,2018:2018 https://10.1155/2018/7419058.10.1155/2018/7419058 ↗
13. A novel hybrid approach for crack detection
14. Densely connected deep neural network considering connectivity of pixels for automatic crack detection10.1016/j.autcon.2019.103018 ↗
15. Automatic pixel-level crack detection and measurement using fully convolutional network10.1111/mice.12412 ↗
16. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete10.1016/j.conbuildmat.2018.08.011 ↗
17. Novel approach to pavement cracking detection based on neural network10.3141/1764-13 ↗
18. Image processing–based classification of asphalt pavement cracks using support vector machine optimized by artificial bee colony10.1061/(ASCE)CP.1943-5487.0000781 ↗
19. A cost effective solution for pavement crack inspection using cameras and deep neural networks10.1016/j.conbuildmat.2020.119397 ↗
20. J. Deng, W. Dong, R. Socher, ImageNet: a large-scale hierarchical image database, In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009, pp.248-255, https://10.1109/CVPR.2009.5206848 .10.1109/CVPR.2009.5206848 ↗
21. T.-Y. Lin, M. Maire, S. Belongie, Microsoft COCO: Common Objects in Context, Computer Vision – ECCV 2014. (eds D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars)(2014), pp.740-755, https://link.springer.com/chapter/10.1007/978-3-319-10602-1_48.10.1007/978-3-319-10602-1_48 ↗
22. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
23. Going deeper with convolutions
24. Very deep convolutional networks for large-scale image recognition
25. K. He, X. Zhang, S. Ren, Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2016), pp.770-778, https://10.1109/CVPR.2016.90 .10.1109/CVPR.2016.90 ↗
26. G. Huang, Z. Liu and K.Q. Weinberger.Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision Pattern Recognition,2016,pp.2261-2269.https://doi.org/10.48550/arXiv.1608.06993.10.1109/CVPR.2017.243 ↗
27. Automatic classification of asphalt pavement cracks using a novel integrated generative adversarial networks and improved VGG model10.1016/j.engstruct.2022.115406 ↗
28. Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks10.1016/j.autcon.2022.104674 ↗
29. Pavement crack detection with hybrid-window attentive vision transformers
30. Road crack detection using deep convolutional neural network
31. Deep learning-based crack damage detection using convolutional neural networks10.1111/mice.12263 ↗
32. L. Pauly, H. Peel, S. Luo et al.Deeper networks for pavement crack detection, In: ISARC 2017 - Proceedings of the 34th International Symposium on Automation and Robotics in Construction. (2017), pp.479-485, https://doi.org/10.22260/ISARC2017/0066.10.22260/ISARC2017/0066 ↗
33. Y. Xu, Y. Bao, J. Chen et al.Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images.Structural Health Monitoring,2018:18 (3),pp.653-674.https://10.1177/1475921718764873.10.1177/1475921718764873 ↗
34. Automatic recognition of pavement cracks from combined GPR B-scan and C-scan images using multiscale feature fusion deep neural networks10.1016/j.autcon.2022.104698 ↗
35. Automatic pixel-level detection of vertical cracks in asphalt pavement based on GPR investigation and improved mask R-CNN10.1016/j.autcon.2022.104689 ↗
36. Convolutional networks and transformers for intelligent road tunnel investigations10.1016/j.compstruc.2022.106918 ↗
37. Y.-J. Cha, W. Choi, G. Suh et al.Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types.Computer-Aided Civil and Infrastructure Engineering,2018:33 (9),pp.731-747.https://10.1111/mice.12334.10.1111/mice.12334 ↗
38. Increasing the robustness of material-specific deep learning models for crack detection across different materials10.1016/j.engstruct.2019.110157 ↗
39. A survey on transfer learning10.1109/TKDE.2009.191 ↗
40. Deep transfer learning for image-based structural damage recognition10.1111/mice.12363 ↗
41. Real-time detection of cracks in tiled sidewalks using YOLO-based method applied to unmanned aerial vehicle (UAV) images10.1016/j.autcon.2023.104745 ↗
42. Deep learning for intelligent identification of concrete wind-erosion damage10.1016/j.autcon.2022.104427 ↗
43. Recognition of concrete microcrack images under fluorescent excitation based on attention mechanism deep recurrent neural networks
44. A hybrid deep learning pavement crack semantic segmentation10.1016/j.engappai.2023.106142 ↗
45. Fully convolutional networks for semantic segmentation10.1109/TPAMI.2016.2572683 ↗
46. Screening of glaucoma disease from retinal vessel images using semantic segmentation10.1016/j.compeleceng.2021.107036 ↗
47. Dynamic adaptive residual network for liver CT image segmentation10.1016/j.compeleceng.2021.107024 ↗
48. Encoder-decoder with atrous separable convolution for semantic image segmentation
49. CNN-based network with multi-scale context feature and attention mechanism for automatic pavement crack segmentation10.1016/j.autcon.2024.105482 ↗
50. Lightweight convolutional neural network driven by small data for asphalt pavement crack segmentation10.1016/j.autcon.2023.105214 ↗
51. Automatic road-marking detection and measurement from laser-scanning 3D profile data10.1016/j.autcon.2019.102957 ↗
52. Intelligent recognition of defects in high-speed railway slab track with limited dataset
53. MobileCrack: object classification in asphalt pavements using an adaptive lightweight deep learning10.1061/JPEODX.0000245 ↗
54. JTG5210-2018. Highway performance assessment standards. Ministry of Transport of the People’s Republic of China, Beijing, China: 2018.
55. How to get pavement distress detection ready for deep learning? A systematic approach
56. Feature pyramid and hierarchical boosting network for pavement crack detection10.1109/TITS.2019.2910595 ↗
57. S. Xie and Z. Tu.Holistically-Nested Edge Detection, 2015 IEEE International Conference on Computer Vision (ICCV). (2015), pp.1395-1403, https://10.1109/ICCV.2015.164.10.1109/ICCV.2015.164 ↗
58. Adaptive local tone mapping based on retinex for high dynamic range images
59. X. Zhang, X. Zhou, M. Lin et al.ShuffleNet: an extremely efficient convolutional neural network for mobile devices.arXiv e-prints,2017:arXiv:1707.01083,pp.6848-6856.https://doi.org/10.48550/arXiv.1707.01083.10.1109/CVPR.2018.00716 ↗
60. Nearest neighbor pattern classification10.1109/TIT.1967.1053964 ↗
61. Support-vector networks10.1007/BF00994018 ↗
62. Visualizing data using t-SNE
63. A.G. Sorguç.Performance Comparison of pretrained convolutional neural networks on crack detection in buildings, In: Proceedings of the 35th International Symposium on Automation and Robotics in Construction (ISARC). (2018), pp.693-700, https://10.22260/ISARC2018/0094.