Research on Automatic Pavement Crack Recognition Based on the Mask R-CNN Model
Source abstract
Abstract
Pavement will inevitably be damaged in the process of use; pavement damage detection and assessment are an important part of maintenance management. In order to prevent road diseases, it is necessary to fix the road cracks and implement automatic road crack inspection and monitoring. In this paper, the automatic identification of road cracks is realized by constructing the Mask R-CNN model. The labeled area can be segmented by pixels and positioned at the original data by integrating the image data used for training and the labeled data into a network model. The effect of the training model can be improved by increasing the number of data sets, the pixel of the fracture image, the background of the fracture, and the marking method of the fracture type. The validity and accuracy of the test results were characterized by RPN bounding-box loss, classification loss, mask loss, and total loss.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Concrete Corrosion and Durability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shandong High-Speed Infrastructure Construction Co., Ltd., Jinan 250014, China
Shandong Provincial Communications Planning and Design Institute Group Co., Ltd., Jinan 250101, China
Shandong High-Speed Group Co., Ltd., Jinan 250014, China
School of Qilu Transportation, Shandong University, Jinan 250002, China
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
Shandong Hi-Speed Jiwei Expressway Co., Ltd., Jinan 250200, China
Funding
Qilu Young Scholars Program of Shandong University · Natural Science Foundation of Shandong Province (CN) · Jinan Research Leader Studio · National Key Research and Development Plan Project
References (23)
Show source-provided references
1. Chemical, rheological properties and microstructure of road asphalt prepared from deoiled asphalt, slurry oil and polymers10.1016/j.conbuildmat.2020.119571 ↗
2. The innovative self-sensing strain sensor for asphalt pavement structure: Substitutability and synergy effects of graphene platelets with carbon nanotubes in epoxy composites10.3389/fmats.2022.824364 ↗
3. Yang, Y. (2014). Research on Pavement Crack Image Segmentation Method Based on Fractal Dimension, Changan University.
4. Pavement image datasets: A new benchmark dataset to classify and densify pavement distresses10.1177/0361198120907283 ↗
5. A real-time crack detection algorithm for pavement based on CNN with multiple feature layers10.1080/14680629.2021.1925578 ↗
6. Automated pavement distress detection using region based convolutional neural networks10.1080/10298436.2020.1833204 ↗
7. Automatic parallel cracking detection algorithm based on 1 mm resolution 3D pavement images
8. Feng, X. (2016). Research on Algorithm of Asphalt Pavement Cracks Detection Based on Range Image, Hubei University of Technology.
9. Prediction method for asphalt pavement crack based on GRNN neural network
10. A novel pavement transverse cracks detection model using WT-CNN and STFT-CNN for smartphone data analysis10.1080/10298436.2021.1945056 ↗
11. Aslan, O.D., Gultepe, E., Ramaji, I.J., and Kermanshachi, S. (2019). International Conference on Smart Infrastructure and Construction 2019 (ICSIC) Driving Data-Informed Decision-Making, ICE Publishing.
12. Piao, W. (2019). Research on Segmentation Algorithm of Pavement Crack in Complex Environment, Zhengzhou University.
13. Lv, J. (2019). Research and Implementation of Pavement Crack Detection Method Based on Deep Learning, Southeast University.
14. Monitoring Asphalt Pavement Aging and Damage Conditions from Low-Altitude UAV Imagery Based on a CNN Approach10.1080/07038992.2020.1870217 ↗
15. Automated asphalt pavement damage rate detection based on optimized GA-CNN10.1016/j.autcon.2022.104180 ↗
16. Premachandra, C., Waruna, H., Premachandra, H., and Parape, C.D. (2013, January 13–16). Image Based Automatic Road Surface Crack Detection for Achieving Smooth Driving on Deformed Roads. Proceedings of the 2013 IEEE International Conference on Systems, Man, and Cybernetics, Manchester, UK.10.1109/SMC.2013.686 ↗
17. Oliveira, H., and Correia, P.L. (2014, January 27–30). Crack-IT an image processing toolbox for crack detection and characterization. Proceedings of the IEEE International Conference on Image Processing 2014, Paris, France.10.1109/ICIP.2014.7025160 ↗
18. Recognition and measurement of pavement disasters based on convolutional neural networks
19. Palevičius, P., Pal, M., Landauskas, M., Orinaitė, U., Timofejeva, I., and Ragulskis, M. (2022). Automatic detection of cracks on concrete surfaces in the presence of shadows. Sensors, 22.10.3390/s22103662 ↗
20. Pal, M., Palevičius, P., Landauskas, M., Orinaitė, U., Timofejeva, I., and Ragulskis, M. (2021). An overview of challenges associated with automatic detection of concrete cracks in the presence of shadows. Appl. Sci., 11.10.3390/app112311396 ↗
21. Life cycle cost analysis and life cycle assessment for road pavement materials and reconstruction technologies10.7250/bjrbe.2020-15.510 ↗
22. Nguyen, N.T.H., Le, T.H., Perry, S., and Nguyen, T.T. (2018, January 6–7). Pavement crack detection using convolutional neural network. Proceedings of the Ninth International Symposium on Information and Communication Technology, Da Nang City, Viet Nam.10.1145/3287921.3287949 ↗
23. Xu, X., Zhao, M., Shi, P., Ren, R., He, X., Wei, X., and Yang, H. (2022). Crack detection and comparison study based on faster R-CNN and mask R-CNN. Sensors, 22.10.3390/s22031215 ↗