Highway Pavement Crack Detection Using Image Processing

Deepa Choudhury

Independent Researcher

India

Abstract

Pavement crack detection is a critical task in highway maintenance for ensuring safety and longevity. Traditional manual inspection methods are labor-intensive, time-consuming, and prone to human error. This paper explores the use of image processing techniques for automated crack detection on highway pavements, employing digital image acquisition and analysis methods based on edge detection and morphological operations. A comparative study of different algorithms including Canny edge detection, Otsu thresholding, and morphological filtering is presented. The experimental results demonstrate that image processing-based approaches can effectively identify cracks with high accuracy and reliability. Statistical analysis validates the detection performance, establishing the feasibility of automated systems for practical highway infrastructure monitoring using technology available till 2019.

Keywords

Pavement Crack Detection, Image Processing, Edge Detection, Morphological Operations, Highway Maintenance, Automated Inspection

REFERENCES

  Al-amri, S. S., Kalyankar, N. V., & Khamitkar, S. D. (2010)          
Image segmentation for damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering 32:361–78. arxiv.org+15maxapress.com+15researchgate.net+15

  Zhang, Y., & Zhou, H. (2012)  
Automatic pavement crack detection and classification using Radon transform. Journal of Information and Computational Science, 9, 5241–??. maxapress.com

  Zhang, A., Li, Q. J., Wang, K. C. P., & Qiu, S. (2013)      
Matched filtering algorithm for pavement cracking detection. Transportation Research Record: Journal of the Transportation Research Board, 2367, 30–.? researchgate.net+14maxapress.com+14ascelibrary.org+14

  Xu, W., Tang, Z. M., Xu, D., & Wu, G. X. (2015)
Integrating multi-features fusion and gestalt principles for pavement crack detection. Journal of Computer‑Aided Design & Computer Graphics, 27(1), 147–156. maxapress.com

  Song, H., Wang, W., Wang, F., Wu, L., & Wang, Z. (2015)          
Pavement crack detection by ridge detection on fractional calculus and dual-thresholds. International Journal of Multimedia and Ubiquitous Engineering, 10(4), 19–30. frontiersin.org+15gvpress.com+15researchgate.net+15

  Wang, X., & Hu, Z. (2017)      
Grid-based pavement crack analysis using deep learning. Proceedings of ICTIS, 917–924. researchgate.net+4maxapress.com+4arxiv.org+4

  Fan, Z., Wu, Y., Lu, J., & Li, W. (2018)
Automatic pavement crack detection based on structured prediction with CNN. arXiv:1802.02208. arxiv.org

  Yang, F., Zhang, L., Yu, S., Prokhorov, D., Mei, X., & Ling, H. (2019)      
Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection. arXiv:1901.06340. arxiv.org  

  Fan, R., Bocus, M. J., Zhu, Y., Jiao, J., Wang, L., Ma, F., Cheng, S., & Liu, M. (2019)        
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding. arXiv:1904.08582. frontiersin.org+14arxiv.org+14maxapress.com+14

  Liu, W., Huang, Y., Li, Y., & Chen, Q. (2019)    
FPCNet: Fast Pavement Crack Detection Network Based on Encoder-Decoder Architecture. arXiv:1907.02248. researchgate.net+3arxiv.org+3arxiv.org+3

  Yusof, N. M. et al. (2019)        
Deep convolution neural network for crack detection on asphalt pavement. Journal of Physics: Conference Series, 1349:012020. maxapress.com