Two-Dimensional Image Processing for Automated Detection of Potholes in Asphalt Pavements: A Comparative Analysis of Feature-Based and Machine Learning Approaches

Document Type : Original Article

Authors
Mohammad Ali Tabeei 1
Hossein Alinegadiyan 2
Barat Mojaradi 3
Mahmood Ameri 4
1 Ph.D., Student, School of Civil Engineering, Iran University of Science and Technology (IUST), Tehran, Iran.
2 Ph.D., Student, Faculty of Civil Engineering, Shahrood University of Technology, Semnan, Iran.
3 Associate Professor, Department of Civil Engineering, Iran University of Science and Technology (IUST), Tehran, Iran.
4 Professor, Department of Civil Engineering, Iran University of Science and Technology (IUST), Tehran, Iran.
10.22034/road.2025.549738.2440
Abstract
Accurate and timely detection of pavement distresses plays a vital role in maintaining the safety and durability of asphalt pavements. Traditional inspection methods, such as visual surveys, suffer from limitations including human error, high cost, and lack of repeatability. In this study, two distinct approaches—feature-based image processing and machine learning—were employed and compared to automatically detect potholes in asphalt pavements from two-dimensional images. A dataset consisting of pothole and non-pothole images was collected, preprocessed, and used for feature extraction. Subsequently, several classification algorithms, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, and Random Forest, were trained and evaluated. Model evaluation results indicated that the linear-kernel SVM achieved superior performance, with an accuracy exceeding 97% in distinguishing pothole images from intact surfaces. Despite its computational simplicity, the proposed approach demonstrated high accuracy and satisfactory efficiency compared with traditional methods, under controlled lighting (overcast conditions) and a fixed imaging angle. This method can serve as a practical and cost-effective alternative to visual inspection in pavement maintenance management.
Keywords
Pavement distress detection
Image processing
Feature extraction
Machine learning
-Ahmad, C. F., Al-Sayegh, A. T., Cheema, A., Qayyum, W., Ehtisham, R., Saghir, S., & Ahmad, A. (2024). Classification of different sizes of potholes based on surface area using convolutional neural network. Discover Applied Sciences, 6, 207.
-Álvarez-García, J., Villavicencio, G., Altimiras, F., Crawford, B., Soto, R., Minatogawa, V., Franco, M. M. V.,Martínez-Muñoz, D., & Martí, J. V. (2022). Machine learning techniques applied to construction: A hybrid bibliometric analysis of advances and future directions. Automation in Construction, 140, 104532.
-Al-Sabaeei, A. M., Souliman, M. I., & Jagadeesh, A. (2024). Smartphone applications for pavement condition monitoring: A review. Construction and Building Materials, 423, 134207.
-Aparna, Bhatia, Y., Rai, R., Gupta, V., & Aggarwal, N. (2019). Convolutional neural networks based pothole detection using thermal imaging. Journal of King Saud University – Computer and Information Sciences.
-Becker, Y. V. F., Siqueira, H. L., Matsubara, E. T., Gonçalves, W. N., & Marcato Jr., J. (2019). Asphalt pothole detection in UAV images using convolutional neural networks. IGARSS 2019 – IEEE International Geoscience and Remote Sensing Symposium,  5236–5239.
-Bradski, G. (2000). The OpenCV library. Dr. Dobb’s Journal of Software Tools.
-Chawla, K., Sharma, T., Mishra, M. K., & Mehta, D. (2025). Detecting potholes using machine learning and transfer learning models: Transforming road safety. Communications in Computer and Information Science, 1956.
-Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 1, 886–893.
-Fan, R., Ozgunalp, U., Hosking, B., Liu, M., & Pitas, I. (2019). Pothole detection based on disparity transformation and road surface modeling. IEEE Transactions on Image Processing, 28(12), 6712–6725.
-Fan, R., Wang, H., Wang, Y., Liu, M., & Pitas, I. (2021). Graph attention layer evolves semantic segmentation for road pothole detection: A benchmark and algorithms. IEEE Transactions on Image Processing, 30, 8144–8154.
-Fan, R., et al. (2021). Rethinking road surface 3-D reconstruction and pothole detection: From perspective transformation to disparity map segmentation. IEEE Transactions on Cybernetics, 52(12), 13119–13131.
-Fox, A., Kumar, B. V. K. V., Chen, J., & Bai, F. (2017). Multi-lane pothole detection from crowdsourced undersampled vehicle sensor data. IEEE Transactions on Mobile Computing, 16(12), 3417–3430.
 -Georgopoulos, A., Loizos, A., & Flouda, A. (1995). Digital image processing as a tool for pavement distress evaluation. ISPRS Journal of Photogrammetry and Remote Sensing, 50(1), 23–33.
-Gonzalez, R. C., & Woods, R. E. (2018). Digital image processing (4th ed.). Pearson Education.
-Hadjidemetriou, G. M., & Christodoulou, S. E. (2013). Patch defects detection for pavement assessment using smartphones and support vector machines. Journal of Computing in Civil Engineering, 27(6), 664–670.
-Hoang, N.-D. (2018). 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, 7419058.
-Joy, S., Haripriya, P., & Shukla, S. (2025). Novel pothole detection system using YOLOv8 algorithm. Proceedings of the 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI).
-Koch, C., Georgieva, K., Kasireddy, V., Akinci, B., & Fieguth, P. (2015). A review on computer vision-based defect detection and condition assessment of concrete and asphalt civil infrastructure. Advanced Engineering Informatics, 29(3), 196–210.
-Ling, M., Shi, Q., Zhao, X., Chen, W., Wei, W., Xiao, K., Yang, Z., Zhang, H., Li, S., Lu, C., & Zeng, Y. (2024). Nighttime pothole detection: A benchmark. Electronics, 13(19), 3790.
-Lydon, D., Taylor, S. E., Lydon, M., & Early, J. (2020). A review of vision-based methods for pothole detection and road profile analysis. Civil Engineering Research in Ireland
(CERI 2020).
-Lv, Z., Hao, Z., Zhu, Y., & Lu, C. (2025). A review on automated detection and identification algorithms for highway pavement distress. Applied Sciences, 15(11), 6112.
-Ma, N., Fan, J., Wang, W., Wu, J., Jiang, Y., Xie, L., & Fan, R. (2022). Computer vision for road imaging and pothole detection: A state-of-the-art review of systems and algorithms. Transportation Safety and Environment, 4(3), tdac026.
-Martins, W. D., Osório, F. S., & Bruno, D. R. (2025). Real-time deep learning-based pothole detection on low-cost embedded devices for ADAS. Proceedings of the Brazilian Conference on Robotics (CROS).
-Misra, M., Sharma, R., & Tiwari, S. (2024). An optimized deep belief network-based pothole detection model for asphalt road. International Journal of Intelligent Decision Technologies, 18(4), 761–776.
-Ochoa-Ruiz, G., Angulo-Murillo, A. A., Ochoa-Zezzatti, A., Aguilar-Lobo, L. M., Vega-Fernández, J. A., & Natraj, S. (2020). An asphalt damage dataset and detection system based on RetinaNet for road conditions assessment. Applied Sciences, 10(21), 7546.
-Ozoglu, F., & Gökgöz, T. (2023). Detection of road potholes by applying convolutional neural network method based on road vibration data. Sensors, 23(22), 9023.
-Pawar, S., Admuthe, S., Shah, M., Kulkarni, S., & Thengadi, R. (2016). Pothole detection and warning system using IBM Bluemix platform. International Research Journal of Engineering and Technology, 3(5), 1991–1994.
-Peraka, N. S. P., & Biligiri, K. P. (2020). Pavement asset management systems and technologies: A review. Automation in Construction, 119, 103336.
-Phan, T. M., Kim, J., Kim, H., & Park, D. (2024). Automated repair of asphalt pavement cracks and potholes utilizing 3D printing and LiDAR scanning. Construction and Building Materials, 450, 138748.
-Ranyal, E., Sadhu, A., & Jain, K. (2022). Road condition monitoring using smart sensing and artificial intelligence: A review. Sensors, 22(8), 3044.
-Ren, M., Zhang, X., Chen, X., Zhou, B., & Feng, Z. (2023). YOLOv5s-M: A deep learning network model for road pavement damage detection from urban street-view imagery. International Journal of Applied Earth Observation and Geoinformation, 121, 103335.
-Rizelioğlu, M. (2025). An extensive bibliometric analysis of pavement deterioration detection using sensors and machine learning: Trends, innovations, and future directions. Alexandria Engineering Journal, 112,169–191.
-Rufei, L., Jiben, Y., Hongwei, R., Bori, C., & Chenhao, C. (2022). Research on a pavement pothole extraction method based on vehicle-borne continuous laser scanning point cloud. Measurement Science and Technology, 33(9), 095012.
-Safyari, Y., Mahdianpari, M., & Shiri, H. (2024). A review of vision-based pothole detection methods using computer vision and machine learning. Sensors, 24(17), 5652.
-Sathya, R., & Saleena, B. (2022). A framework for designing unsupervised pothole detection by integrating feature extraction using deep recurrent neural network. Wireless Personal Communications, 126(2), 1275–1292.
-Schnebele, E., Tanyu, B. F., Cervone, G., & Waters, N. (2015). Review of remote sensing methodologies for pavement management and assessment. European Transport Research Review, 7, 17.
-Senbagavalli, M., Mahapatra, S., Ahamed, K. H., & Ruchita, L. (2025). Revolutionizing road safety: An innovative approach to pothole detection and prevention using XAI and deep learning. Proceedings of the 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL).
-Silva, L. A., Sanchez, H., San Blas, D., García, D. P., Mendes, A. S., & Villarubia González, G. (2020). An architectural multi-agent system for a pavement monitoring system with pothole recognition in UAV images. Sensors, 20(17), 4906.
-Tamagusko, T., Correia, M. G., & Ferreira, A. (2024). Machine learning applications in road pavement management: A review, challenges and future directions. Infrastructures, 9(12), 213.
-Tsai, Y.-C., & Chatterjee, A. (2017). Pothole detection and classification using 3D technology and watershed method. Journal of Computing in Civil Engineering, 31(4), 04017020.
-Vinodhini, K. A., & Sidhaarth, K. R. A. (2023). Pothole detection in bituminous road using CNN with transfer learning. Measurement: Sensors, 25, 100940.
-Wang, P., Hu, Y., Dai, Y., & Tian, M. (2017). Asphalt pavement pothole detection and segmentation based on wavelet energy field. Mathematical Problems in Engineering, 2017, 1604130.
-Ye, W., Jiang, W., Tong, Z., Yuan, D., & Xiao, J. (2019). Convolutional neural network for pothole detection in asphalt pavement. Road Materials and Pavement Design, 20(7),
1683–1703.
-Zhang, L., Shen, J., & Zhu, B. (2022).A review of the research and application of deep learning-based computer vision in structural damage detection. Earthquake Engineering and Engineering Vibration, 21, 1–18.