YOLOv8 for Road DamageRecognition: Deep Learning-Based Segmentation and Detection System

Abstract

Road surface detection is critical for improving traffic safety and reducing road maintenance costs. Because traditional methods are time-consuming and costly, deep learning-based image processing techniques offer an important alternative in this field. This study aims to develop a model that automates the detection and segmentation of road surface defects such as potholes, manhole covers, and culverts using deep-learning-based image processing techniques. In this study, a dataset previously used in the literature was preferred. It was observed that object detection was performed using a dataset from the literature. In this study, both object detection and object segmentation were performed using different parameters. To prove the success of object segmentation, both object detection and segmentation were performed using the YOLOv8 algorithm, which has previously obtained successful results. AdamW optimization and Auto Batch parameters were selected for this study. With these parameters, object detection was first performed with the YOLOv8s model, which is one of the variances of the YOLOv8 algorithm with the most successful results in the literature, and a successful 92.8% mAP@50 performance value was obtained according to the sources in the literature. In this study, the YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l variance models of the YOLOv8 algorithm were used with the preferred parameters, and segmentation was performed. In object segmentation, a map@50 performance value of 90.9% in all classes and 99.1% in culverts was obtained using the YOLOv8l model. A map@50 performance value of 89.1% for pothole segmentation and 88% for manhole cover segmentation was obtained using the YOLOv8s model. The results of the analyses showed consistency in precision and recall values. These findings contribute significantly to improving road safety, reducing maintenance costs, and supporting sustainable urban infrastructure. Future research could explore integrating multiple data sources and adapt these models to more complex road conditions.

Keywords

• YOLOv8
• pothole detection
• road damage segmentation
• image preprocessing
• surface cracks

References

1. Agrawal, R., Chhadva, Y., Addagarla, S., and Chaudhari, S. (2021). Road surface classification and subsequent pothole detection using deep learning. In 2021 2nd International Conference for Emerging TechnologY (INCET) (pp. 1-6). IEEE. https://doi.org/10.1109/INCET 51464.2021.9456126. google scholar
2. Ahmed, K. R. (2021). Smart pothole detection using deep learning based on dilated convolution. Sensors, 21(24), 8406. https://doi.org/ 10.3390/s21248406. google scholar
3. Alhussan, A., Khafaga, D. S., El-KenawY, E. S. M., Ibrahim, A., Eid, M. M., and Abdelhamid, A. A. (2022). Pothole and plain road classification using adaptive mutation dipper throated optimization and transfer learning for self driving cars. IEEE Access, 10, 84188-84211. https://doi.org/10.1109/ACCESS.2022.3196670. google scholar
4. Al Haqi, N., and HidaYat, F. (2022). Classification of road damage using supervised learning to assist visual assessment of road damage. In 2022 International Conference on Information TechnologY SYstems and Innovation (ICITSI). IEEE. https://doi.org/10.1109/icitsi 56531.2022.9971082. google scholar
5. Arjapure, S., and Kalbande, D. (2021). Deep learning model for pothole detection and area computation. In 2021 International Conference on Communication information and Computing TechnologY (ICCICT) (pp. 1-6). IEEE. https://doi.org/10.1109/ICCICT50803.2021. 9510153. google scholar
6. Atluri, S. and Bandi, S. (2022). Segmentation of potholes from road images. IEEE Xplore. doi:10.1109/ICACCS54159.2022.9716468. google scholar
7. Babulal, K. S., and Das, A. (2022). Deep learning-based object detection: An investigation. G. S. Tomar, N. Chaki, L. C. Jain, R. Garg, and T. K. Gandhi (Eds.), Multimedia Processing, Communication and Computing Applications (pp. 669-681). Springer. https://doi.org/10. 1007/978-981-19-5037-7_50. google scholar
8. Baek, J. W., & Chung, K. (2020). Pothole classification model based on edge detection in road image. Applied Sciences, 10(19), 6662. https://doi.org/10.3390/app10196662. google scholar

9. Bello, S. A., Yu, S.; Wang, C. (2020). Review: Deep learning on 3D point clouds. Remote Sensing, 12(11), 1729. https://doi.org/10.3390/ rs12111729. google scholar
10. Bhatt, U., Mani, S., Xi, E., &Kolter, J. Z. (2017). Intelligent pothole detection and road condition assessment. arXiv preprint arXiv:1710.02595. https://arxiv.org/abs/1710.02595. google scholar
11. Bhavana, N., Kodabagi, M. M., Kumar, B. M., AjaY, P., Muthukumaran, N., &Ahilan, A. (2024). POT-YOLO: Real-time road potholes detection using edge segmentation based YOLOv8 network. IEEE Sensors. https://doi.org/10.1109/JSEN.2024.3354780. google scholar
12. Chen, H., Yao, M., &Gu, Q. (2020). Pothole detection using location-aware convolutional neural networks. Int. J. Machine Learning CYbern. 11, 899-911. https://doi.org/l0.1007/s13042-020-01078-7. google scholar
13. Chen, Y., Wang, S., Lin, L., Cui, Z., &Zong, Y. (2024). Computer vision and deep learning transforming image recognition and beYond. International Journal of Computer Science and Information Technology. 15(1), 153-187. google scholar
14. Chunmian, L., Tian, D., Duan, X., Zhou, J., Zhao, D., & Cao, D. (2022). DA-RDD: Toward domain adaptive road damage detection across different countries. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/tits.2022.3221067. google scholar
15. DhoundiYal, P., Sharma, V., & Vats, S. (2023). Deep learning framework for automated pothole detection. In 2023 International Conference on Sustainable Communication Networks and Application (ICSCNA) (pp. 1382-1387). IEEE. https://doi.org/10.1109/ICSCNA58489. 2023.10370471. google scholar
16. Diwan, T., Anirudh, G. S., &Tembhurne, J. V. (2022). Object detection using YOLO: Challenges, architectural successors, datasets and applications. Multimedia Tools and Applications, 82, 9243-9275. https://doi.org/10.1007/s11042-022-13702-5. google scholar
17. Fan, J., Bocus, M. J., Hosking, B., Wu, R., Liu, Y., VitYazev, S., & Fan, R. (2021). Multi-scale feature fusion: Learning better semantic segmentation for road pothole detection. arXiv. https://arxiv.org/abs/2112.13082. google scholar
18. Fan, R., Wang, H., Bocus, M. J., & Liu, M. (2020). We improve road pothole detection: From attention aggregation with adversarial domain adaptation. arXiv. https://arxiv.org/abs/2008.06840. google scholar
19. Fan, R., Wang, H., Wang, Y., Liu, M., & Pitas, I. (2021). The graph attention laYer evolves semantic segmentation for road pothole detection: A benchmark and algorithms. arXiv. https://arxiv.org/abs/2109.02711. google scholar
20. Ghanem, R., and Khaled, B. (2023). The robustness of the YOLO object detection algorithm in terms of detecting objects in noisY environment. Journal of Scientific Reports-A. https://doi.org/10.59313/jsr-a.1257361. google scholar
21. Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann Publishers. google scholar
22. Hoang, N. D., HuYnh, T. C., and Tran, V. D. (2021). Computer vision-based patched and unpatched pothoLe cLassification using machine Learning approach optimized bY forensic-based investigation metaheuristic. Complexity, https://doi.org/10.1155/2021/3511375. google scholar
23. Jakubec, M., Lieskovskâ, E., Bucko, B., &Zâbovskâ, K. (2023). Comparison of CNN-based modeLs for pothoLe detection in real-world adverse conditions: Overview and evaluation. Applied Sciences, 13(10), 6139. https://doi.org/10.3390/app13106139. google scholar
24. Kang, C. H., & Kim, S. Y. (2023). Real-time object detection and segmentation technologY: An analYsis of the YOLO algorithm. JMST Advances, 5, 69-76. https://doi.org/10.1007/s42791-023-00049-7. google scholar
25. Khan, M., Raza, M. A., Abbas, G., Othmen, S., Yousef, A., &Jumani, T. A. (2024). Pothole detection for autonomous vehicles using deep learning: A robust and efficient solution. Frontiers in Built Environment, 9, 1323792. https://doi.org/10.3389/fbuil.2023.1323792. google scholar
26. Khare, O., Gandhi, S., Rahalkar, A., & Mane, S. (2023). YOLOv8-based visual detection of road hazards: Potholes, sewer covers, and manholes. In 2023 IEEE Pune Section International Conference (PuneCon) (pp. 1-6). IEEE. https://doi.org/10.1109/PuneCon58716. 2023.10149050. google scholar
27. Kilic, E., & Ozturk, S. (2019). A subclass supported convolutional neural network for object detection and localization in remote-sensing images. International journal of remote sensing, 40(11), 4193-4212. google scholar
28. Kim, T., &RYu, S. K. (2014a). A guideline for pothole classification. International Journal of Engineering and Technology, 4(10), 618-622. google scholar
29. Kim, T., and RYu, S. K. (2014b). Review and analYsis of pothole detection methods. Journal of Emerging Trends in Computing and Information Sciences, 5(8), 603-608. google scholar
30. Kim, Y. M., Kim, Y. G., Son, S. Y., Lim, S. Y., Choi, B. Y., and Choi, D. H. (2022). Review of recent automated pothole-detection methods. Applied Sciences, 12(11), 5320. https://doi.org/10.3390/app12115320. google scholar
31. Kumar, A. C., Gaur, N., ChakravartY, S., Alsharif, M. H., Uthansakul, P., &Uthansakul, M. (2023). AnalYsis of spectrum sensing using deep learning algorithms: CNNs and RNNs. Ain Shams Engineering Journal, 14(8), 102164. https://doi.org/10.1016/j.asej.2023.102164. google scholar
32. Li, C., Li, X., Chen, M., & Sun, X. (2023). Deep learning and image recognition. In 2023 IEEE 6th International Conference on Electronic Information and Communication TechnologY (ICEICT) (pp. 557-562). IEEE. https://doi.org/10.1109/ICEICT59239.2023.10373631. google scholar
33. Liao, K. (2022). Road damage intelligent detection with deep learning techniques. In 2022 IEEE 5th International Conference on Infor-mation SYstems and Computer Aided Education (ICISCAE). IEEE. https://doi.org/10.1109/ICISCAE55891.2022.9913326. google scholar
34. 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(4), 403-439. https://doi.org/10.1093/tse/tdac019. google scholar
35. Nawale, S., Khut, D., Dave, D., SawhneY, G., Aggrawal, P., &Devadakar, K. (2023). PotholeGuard: A pothole detection approach bY point cloud semantic segmentation. arXiv. https://arxiv.org/abs/2311.02641 google scholar
36. Omar, M., & Kumar, P. (2024). PD-ITS: Pothole detection using YOLO variants for intelligent transport sYstem. SN Computer Science, 5, 552. https://doi.org/10.1007/s42979-024-02887-1 google scholar
37. Paramarthalingam, A., Sivaraman, J., Theerthagiri, P., VijaYakumar, B., &Baskaran, V. (2024). A deep learning model to assist visuallY impaired in pothole detection using computer vision. Decision Analytics Journal, 12.https://doi.org/10.1016/j.dajour.2024.100507 google scholar
38. Ragab, K. (2021). Smart pothole detection using deep learning based on dilated convolution. Sensors, 21(24), 8406. https://doi.org/10. 3390/s21248406 google scholar
39. Rastogi, R., Kumar, U., KashYap, A., Jindal, S., and Pahwa, S. (2020). A comparative evaluation of the deep learning algorithms for pothole detection. In 2020 IEEE 17th India Council International Conference (INDICON). IEEE. doi:10.1109/INDICON49873.2020.9342267 google scholar
40. ReddY, J. R., Raghava Deekshith, R., Venu Gopal, B., & Rajwanth, C. (2024). Real time pothole detection using YOLO algorithm. Available at SSRN 5088842. https://doi.org/10.2139/ssrn.5088842 google scholar
41. Rehana, K. C., &RemYa, G. (2022). Road damage detection and classification using YOLOv5. In 2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT). IEEE. https://doi.org/10.1109/icicict54557.2022.9917763 google scholar
42. 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. https://doi.org/10.3390/s24175652 google scholar
43. Saha, P., ArYa, D., Kumar, A., Maeda, H., & Sekimoto, Y. (2022). Road rutting detection using deep learning on images. In 2022 IEEE International Conference on Big Data (Big Data). IEEE. https://doi.org/10.1109/bigdata55660.2022.10020458 google scholar
44. Saisree, C., and Umaran, U. (2023). Pothole detection using a deep learning classification method. Procedia Computer Science, 218, 2143-2152. https://doi.org/10.1016/j.procs.2023.01.193 google scholar
45. SaranYa, E., Nivetha, R., Abirami, S., MohaideenArsath, M., &Dharaneesh, S. (2024). Revolutionizing road maintenance: YOLO-based pothole detection system. In 2024 10th International Conference on Advanced Computing and Communication SYstems (ICACCS) (Vol. 1, pp. 1991-1997). IEEE. https://doi.org/10.1109/ICACCS59260.2024.10475429 google scholar
46. Tang, J., Li, Y., & Wang, S. (2023). A comparison of road damage detection based on YOLOv8. ResearchGate. https://www.researchgate.net/publication/376021160_A_Comparison_of_Road_Damage_Detection_Based_on_YOLOv8 google scholar
47. Thiruppathiraj, S., Kumar, U. and Bagke, S. (2020). Automatic pothole classification and segmentation using android smartphone sensors and camera images with machine learning techniques. In 2020 IEEE Region 10 Conference (TENCON) (pp. 1386-1391). IEEE. https:// doi.org/10.1109/TENCON50793.2020.9293756 google scholar
48. Tsai, Y. C., & Chatterjee, A. (2018). Pothole detection and classification using 3D technologY and watershed method. Journal of Computing in Civil Engineering, 32(2), 04017078. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000726 google scholar
49. Ultralytics. (2025). YOLOv8: State-of-the-art computer vision model. Retrieved from https://Yolov8.com/ google scholar
50. Varona, B., Monteserin, A., &Teyseyre, A. (2020). A deep-learning approach for automatic road surface monitoring and pothole detection. Personal and Ubiquitous Computing, 24, 519-534. https://doi.org/l0.1007/s00779-019-01234-z google scholar
51. Yu, X., &Salari, E. (2011). Sidewalk pothole detection and severity measurements using laser imaging. In 2011 IEEE International Confer-ence on Electro/Information TechnologY (pp. 1-5). IEEE. https://doi.org/10.1109/EIT.2011.5978573 google scholar
52. Zanevych, Y., Yovbak, V., Basystiuk, O., Shakhovska, N., Fedushko, S., &Argyroudis, S. (2024). Evaluation of pothole detection performance using deep learning models under low-light conditions. Sustainability. 16(24),10964. https://doi.org/10.3390/su16241 google scholar