Benchmarking Yolov8n, Yolov11n, and Yolov12n for Smart Road Pothole Detection
DOI:
https://doi.org/10.29408/edumatic.v10i2.35908Keywords:
computer vision, deep learning, object detection, road pothole detection, yoloAbstract
Road potholes present a considerable threat to traffic safety, highlighting the need for precise and efficient automatic detection in road-monitoring systems. Although recent research has utilized various YOLO-based models for detecting potholes, there is a scarcity of comparative evaluations of the newest lightweight YOLO architectures under uniform experimental conditions. This study seeks to evaluate the performance of YOLOv8n, YOLOv11n, and YOLOv12n in the context of smart road pothole detection. A quantitative experimental approach was applied using the road pole dataset. Each model underwent training using identical preprocessing, training configurations, and evaluation protocols. Performance metrics included Precision, Recall, mAP50, mAP50–95, inference time, and computational efficiency. The experimental findings indicate that YOLOv11n delivered the best overall results, achieving 90.02% precision, 90.25% mAP50, and 48.35% mAP50–95, along with the quickest inference time of 3.13 ms and the highest end-to-end processing speed. Although YOLOv12n recorded the highest recall at 86.11%, its overall detection performance and computational efficiency were inferior to those of YOLOv11n. These results suggest that YOLOv11n offers the most balanced compromise between detection accuracy and computational efficiency, providing empirical support for choosing lightweight object detection models for intelligent road-monitoring systems.
References
Abdelwahed, S. H., Sharobim, B. K., Wasfey, B., & Said, L. A. (2025). Advancements in real time road damage detection : a comprehensive survey of methodologies and datasets. Journal of Real-Time Image Processing, 22(4), 1–13. https://doi.org/10.1007/s11554-025-01683-1
Ettalibi, A., Elouadi, A., & Mansour, A. (2024). AI and Computer Vision-based Real-time Quality Control : A Review of Industrial Applications. Procedia Computer Science, 231(2023), 212–220. https://doi.org/10.1016/j.procs.2023.12.195
Giordani, E., Arcioni, L., Gil-martín, M., Foresti, G. L., & Marini, M. R. (2026). Real-world road damage dataset with potholes , cracks , and maintenance holes. Scientific Reports, 16(15318), 1–22. https://doi.org/10.1038/s41598-026-46679-4
Gorro, K., Ranolo, E., Roble, L., & Santillan, R. N. (2024). Road Pothole Detection Using YOLOv8 with Image Augmentation. 12(4), 417–426. https://doi.org/10.18178/joig.12.4.417-426
Jakubec, M., Lieskovska, E., Bučko, B., & Zábovská, K. (2023). Comparison of CNN-based models for pothole detection in real-world adverse conditions: Overview and evaluation. Applied Sciences, 13(9), 5810. https://doi.org/10.3390/app13095810
Lee, J., & Hwang, K. (2022). YOLO with adaptive frame control for real time object detection applications. Multimedia Tools and Applications, 36375–36396. https://doi.org/10.1007/s11042-021-11480-0
Li, B., Wang, K., Liu, Z., Huang, M., & Zhang, S. (2025). DMC-YOLOv11 : an improved pavement damage detection model based on YOLOv11. Systems Science & Control Engineering An Open Access Journal, 2583. https://doi.org/10.1080/21642583.2025.2579987
Li, X., Zhang, N., Pan, Y., Lv, Y., Xu, X., & Wang, Z. (2026). A lightweight and attention-enhanced framework for robust pavement defect detection. Engineering Applications of Artificial Intelligence, 165(PB), 113545. https://doi.org/10.1016/j.engappai.2025.113545
Li, Y., Yin, C., Lei, Y., Zhang, J., & Yan, Y. (2024). RDD-YOLO: road damage detection algorithm based on improved you only look once version 8. Applied Sciences, 14(8), 3360. https://doi.org/10.3390/app14083360
Lin, J., Wang, P., Ruan, Y., & Sun, Y. (2026). YOLO11-WLBS: an efficient model for pavement defect detection. Scientific Reports, 16(5284), 1–16. https://doi.org/10.1038/s41598-026-35743-8 1
Lin, Z., & Pan, W. (2026). YOLO-ROC: a high-precision and ultra-lightweight model for real-time road damage detection. Measurement Science and Technology, 37(3), 035405. https://doi.org/10.48550/arXiv.2507.23225
Ranyal, E., Sadhu, A., & Jain, K. (2022). Road condition monitoring using smart sensing and artificial intelligence: A review. Sensors, 22(8), 3044. https://doi.org/10.3390/s22083044
Rasee, M. A., Ung, L. L., Tan, G. J., Tan, C. W., Buking, R., Yahya, N., & Ismail, H. (2025). AI-driven Vision-based Pothole Detection for Improved Road Safety. 33(3), 1535–1562. https://doi.org/10.47836/pjst.33.3.20
Reddy, S. S., Janarthanan, M., Khan, I. U., & Amrutha, K. (2026). A Deep Learning Framework for Real-Time Pothole Detection from Combined Drone Imagery and Custom Dataset Using Enhanced YOLOv8 and Custom Feature Extraction. Mathematics, 1–32. https://doi.org/10.3390/math14050898
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
Sahputra, A., & Muhammad, A. H. (2026). Identity-Aware Lightweight MobileNetV2 with Distillation and Optuna for Face Spoofing Detection. Edumatic : Jurnal Pendidikan Informatika, 10(2), 320–329. https://doi.org/10.29408/edumatic.v10i2.34863
Setiaji, P., Triyanto, W. A., & Nurhaliza, M. (2025). Real-Time Traffic Density and Anomaly Monitoring Using YOLOv8, OpenCV and Pattern Recognition for Smart City Applications in Demak. Jurnal Teknik Informatika (JUTIF), 6(4), 1769–1782. https://doi.org/10.52436/1.jutif.2025.6.4.4867
Tian, Y., Ye, Q., & Doermann, D. (2026). Yolov12: Attention-centric real-time object detectors. Advances in neural information processing systems, 38, 78433-78457. https://doi.org/10.52202/085713-2627
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/su162410964
Zeng, J., & Zhong, H. (2024). YOLOv8 PD : an improved road damage detection algorithm based on YOLOv8n model. Scientific Reports, 14(12052), 1–14. https://doi.org/10.1038/s41598-024-62933-z
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ilham Arif Febriansyah, Eko Darmanto, Pratomo Setiaji
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All articles in this journal are the sole responsibility of the authors. Edumatic: Jurnal Pendidikan Informatika can be accessed free of charge, in accordance with the Creative Commons license used.
This work is licensed under a Lisensi a Creative Commons Attribution-ShareAlike 4.0 International License.
