Benchmarking YOLOv8 Variants with Transfer Learning for Real-Time Detection and Classification of Road Cracks and Potholes
DOI:
https://doi.org/10.29207/resti.v9i4.6710Keywords:
classification, deep learning, road damage detection, transfer learning, YOLOv8Abstract
Road damage, including potholes and cracks, is a significant issue frequently encountered in road infrastructure in many regions. Such conditions accelerate road degradation, increase the risk of traffic accidents, and significantly increase the maintenance and repair costs. Although several deep learning models have been proposed for road damage detection, few studies have systematically compared the performance of lightweight YOLOv8 variants using a consistent dataset. To address this gap, this study proposes a road defect detection and classification model based on the YOLOv8 series, which is enhanced using transfer learning to improve performance and efficiency. The dataset, obtained from Roboflow, comprises 3,846 images categorized into training, validation, and testing sets. Three YOLOv8 variants—YOLOv8n, YOLOv8s, and YOLOv8m—were benchmarked for performance. A performance evaluation was performed using the metrics of precision, recall, and mean Average Precision (mAP). Results show that YOLOv8m achieved the highest precision (99.00%), recall (98.40%), and mAP (99.50%). In the pothole category, precision reached 98.70% and recall 99.30%; in the crack category, precision was 99.30% and recall 97.60%. The findings demonstrate that YOLOv8, particularly the YOLOv8m variant, is highly effective for real-time road damage detection and classification, offering a viable solution for intelligent transportation systems and automated infrastructure monitoring. This research has the potential to revolutionize infrastructure monitoring by enabling scalable, real-time, and cost-effective assessments of road conditions. It minimizes reliance on manual inspections, reduces human errors, and contributes to the development of intelligent transportation systems and predictive maintenance strategies.
Downloads
References
Menteri PUPR, “Peraturan Menteri Pekerjaan Umum Dan Perumahan Rakyat Republik Indonesia Nomor 5 Tahun 2023 Tentang Persyaratan Teknis Jalan Dan Perencanaan Teknis Jalan,” 2023. [Online]. Available: https://binamarga.pu.go.id/index.php/peraturan/dokumen/peraturan-menteri-pekerjaan-umum-dan-perumahan-rakyat-nomor-5-tahun-2023-tentang-persyaratan-teknis-jalan-dan-perencanaan-teknis-jalan
N. Kaiser and C. K. Barstow, “Rural Transportation Infrastructure in Low- and Middle-Income Countries: A Review of Impacts, Implications, and Interventions,” Sustainability, vol. 14, no. 4, p. 2149, May 2022, doi: 10.3390/su14042149.
Menteri PUPR, “Anggaran yang dialokasikan untuk tahap pertama pada jalan daerah,” 2024, [Online]. Available: https://binamarga.pu.go.id/index.php/berita/anggarkan-rp146-triliun-kementerian-pupr-mulai-perbaikan-jalan-daerah-bulan-juli
T. B. Sembiring, B. P. Ndruru, S. T. Sitepu, Z. S. Siregar, and W. W. Tarigan, “Jalan Rusak Sebagai Ajang Pungutan Liar,” vol. 4, no. 1, 2024, doi: 10.56799/peshum.v4i1.6718.
S. Sulartopo, S. Kholifah, D. Danang, and J. T. Santoso, “Transformasi Proyek Melalui Keajaiban Kecerdasan Buatan: Mengeksplorasi Potensi AI Dalam Project Management,” J. Publ. Ilmu Manaj., vol. 2, no. 2, pp. 363–392, Mar. 2023, doi: 10.55606/jupiman.v2i2.2477.
M. Azimi, A. Eslamlou, and G. Pekcan, “Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review,” Sensors, vol. 20, no. 10, p. 2778, May 2020, doi: 10.3390/s20102778.
M. Jakubec, E. Lieskovská, B. Bučko, and K. Zábovská, “Comparison of CNN-Based Models for Pothole Detection in Real-World Adverse Conditions: Overview and Evaluation,” Appl. Sci., vol. 13, no. 9, 2023, doi: 10.3390/app13095810.
B. Sasmito, B. H. Setiadji, and R. Isnanto, “Deteksi Kerusakan Jalan Menggunakan Pengolahan Citra Deep Learning di Kota Semarang,” TEKNIK, vol. 44, no. 1, pp. 7–14, Jan. 2023, doi: 10.14710/teknik.v44i1.51908.
X. Wang, H. Gao, Z. Jia, and Z. Li, “BL-YOLOv8: An Improved Road Defect Detection Model Based on YOLOv8,” Sensors (Basel)., vol. 23, no. 20, 2023, doi: 10.3390/s23208361.
M. M. Ali, M. Faishol, and K. Anwar, “Deteksi Jalan Berlubang Menggunakan Metode Grey Level Co-Occurrence Matrix Dan Neural Network,” COREAI J. Kecerdasan Buatan, Komputasi dan Teknol. Inf., vol. 3, no. 1, pp. 1–8, Feb. 2022, doi: 10.33650/coreai.v3i1.4088.
M. F. Djulyansyah, G. Fitri Laxmi, and S. Agustian H, “Model Deteksi Jalan Untuk Smart Glasses Menggunakan Algoritma Yolo,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 4, pp. 7963–7970, Jan. 2024, doi: 10.36040/jati.v8i4.10620.
Q. H. Nguyen et al., “Influence of Data Splitting on Performance of Machine Learning Models in Prediction of Shear Strength of Soil,” Math. Probl. Eng., vol. 2021, pp. 1–15, May 2021, doi: 10.1155/2021/4832864.
J. Chappidi and D. M. Sundaram, “Novel Animal Detection System: Cascaded YOLOv8 With Adaptive Preprocessing and Feature Extraction,” IEEE Access, vol. 12, pp. 110575–110587, May 2024, doi: 10.1109/ACCESS.2024.3439230.
G. Parsons, W. Y. Liu, and T. Zahra, “A Novel Wind Turbine Fault Diagnosis Model Based on Pre-Trained Yolov8 Deep Transfer Learning,” Eng. Res. Express, May 2025, doi: 10.1088/2631-8695/adc3ea.
M. Iman, H. R. Arabnia, and K. Rasheed, “A Review of Deep Transfer Learning and Recent Advancements,” Technologies, vol. 11, no. 2, p. 40, May 2023, doi: 10.3390/technologies11020040.
C. Fang et al., “Enhancing Livestock Detection: An Efficient Model Based on YOLOv8,” Appl. Sci., vol. 14, no. 11, p. 4809, May 2024, doi: 10.3390/app14114809.
M. Hussain, “YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision,” May 02, 2024, arXiv. doi: 10.48550/arXiv.2407.02988.
P. Zhao, W. Zhou, and L. Na, “High-precision object detection network for automate pear picking,” Sci. Rep., vol. 14, no. 1, p. 14965, May 2024, doi: 10.1038/s41598-024-65750-6.
N. R. Muntiari, I. C. Nisa, A. Sriekaningih, A. Y. A. Prasetyo, and M. Yusril, “Penerapan Algoritma YOLOv8 Dalam Indentifikasi Wajah secara Real- Time menggunakan CCTV untuk Presensi Siswa,” vol. 4, no. 3, 2024, doi: 10.51454/decode.v4i3.847.
Y. Li and S. Wang, “EGM-YOLOv8: A Lightweight Ship Detection Model with Efficient Feature Fusion and Attention Mechanisms,” J. Mar. Sci. Eng., vol. 13, no. 4, 2025, doi: 10.3390/jmse13040757.
X. Zhu, S. Lyu, X. Wang, and Q. Zhao, “TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios,” in 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), IEEE, May 2021, pp. 2778–2788. doi: 10.1109/ICCVW54120.2021.00312.
M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation, vol. 11, no. 3, p. 52, May 2023, doi: 10.3390/computation11030052.
L. Alzubaidi, O. Al-Shamma, M. A. Fadhel, L. Farhan, J. Zhang, and Y. Duan, “Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model,” Electronics, vol. 9, no. 3, p. 445, May 2020, doi: 10.3390/electronics9030445.
C. F. G. Dos Santos and J. P. Papa, “Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks,” ACM Comput. Surv., vol. 54, no. 10s, pp. 1–25, May 2022, doi: 10.1145/3510413.
A. Sushma Priya and G. Manasi, “A Review and Performance Analysis of Non-Linear Activation Functions in Deep Neural Networks,” Int. Res. J. Mod. Eng. Technol. Sci., vol. 03, no. 03, 2021, doi: 10.1109/ISCID.2009.214.
Y. Li et al., “SOD-YOLO: Small-Object-Detection Algorithm Based on Improved YOLOv8 for UAV Images,” Remote Sens., vol. 16, no. 16, p. 3057, May 2024, doi: 10.3390/rs16163057.
L. Shen, B. Lang, and Z. Song, “Infrared Object Detection Method Based on DBD-YOLOv8,” IEEE Access, vol. 11, pp. 145853–145868, May 2023, doi: 10.1109/ACCESS.2023.3345889.
W. Rao, S. Chen, and D. Li, “Autonomous Aerial Vehicle Object Detection Based on Spatial Perception and Multiscale Semantic and Detail Feature Fusion,” IEEE Access, vol. 13, pp. 42897–42909, May 2025, doi: 10.1109/ACCESS.2025.3547825.
J. Wei, Q. Wang, Z. Li, S. Wang, S. K. Zhou, and S. Cui, “Shallow Feature Matters for Weakly Supervised Object Localization,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, May 2021, pp. 5989–5997. doi: 10.1109/CVPR46437.2021.00593.
M. L. Ali and Z. Zhang, “The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection,” Computers, vol. 13, no. 12, p. 336, May 2024, doi: 10.3390/computers13120336.
R. Padilla, W. L. Passos, T. L. B. Dias, S. L. Netto, and E. A. B. Da Silva, “A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit,” Electronics, vol. 10, no. 3, p. 279, May 2021, doi: 10.3390/electronics10030279.
Roboflow, “Cap DP Dataset and Pre-Trained Model by TS,” 2023, [Online]. Available: https://universe.roboflow.com/ts-25tom/cap-dp/model/1
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;





