Deep Learning-Based Road Damage Detection and Classification Using Computer Vision
DOI:
https://doi.org/10.51903/bxvt9389Keywords:
Computer Vision, Damage Detection, YOLO, Object Detection, Road DamageAbstract
Road damage detection is essential for supporting efficient road infrastructure inspection, yet conventional visual assessment is time-consuming and may produce inconsistent results when dealing with diverse pavement distress patterns. This study aims to comparatively evaluate YOLOv8s, YOLOv10s, YOLOv11s, and an optimized YOLOv11s configuration for detecting and classifying longitudinal cracks, transverse cracks, alligator cracks, and potholes using the RDD2022 dataset. A quantitative experimental approach was employed using 55,007 annotated damage instances, with all models trained under consistent experimental conditions and evaluated using precision, recall, F1-score, mAP@50, mAP@50–95, and inference time. The results show a progressive improvement across the evaluated configurations, with optimized YOLOv11s achieving the highest performance at 83.4% precision, 80.9% recall, 82.1% F1-score, 88.4% mAP@50, and 59.6% mAP@50–95, with an inference time of 8.7 ms. Class-specific analysis showed that longitudinal cracks achieved the highest F1-score of 85.5%, whereas alligator cracks recorded the lowest at 79.7%, with the largest classification confusion occurring between potholes and alligator cracks. The novelty of this study lies in the systematic cross-generation comparison of YOLOv8s, YOLOv10s, YOLOv11s, and optimized YOLOv11s under consistent experimental conditions while jointly examining overall performance, class-specific behavior, classification errors, and inference efficiency. The study contributes a detailed characterization of model performance across heterogeneous road-damage categories and provides quantitative evidence for selecting an effective YOLO configuration for automated road infrastructure inspection.
Downloads
References
[1] R. Romarez, R. Sembiring, and U. Hanifah, “Aesthetic Misinformation in Local Digital Journalism: A Case Study on Editorial Bypass in Public Service News Production,” Int. J. Graph. Des., vol. 2, no. 1, pp. 01–19, May 2024, doi: 10.51903/rgb91w74.
[2] M. Syafril, S. Arief, and J. D. Pangaribuan, “Application of Digital Twin Technology for Real-Time Monitoring and Predictive Maintenance of Coastal Bridges under Climate Change Scenarios,” J. Rekayasa Sipil dan Arsit., vol. 1, no. 2, pp. 39–51, Mar. 2025, doi: 10.51903/5fkqb467.
[3] Z. Zhong, L. Yun, F. Cheng, Z. Chen, and C. Zhang, “Light-YOLO: A Lightweight and Efficient YOLO-Based Deep Learning Model for Mango Detection,” Agriculture, vol. 14, no. 1, p. 140, 2024, doi: 10.3390/agriculture14010140.
[4] A. Ashraf, A. Sophian, and A. A. Bawono, “Crack Detection, Classification, and Segmentation on Road Pavement Material Using Multi-Scale Feature Aggregation and Transformer-Based Attention Mechanisms,” Constr. Mater., vol. 4, no. 4, pp. 655–675, 2024, doi: 10.3390/constrmater4040036.
[5] Y. Xu, Y. Xia, Q. Zhao, K. Yang, and Q. Li, “A Road Crack Segmentation Method Based on Transformer and Multi-Scale Feature Fusion,” Electronics, vol. 13, no. 12, p. 2257, 2024, doi: 10.3390/electronics13122257.
[6] Y. Zhu, L. Fan, Q. Li, and J. Chang, “Multi-Scale Discrete Cosine Transform Network for Building Change Detection in Very-High-Resolution Remote Sensing Images,” Remote Sens., vol. 15, no. 21, p. 5243, 2023, doi: 10.3390/rs15215243.
[7] S. Zhou et al., “A Lightweight Drone Detection Method Integrated into a Linear Attention Mechanism Based on Improved YOLOv11,” Remote Sens., vol. 17, no. 4, p. 705, 2025, doi: 10.3390/rs17040705.
[8] F. Samadzadegan, F. Dadrass Javan, F. Ashtari Mahini, M. Gholamshahi, and F. Nex, “Automatic Road Pavement Distress Recognition Using Deep Learning Networks from Unmanned Aerial Imagery,” Drones, vol. 8, no. 6, p. 244, 2024, doi: 10.3390/drones8060244.
[9] S. Alqaydi, W. Zeiada, A. El Wakil, A. J. Alnaqbi, and A. Azam, “A Comprehensive Review of Smartphone and Other Device-Based Techniques for Road Surface Monitoring,” Eng, vol. 5, no. 4, pp. 3397–3426, 2024, doi: 10.3390/eng5040177.
[10] X. Dong, Y. Liu, and J. Dai, “Concrete Surface Crack Detection Algorithm Based on Improved YOLOv8,” Sensors, vol. 24, no. 16, p. 5252, 2024, doi: 10.3390/s24165252.
[11] M. Kardoš, I. Sačkov, J. Tomaštík, I. Basista, Ł. Borowski, and M. Ferenčík, “Elevation Accuracy of Forest Road Maps Derived from Aerial Imaging, Airborne Laser Scanning and Mobile Laser Scanning Data,” Forests, vol. 15, no. 5, p. 840, 2024, doi: 10.3390/f15050840.
[12] Y. Chen, L. Li, H. Cheng, and C. He, “Pavement Crack Identification in UAV Images Based on Joint Context Information,” Appl. Sci., vol. 16, no. 7, p. 3371, 2026, doi: 10.3390/app16073371.
[13] J. Cha, S. Lee, and H.-K. Kim, “Deep Learning-Based Detection and Assessment of Road Damage Caused by Disaster with Satellite Imagery,” Appl. Sci., vol. 15, no. 14, p. 7669, 2025, doi: 10.3390/app15147669.
[14] P. Wang et al., “Research on Automatic Pavement Crack Recognition Based on the Mask R-CNN Model,” Coatings, vol. 13, no. 2, p. 430, 2023, doi: 10.3390/coatings13020430.
[15] A. A. Sami, S. Sakib, K. Deb, and I. H. Sarker, “Improved YOLOv5-Based Real-Time Road Pavement Damage Detection in Road Infrastructure Management,” Algorithms, vol. 16, no. 9, p. 452, 2023, doi: 10.3390/a16090452.
[16] Y. Fan, Q. Li, Y. Chen, Z. Yao, Y. Sun, and W. Zhang, “DAH-YOLO: An Accurate and Efficient Model for Crack Detection in Complex Scenarios,” Appl. Sci., vol. 16, no. 2, p. 900, 2026, doi: 10.3390/app16020900.
[17] H. Yang, Y. Song, Y. Liang, E. Tang, and D. Cao, “SDC-YOLOv8: An Improved Algorithm for Road Defect Detection Through Attention-Enhanced Feature Learning and Adaptive Feature Reconstruction,” Sensors, vol. 26, no. 2, p. 609, 2026, doi: 10.3390/s26020609.
[18] T. Nkosi and N. Mokoena, “AI-Driven Digital Twin for Urban Transport Infrastructure Network Operations Optimization,” Civ. Eng. Sci. Technol., vol. 2, no. 1, pp. 69–89, Mar. 2026, doi: 10.51903/zxxtac97.
[19] A.-P. Botezatu, A. Burlacu, and C. Orhei, “A Review of Deep Learning Advancements in Road Analysis for Autonomous Driving,” Appl. Sci., vol. 14, no. 11, p. 4705, 2024, doi: 10.3390/app14114705.
[20] Y. Li, C. Yin, Y. Lei, J. Zhang, and Y. Yan, “RDD-YOLO: Road Damage Detection Algorithm Based on Improved You Only Look Once Version 8,” Appl. Sci., vol. 14, no. 8, p. 3360, 2024, doi: 10.3390/app14083360.
[21] H. Yoon, H.-K. Kim, and S. Kim, “PPDD: Egocentric Crack Segmentation in the Port Pavement with Deep Learning-Based Methods,” Appl. Sci., vol. 15, no. 10, p. 5446, 2025, doi: 10.3390/app15105446.
[22] Z. Tian, X. Shao, Y. Bai, Q. Zhang, Z. Wang, and Y. Ji, “A Symmetry-Aware Hierarchical Graph-Mamba Network for Spatio-Temporal Road Damage Detection,” Symmetry (Basel)., vol. 17, no. 12, p. 2173, 2025, doi: 10.3390/sym17122173.
[23] F. Yang, J. Huo, Z. Cheng, H. Chen, and Y. Shi, “An Improved Mask R-CNN Micro-Crack Detection Model for the Surface of Metal Structural Parts,” Sensors, vol. 24, no. 1, p. 62, 2024, doi: 10.3390/s24010062.
[24] Y. Jiang, H. Yan, Y. Zhang, K. Wu, R. Liu, and C. Lin, “RDD-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection,” Sensors, vol. 23, no. 19, p. 8241, 2023, doi: 10.3390/s23198241.
[25] X. Wang, H. Gao, Z. Jia, and Z. Li, “BL-YOLOv8: An Improved Road Defect Detection Model Based on YOLOv8,” Sensors, vol. 23, no. 20, p. 8361, 2023, doi: 10.3390/s23208361.
[26] J. Ren, H. Zhang, and M. Yue, “YOLOv8-WD: Deep Learning-Based Detection of Defects in Automotive Brake Joint Laser Welds,” Appl. Sci., vol. 15, no. 3, p. 1184, 2025, doi: 10.3390/app15031184.
[27] T. Ye, Y. Pang, Y. Li, E. Liang, Y. Wang, and T. Zhou, “LSTM-CA-YOLOv11: A Road Sign Detection Model Integrating LSTM Temporal Modeling and Multi-Scale Attention Mechanism,” Appl. Sci., vol. 16, no. 1, p. 116, 2026, doi: 10.3390/app16010116.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Calvin Arsento, Nadia Weningrum (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
