The Development of a Lane Identification and Assessment Framework for Maintenance Using AI Technology
Source abstract
Abstract
This study proposes a vision-based framework to support AVs in maintaining stable lane-keeping by assessing the condition of lane markings. Unlike existing infrastructure standards focused on human visibility, this study addresses the need for criteria suited to sensor-based AV environments. Using real driving data from urban expressways in Seoul, a YOLOv5-based lane detection algorithm was developed and enhanced through multi-label annotation and data augmentation. The model achieved a mean average precision (mAP) of 97.4% and demonstrated strong generalization on external datasets such as KITTI and TuSimple. For lane condition assessment, a pixel occupancy–based method was applied, combined with Canny edge detection and morphological operations. A threshold of 80-pixel occupancy was used to classify lanes as intact or worn. The proposed framework reliably detected lane degradation under various road and lighting conditions. These results suggest that quantitative, image-based indicators can complement traditional standards and guide AV-oriented infrastructure policy. Limitations include a lack of adverse weather data and dataset-specific threshold sensitivity.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Infrastructure Maintenance and Monitoring · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Transportation Engineering, University of Seoul, Seoul 02504, Republic of Korea
Department of Urban Big Data Convergence, Graduate School, University of Seoul, Seoul 02504, Republic of Korea
Department of Civil and Environmental Engineering, Seoul National University, Seoul 08826, Republic of Korea
References (28)
Show source-provided references
1. World Road Association (PIARC) (2020). The Contribution of Road Transport to Sustainability and Economic Development: A PIARC Special Project, World Road Association (PIARC).
2. A Survey of Deep Learning Techniques for Autonomous Driving10.1002/rob.21918 ↗
3. Vision-Based Lane Departure Warning Framework10.1016/j.heliyon.2019.e02169 ↗
4. Paek, D., Kong, S.-H., and Wijaya, K.T. (2021). K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways. arXiv.10.1109/CVPRW56347.2022.00491 ↗
5. Yadav, S., Kumar, S.N.T., and Rajalakshmi, P. (2023, January 20–23). Vehicle Detection and Tracking Using Radar for Lane Keep Assist Systems. Proceedings of the 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), Florence, Italy.10.1109/VTC2023-Spring57618.2023.10199286 ↗
6. Federal Highway Administration (FHWA) (2023). Manual on Uniform Traffic Control Devices for Streets and Highways, USA Department of Transportation. [11th ed.].
7. California Department of Motor Vehicles (DMV) (2024, July 29). Disengagement Reports; 2024, Available online: https://www.dmv.ca.gov/portal/vehicle-industry-services/autonomous-vehicles/disengagement-reports/.
8. A Review of Lane Detection Methods Based on Deep Learning10.1016/j.patcog.2020.107623 ↗
9. Mamun, A.A., Ping, E.P., Hossen, J., Tahabilder, A., and Jahan, B. (2022). A Comprehensive Review on Lane Marking Detection Using Deep Neural Networks. Sensors, 22.10.3390/s22197682 ↗
10. Na, H., Kim, D., Kang, J., and Lee, C. (2025, January 19–21). Development of a Lane Identification and Assessment Framework for Maintenance Using AI Techniques. Proceedings of the 16th ITS European Congress, Seville, Spain.10.20944/preprints202505.2199.v1 ↗
11. Aly, M. (2008, January 4–6). Real-Time Detection of Lane Markers in Urban Streets. Proceedings of the 2008 IEEE Intelligent Vehicles Symposium, Eindhoven, The Netherlands.10.1109/IVS.2008.4621152 ↗
12. Bojarski, M., Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L.D., and Muller, U. (2016). End-to-End Learning for Self-Driving Cars. arXiv.
13. Pan, X., Shi, J., Luo, P., Wang, X., and Tang, X. (2018, January 2–7). Spatial As Deep: Spatial CNN for Traffic Scene Understanding. Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.12301 ↗
14. Kim, J., and Lee, M. (2014). Robust Lane Detection Based on Convolutional Neural Network and Random Sample Consensus. Neural Information Processing: 21st International Conference, Proceedings of the ICONIP 2014, Kuching, Malaysia, 3–6 November 2014, Springer.
15. Huval, B., Wang, T., Tandon, S., Kiske, J., Song, W., Pazhayampallil, J., Andriluka, M., Rajpurkar, P., Migimatsu, T., and Cheng-Yue, R. (2015). An Empirical Evaluation of Deep Learning on Highway Driving. arXiv.
16. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
17. Roy, A.M., and Bhaduri, J. (2023). A Computer Vision Enabled Damage Detection Model with Improved YOLOv5 Based on Transformer Prediction Head. arXiv.
18. Real-Time Lane Detection for Autonomous Vehicles Using YOLOv5 Segmentation Model
19. LDTR: Transformer-Based Lane Detection with Anchor-Chain Representation10.1007/s41095-024-0421-5 ↗
20. Wang, P., Luo, Z., Zha, Y., Zhang, Y., and Tang, Y. (2025). End-to-End Lane Detection: A Two-Branch Instance Segmentation Approach. Electronics, 14.10.3390/electronics14071283 ↗
21. Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2018, January 8–14). DeepLabv3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
22. Ghafoorian, M., Nugteren, C., Baka, N., Booij, O., and Hofmann, M. (2018). EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection. arXiv.10.1007/978-3-030-11009-3_15 ↗
23. Towards End-to-End Lane Detection: An Instance Segmentation Approach
24. Paszke, A., Chaurasia, A., Kim, S., and Culurciello, E. (2016). ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation. arXiv.
25. Contrastive Learning for Lane Detection via Cross-Similarity (CLLD)10.1016/j.patrec.2024.08.007 ↗
26. Peng, J., Bu, X., Sun, M., Zhang, Z., Tan, T., and Yan, J. (2020). Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels. arXiv.10.1109/CVPR42600.2020.00973 ↗
27. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (November, January 27). CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
28. Zhang, J. (2025, January 23–25). Evolution of YOLO: A Comparative Analysis of YOLOv5, YOLOv8, and YOLOv10. Proceedings of the 9th International Conference on Computing Innovation and Applied Physics (CONF-CIAP 2025), Singapore.10.54254/2755-2721/2025.21591 ↗