A Study on the Lightweighting of YOLOv11-based Traffic Sign Detection Models
DOI:
https://doi.org/10.54097/8bwp0z34Keywords:
Traffic Sign Detection, YOLOv11, Small Object Detection, Feature Pyramid Network, Lightweight ModelAbstract
Accurate and real-time traffic sign detection is a critical component of environmental perception for Advanced Driver-Assistance Systems (ADAS) and autonomous vehicles, playing a vital role in ensuring driving safety. However, current mainstream lightweight object detection models often encounter performance bottlenecks when dealing with challenges prevalent in real-world road scenes, such as small objects and complex backgrounds, primarily due to the loss of feature information. To address this issue, this paper conducts an in-depth application and performance evaluation of an improved YOLOv11-based lightweight detection algorithm. The algorithm is characterized by two key features: first, it enhances the perceptual capabilities for tiny objects by introducing a higher-resolution P2 feature layer; second, it adopts an integrated fusion detection module, termed FPN-P2 in this paper, which applies a "shallow feature direct-path, deep feature fusion" strategy to efficiently integrate multi-scale features. Extensive experiments on the public TT100K dataset demonstrate that the optimized configurations of this architecture achieve significant breakthroughs in both performance and efficiency. Specifically, its performance-optimal configuration achieves a mAP@0.5 of 76.3%, substantially surpassing baseline models like YOLOv8n. Meanwhile, its efficiency-optimal configuration attains a high accuracy of 68.8% while having fewer parameters than the baseline model. This research not only provides and validates highly competitive solutions for high-precision lightweight traffic sign detection but also, through intensive ablation studies, offers valuable empirical insights into model architecture selection and optimization for specific tasks.
Downloads
References
[1] World Health Organization. (2018). Global status report on road safety 2018. https:// www.who. int/ publications/ i/item/ 9789241565684.
[2] Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 1, pp. I-511-I-518). IEEE.
[3] Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 1, pp. 886–893). IEEE. https:// doi. org/ 10.1109/CVPR.2005.177.
[4] Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. https://doi.org/10. 1109/ TPAMI. 2016.2577031.
[5] Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 779–788). IEEE. https://doi. org/ 10.1109/CVPR.2016.91.
[6] Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767. https:// doi. org/ 10.48550/arXiv.1804.02767.
[7] Jocher, G. (2020). YOLOv5. GitHub. https:// github.com/ ultralytics/ yolov5.
[8] Jocher, G., Chilian, A., Rai, P., & Solawetz, J. (2023). Ultralytics YOLOv8. GitHub. https://github. com/ ultralytics/ yolov8.
[9] Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402. 13616. https:// doi. org/ 10.48550/arXiv.2402.13616.
[10] Wang, A., Chen, H., Liu, L., Chen, K., Wang, Z., & He, J. (2024). YOLOv10: Real-time end-to-end object detection. arXiv preprint arXiv:2405.14458. https://doi. org/10. 48550/ arXiv. 2405.14458.
[11] Li, H., Li, J., Wei, H., Liu, Z., Wang, Z., & Xu, Z. (2024). GOLD-YOLO: A novel real-time object detector. arXiv preprint arXiv:2403. 11331. https:// doi.org/ 10. 48550/ arXiv. 2403.11331.
[12] Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., & Hu, S. (2016). Traffic-sign detection and classification in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2110–2118). IEEE. https:// doi. org/ 10.1109/CVPR.2016.232.
[13] Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), 1627–1645. https:// doi. org/10.1109/TPAMI.2009.167.
[14] Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. https:// doi. org/ 10. 48550/ arXiv. 2004.10934.
[15] Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 8759–8768). IEEE. https:// doi.org/ 10.1109/ CVPR. 2018.00913.
[16] Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2117–2125). IEEE. https:/ / doi.org/10.1109/CVPR.2017.228.
[17] Tan, M., Pang, R., & Le, Q. V. (2020). Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10781–10790). IEEE. https://doi.org/ 10.1109/CVPR42600. 2020.01079.
[18] Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). YOLOX: Exceeding YOLO series in 2021. arXiv preprint arXiv: 2107. 08430. https://doi.org/10.48550/arXiv.2107.08430.
[19] Wang, J., Bai, Y., Zhang, Y., & Wang, H. (2022). Research on traffic sign detection algorithm based on improved YOLOv5. In 2022 IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE) (pp. 432–436). IEEE. https:// doi.org/10.1109/ ICISCAE 55895. 2022. 9936214.
[20] Du, J., Wang, Z., Zhang, T., Ma, Y., & Li, B. (2023). A real-time traffic sign detection method based on improved YOLOv5 in bad weather. Electronics, 12(13), 2788. https:// doi.org/ 10. 3390/ electronics12132788.
[21] Yan, B., Zhang, J., Wang, S., Chen, S., & Li, P. (2023). A lightweight traffic sign detection method based on improved YOLOv5. In 2023 7th International Conference on Virtual and Augmented Reality Simulations (ICVARS) (pp. 130–134). IEEE. https://doi.org/10.1109/ICVARS57878.2023.10134443.
[22] Zhang, X., Liu, C., & Zhao, Z. (2022). An improved YOLOv5-based traffic sign detection algorithm. In 2022 International Conference on Computer Technology and Information Science (CTIS) (pp. 247–251). IEEE. https://doi.org/ 10.1109/ CTIS 55621. 2022.00057.
[23] Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The PASCAL Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2), 303–338. https://doi.org/10.1007/s11263-009-0275-4.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
