An Improved YOLOv11 Algorithm For Traffic Sign Detection

Qianlong Chen, Changming Zhu, Hengbin Li
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:322-330, 2025.

Abstract

As an important part of the Intelligent Transportation System (ITS), traffic sign recognition is of great significance for ensuring driving safety and improving traffic efficiency. This paper proposes a method that incorporates three modules, namely Adaptive Spatial Feature Fusion (ASFF), Spatial and Channel Synergistic Attention (SCSA), and Omni-Dimensional Dynamic Convolution (ODConv), into YOLOv11, aiming to enhance the performance of traffic sign detection. By enhancing the adaptability of feature scales through ASFF, optimizing feature extraction and fusion with SCSA, and strengthening the convolution operation with ODConv, the research results effectively improve the recognition accuracy and speed of various road signs on complex roads. Experimental results show that this integrated model outperforms the original YOLOv11 model and other comparative models in the traffic sign detection task, providing a more effective detection solution for the intelligent transportation field.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-chen25a, title = {An Improved YOLOv11 Algorithm For Traffic Sign Detection}, author = {Chen, Qianlong and Zhu, Changming and Li, Hengbin}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {322--330}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/chen25a/chen25a.pdf}, url = {https://proceedings.mlr.press/v278/chen25a.html}, abstract = {As an important part of the Intelligent Transportation System (ITS), traffic sign recognition is of great significance for ensuring driving safety and improving traffic efficiency. This paper proposes a method that incorporates three modules, namely Adaptive Spatial Feature Fusion (ASFF), Spatial and Channel Synergistic Attention (SCSA), and Omni-Dimensional Dynamic Convolution (ODConv), into YOLOv11, aiming to enhance the performance of traffic sign detection. By enhancing the adaptability of feature scales through ASFF, optimizing feature extraction and fusion with SCSA, and strengthening the convolution operation with ODConv, the research results effectively improve the recognition accuracy and speed of various road signs on complex roads. Experimental results show that this integrated model outperforms the original YOLOv11 model and other comparative models in the traffic sign detection task, providing a more effective detection solution for the intelligent transportation field.} }
Endnote
%0 Conference Paper %T An Improved YOLOv11 Algorithm For Traffic Sign Detection %A Qianlong Chen %A Changming Zhu %A Hengbin Li %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-chen25a %I PMLR %P 322--330 %U https://proceedings.mlr.press/v278/chen25a.html %V 278 %X As an important part of the Intelligent Transportation System (ITS), traffic sign recognition is of great significance for ensuring driving safety and improving traffic efficiency. This paper proposes a method that incorporates three modules, namely Adaptive Spatial Feature Fusion (ASFF), Spatial and Channel Synergistic Attention (SCSA), and Omni-Dimensional Dynamic Convolution (ODConv), into YOLOv11, aiming to enhance the performance of traffic sign detection. By enhancing the adaptability of feature scales through ASFF, optimizing feature extraction and fusion with SCSA, and strengthening the convolution operation with ODConv, the research results effectively improve the recognition accuracy and speed of various road signs on complex roads. Experimental results show that this integrated model outperforms the original YOLOv11 model and other comparative models in the traffic sign detection task, providing a more effective detection solution for the intelligent transportation field.
APA
Chen, Q., Zhu, C. & Li, H.. (2025). An Improved YOLOv11 Algorithm For Traffic Sign Detection. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:322-330 Available from https://proceedings.mlr.press/v278/chen25a.html.

Related Material