Traffic Signal Detection Algorithm Based on Dual-GAM Improved YOLO26 under Nighttime Conditions

Main Article Content

Chongtao Hu
College of Engineering, Huazhong Agricultural University, Wuhan, Hubei, 430070, China

DOI: https://doi.org/10.70267/cai.v3n4.8298

Keywords

nighttime traffic light detection, YOLO26, attention mechanism, global attention mechanism (GAM)

Abstract

The environmental recognition of autonomous vehicles depends much on real-time object detection, and identifying small traffic signals in low-light conditions during the night is a difficult problem. The size of traffic signals is small and vulnerable to the disruption caused by street lights and the lights of vehicles, which requires high-quality feature representation capability of detectors. To overcome such a challenge, this paper presents the Global Attention Mechanism (GAM) to YOLO26 and suggests a better algorithm, YOLO26-GAM. Initially, YOLO26 is chosen as the base by comparative experiments between various YOLO-series models. Next, Grad-CAM is applied to view the basis on which the model makes decisions, and GAM modules are added at the H12 and H15 locations in the neck network. Cross-experiments and ablation experiments are done to test the effectiveness of the attention mechanism and the insertion positions. Experimental findings on the curated TN-TLD nighttime traffic light dataset demonstrate that YOLO26-GAM performs the best of all the experiments with a Precision of 0.964, Recall of 0.947, mAP50 of 0.966, mAP50-95 of 0.657, and F1 of 0.955. It is the only configuration that is superior to the baseline, without the attention mechanism, in all evaluation metrics, confirming the efficiency of the proposed method in detecting nighttime traffic signals.

Abstract 16 | PDF Downloads 7

References

  • [1] World Health Organization. (2023). Global status report on road safety 2023: Summary. https://www.who.int/publications/i/item/9789240086252
  • [2] Zhang, J., Yue, Y., & Zhu, X. (2025). Real-time fusion and object detection based on visible light and infrared images. In Proceedings of the 2025 9th International Conference on Control Engineering and Artificial Intelligence. https://doi.org/10.1145/3722150.3722160
  • [3] Jensen, M. B., Philipsen, M. P., Møgelmose, A., Moeslund, T. B., & Trivedi, M. M. (2016). Vision for looking at traffic lights: Issues, survey, and perspectives. IEEE Transactions on Intelligent Transportation Systems, 17(7), 1800–1815. https://doi.org/10.1109/TITS.2015.2509509
  • [4] De Charette, R., & Nashashibi, F. (2009). Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates. In 2009 IEEE Intelligent Vehicles Symposium (pp. 358–363). IEEE. https://doi.org/10.1109/IVS.2009.5164304
  • [5] Gomez-Moreno, H., Maldonado-Bascon, S., Gil-Jimenez, P., & Lafuente-Arroyo, S. (2010). Goal evaluation of segmentation algorithms for traffic sign recognition. IEEE Transactions on Intelligent Transportation Systems, 11(4), 917–930. https://doi.org/10.1109/TITS.2010.2054084
  • [6] De la Escalera, A., Armingol, J. M., & Mata, M. (2003). Traffic sign recognition and analysis for intelligent vehicles. Image and Vision Computing, 21(3), 247–258. https://doi.org/10.1016/S0262-8856(02)00156-7
  • [7] Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 580–587). IEEE.
  • [8] Kim, H.-K., Park, J. H., & Jung, H.-Y. (2018). An efficient color space for deep-learning based traffic light recognition. Journal of Advanced Transportation, 2018, Article 2365414. https://doi.org/10.1155/2018/2365414
  • [9] 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.
  • [10] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). SSD: Single shot multibox detector. In B. Leibe, J. Matas, N. Sebe, & M. Welling (Eds.), Computer Vision – ECCV 2016 (pp. 21–37). Springer. https://doi.org/10.1007/978-3-319-46448-0_2
  • [11] Müller, J., & Dietmayer, K. (2018). Detecting traffic lights by single shot detection. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC) (pp. 266–273). IEEE. https://doi.org/10.1109/ITSC.2018.8569651
  • [12] Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv. https://arxiv.org/abs/1804.02767
  • [13] Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv. https://arxiv.org/abs/2004.10934
  • [14] Du, S., et al. (2024). TSD-YOLO: Small traffic sign detection based on improved YOLO v8. IET Image Processing, 18(11), 2884–2898. https://doi.org/10.1049/ipr2.13166
  • [15] Chakrabarty, S. (2026). YOLO26: An analysis of NMS-free end-to-end framework for real-time object detection. arXiv. https://arxiv.org/abs/2601.12882
  • [16] Jensen, M. B., Nasrollahi, K., & Moeslund, T. B. (2017). Evaluating state-of-the-art object detector on challenging traffic light data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 9–15). IEEE.
  • [17] Girshick, R. (2015). Fast R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1440–1448). IEEE.
  • [18] Ren, S., He, K., Girshick, R., & Sun, J. (2016). 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
  • [19] Gavrilescu, R., Zet, C., Foșalău, C., Skoczylas, M., & Cotovanu, D. (2018). Faster R-CNN: An approach to real-time object detection. In 2018 International Conference and Exposition on Electrical and Power Engineering (EPE) (pp. 0165–0168). IEEE. https://doi.org/10.1109/ICEPE.2018.8559810
  • [20] Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, faster, stronger. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 6517–6525). IEEE.
  • [21] Li, C., et al. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv. https://arxiv.org/abs/2209.02976
  • [22] Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7464–7475). IEEE.
  • [23] Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. In European Conference on Computer Vision (pp. 1–21). Springer.
  • [24] Wang, A., et al. (2024). YOLOv10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, 37, 107984–108011.
  • [25] Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213–229). Springer.
  • [26] Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv. https://arxiv.org/abs/2010.04159
  • [27] Weber, M., Wolf, P., & Zöllner, J. M. (2016). DeepTLR: A single deep convolutional network for detection and classification of traffic lights. In 2016 IEEE Intelligent Vehicles Symposium (IV) (pp. 342–348). IEEE.
  • [28] Behrendt, K., Novak, L., & Botros, R. (2017). A deep learning approach to traffic lights: Detection, tracking, and classification. In 2017 IEEE International Conference on Robotics and Automation (ICRA) (pp. 1370–1377). IEEE. https://doi.org/10.1109/ICRA.2017.7989163
  • [29] Kulkarni, R., Dhavalikar, S., & Bangar, S. (2018). Traffic light detection and recognition for self driving cars using deep learning. In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA) (pp. 1–4). IEEE. https://doi.org/10.1109/ICCUBEA.2018.8697819
  • [30] Han, C., Gao, G., & Zhang, Y. (2019). Real-time small traffic sign detection with revised Faster-RCNN. Multimedia Tools and Applications, 78(10), 13263–13278. https://doi.org/10.1007/s11042-019-7238-9
  • [31] Zhang, H., et al. (2020). Real-time detection method for small traffic signs based on YOLOv3. IEEE Access, 8, 64145–64156. https://doi.org/10.1109/ACCESS.2020.2984554
  • [32] Wang, Q., Zhang, Q., Liang, X., Wang, Y., Zhou, C., & Mikulovich, V. I. (2021). Traffic lights detection and recognition method based on the improved YOLOv4 algorithm. Sensors, 22(1), 200. https://doi.org/10.3390/s22010200
  • [33] Niu, C., & Li, K. (2022). Traffic light detection and recognition method based on YOLOv5s and AlexNet. Applied Sciences, 12(21), 10808. https://doi.org/10.3390/app122110808
  • [34] Zhang, H., Liang, M., & Wang, Y. (2025). YOLO-BS: A traffic sign detection algorithm based on YOLOv8. Scientific Reports, 15, 7558. https://doi.org/10.1038/s41598-025-88184-0
  • [35] Evan, Wulandari, M., & Syamsudin, E. (2020). Recognition of pedestrian traffic light using TensorFlow and SSD MobileNet V2. In IOP Conference Series: Materials Science and Engineering, 1007(1), 012022. https://doi.org/10.1088/1757-899X/1007/1/012022
  • [36] Burgos, D. C., Iztueta, E. J., Ormaechea, I. M., Martínez-Otzeta, J. M., & Mugica, A. C. (2024). Deep learning-based traffic light detection in a custom embedded hardware platform for ADAS applications. IEEE Access, 12, 127862–127878. https://doi.org/10.1109/ACCESS.2024.3456789
  • [37] Zhao, Y., et al. (2024). DETRs beat YOLOs on real-time object detection. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 16965–16974). IEEE.
  • [38] Tang, C., Li, Y., Wang, L., & Li, W. (2025). Real-time traffic light detection based on lightweight improved RT-DETR. Journal of Real-Time Image Processing, 22(2), 82. https://doi.org/10.1007/s11554-025-01621-4
  • [39] Jocher, G., Qiu, J., Liu, M., Lyu, S., Akyon, F. C., & Kalfaoglu, M. E. (2026). Ultralytics YOLO26: Unified real-time end-to-end vision models. arXiv. https://arxiv.org/abs/2606.03748
  • [40] Munir, S., & Lin, H.-Y. (2025). LNT-YOLO: A lightweight nighttime traffic light detection model. Smart Cities, 8(3), 95. https://doi.org/10.3390/smartcities8030095
  • [41] Bajpai, A. (2024). Attire-based anomaly detection in restricted areas using YOLOv8 for enhanced CCTV security. arXiv. https://arxiv.org/abs/2404.00645
  • [42] Gui, Z., & Geng, J. (2024). YOLO-ADS: An improved YOLOv8 algorithm for metal surface defect detection. Electronics, 13(16), 3129. https://doi.org/10.3390/electronics13163129
  • [43] Wibowo, A., Trilaksono, B. R., Hidayat, E. M. I., & Munir, R. (2023). Object detection in dense and mixed traffic for autonomous vehicles with modified YOLO. IEEE Access, 11, 134866–134877. https://doi.org/10.1109/ACCESS.2023.3334567
  • [44] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626). IEEE.
  • [45] Liu, Y., Shao, Z., & Hoffmann, N. (2021). Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv. https://arxiv.org/abs/2112.05561
  • [46] Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 7132–7141). IEEE.
  • [47] Hou, Q., Zhou, D., & Feng, J. (2021). Coordinate attention for efficient mobile network design. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 13708–13717). IEEE.
  • [48] Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020). ECA-Net: Efficient channel attention for deep convolutional neural networks. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 11531–11539). IEEE.
  • [49] Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In European Conference on Computer Vision (pp. 3–19). Springer.

Article Sidebar

PDF
Published
Sep 16, 2026
Issue
Vol. 3 No. 4 (2026)
Section
Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Hu, C. . (2026). Traffic Signal Detection Algorithm Based on Dual-GAM Improved YOLO26 under Nighttime Conditions. Computers and Artificial Intelligence, 3(4), 82-98. https://doi.org/10.70267/cai.v3n4.8298