Abstract
Fast and accurate detection of traffic signs is crucial for the development of intelligent transportation systems. To address the issue of false detection and missing detection of small traffic signs in complex scenes, this paper proposes a YOLO-SG model based on YOLOv5. The YOLO-SG approach employs SPD-Conv as a down-sampling structure to mitigate the loss of feature information during the down-sampling process. This enhances the detection performance of small objects in complex scenes and improves the generalization and robustness of the model. The feature extraction architecture uses GhostNet, which effectively reduces the number of model parameters and weight, enhancing the feasibility of practical model deployment. Furthermore, this study optimizes the output feature structure by introducing a small object detection layer and removing the large object detection layer, enabling the detection of small objects. Extensive experiments conducted on the GTSDB and TT100K datasets demonstrate that YOLO-SG exhibits excellent detection performance. On the GTSDB dataset, YOLO-SG achieved a 2.3% increase in mAP compared to the baseline network, while reducing the number of parameters by 42%. Similarly, on the TT100K dataset, YOLO-SG increased mAP by 6.3% and reduced the number of parameters by 43%. These experimental results showcase the effectiveness and accuracy of YOLO-SG, particularly in detecting small traffic signs.
Similar content being viewed by others
Availability of data and materials
The GTSDB and TT100K datasets used in this paper are open, which can be downloaded from the Internet.
References
Dong X, Yan S, Duan C (2022) A lightweight vehicles detection network model based on YOLOv5. Eng Appl Artif Intell 113:104914
Lei M, Song Y, Zhao J, Wang X, Lyu J, Xu J, Yan W (2022) End-to-end network for pedestrian detection, tracking and re-identification in real-time surveillance system. Sensors 22(22):8693
Zhu X, Lyu S, Wang X, Zhao Q (2021) Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 2778–2788
Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp 740–755. Springer
Wali SB, Hannan MA, Abdullah S, Hussain A, Samad SA (2015) Shape matching and color segmentation based traffic sign detection system. Threshold 90:255
Lillo-Castellano J, Mora-Jiménez I, Figuera-Pozuelo C, Rojo-Álvarez JL (2015) Traffic sign segmentation and classification using statistical learning methods. Neurocomputing 153:286–299
Ellahyani A, Ansari M, Jaafari I, Charfi S (2016) Traffic sign detection and recognition using features combination and random forests. Int J Adv Comput Sci Appl 7(1):686–693
Chakraborty S, Deb K (2015) Bangladeshi road sign detection based on ycbcr color model and dtbs vector. In: 2015 International Conference on Computer and Information Engineering (ICCIE), pp 158–161. IEEE
Berkaya SK, Gunduz H, Ozsen O, Akinlar C, Gunal S (2016) On circular traffic sign detection and recognition. Expert Syst Appl 48:67–75
Madani A, Yusof R (2018) Traffic sign recognition based on color, shape, and pictogram classification using support vector machines. Neural Comput Appl 30:2807–2817
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
Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1440–1448
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol 28
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961–2969
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pp 21–37. Springer
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
Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7263–7271
Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934
Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, et al. (2022) Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976
Zhang J, Xie Z, Sun J, Zou X, Wang J (2020) A cascaded r-cnn with multiscale attention and imbalanced samples for traffic sign detection. IEEE Access 8:29742–29754
Li X, Xie Z, Deng X, Wu Y, Pi Y (2022) Traffic sign detection based on improved faster r-cnn for autonomous driving. J Supercomput, pp 1–21
Liu S, Cai T, Tang X, Zhang Y, Wang C (2022) Visual recognition of traffic signs in natural scenes based on improved retinanet. Entropy 24(1):112
Ahmed S, Kamal U, Hasan MK (2021) Dfr-tsd: A deep learning based framework for robust traffic sign detection under challenging weather conditions. IEEE Trans Intell Transp Syst 23(6):5150–5162
Han C, Gao G, Zhang Y (2019) Real-time small traffic sign detection with revised faster-rcnn. Multimed Tools Appl 78:13263–13278
Liang T, Bao H, Pan W, Pan F (2022) Traffic sign detection via improved sparse r-cnn for autonomous vehicles. J Adv Transp 2022:1–16
Wu J, Liao S (2022) Traffic sign detection based on ssd combined with receptive field module and path aggregation network. Comput Intell Neurosci. https://doi.org/10.1155/2022/4285436
Zhang J, Huang M, Jin X, Li X (2017) A real-time Chinese traffic sign detection algorithm based on modified yolov2. Algorithms 10(4):127
Gu Y, Si B (2022) A novel lightweight real-time traffic sign detection integration framework based on yolov4. Entropy 24(4):487
Wang L, Zhou K, Chu A, Wang G, Wang L (2021) An improved light-weight traffic sign recognition algorithm based on yolov4-tiny. IEEE Access 9:124963–124971
Song W, Suandi SA (2023) Tsr-yolo: A Chinese traffic sign recognition algorithm for intelligent vehicles in complex scenes. Sensors 23(2):749
Hu J, Wang Z, Chang M, Xie L, Xu W, Chen N (2022) Psg-yolov5: A paradigm for traffic sign detection and recognition algorithm based on deep learning. Symmetry 14(11):2262
Wang J, Chen Y, Dong Z, Gao M (2022) Improved yolov5 network for real-time multi-scale traffic sign detection. Neural Comput Appl. https://doi.org/10.1007/s00521-022-08077-5
Sunkara R, Luo T (2023) No more strided convolutions or pooling: a new cnn building block for low-resolution images and small objects. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part III, pp 443–459 . Springer
Han K, Wang Y, Tian Q, Guo J, Xu C, Xu C (2020) Ghostnet: More features from cheap operations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 1580–1589
Houben S, Stallkamp J, Salmen J, Schlipsing M, Igel C (2013) Detection of traffic signs in real-world images: The German traffic sign detection benchmark. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp 1–8. IEEE
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
Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430
Chen X, Gong Z (2021) YOLOv5-Lite: Lighter, faster and easier to deploy. https://doi.org/10.5281/zenodo.5241425
Funding
Funding for this study was received from the Youth Program of Shaanxi Province: 2022JQ-624; the China University Industry Research and Innovation Fund: 2021ALA02002; the Higher Education Teaching Reform Research Project of China Textile Industry Association: 2021BKJGLX004; and the Higher Education Research Project of Xi’an Polytechnic University: 20GJ05.
Author information
Authors and Affiliations
Contributions
Y.H. and F.W. contributed to conceptualization and writing—original draft preparation; W.W. helped with the methodology; Y.H. assisted with software; F.W. carried out validation; Y.H., X.L., and J.Z. conducted investigation; W.W. and F.W. were involved in writing—review and editing; and X.L. and J.Z. were responsible for visualization. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethics approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Han, Y., Wang, F., Wang, W. et al. YOLO-SG: Small traffic signs detection method in complex scene. J Supercomput 80, 2025–2046 (2024). https://doi.org/10.1007/s11227-023-05547-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-023-05547-y