A review of YOLO-based traffic sign target detection

Authors

  • Siteng Liu

DOI:

https://doi.org/10.61173/gv1hwn77

Keywords:

Autonomous Driving, Real-time Detection, YOLO Algorithm, Traffic Signs

Abstract

YOLO (You Only Look Once) as an efficient target detection algorithm has significant advantages in the field of image recognition and traffic sign detection. The continuous development of autonomous driving technology needs to be supported by an algorithm that can quickly and accurately identify traffic signs, vehicles, pedestrians and other important objects on the road. By using the YOLO algorithm, we can achieve fast and accurate recognition of traffic signs, which is of great significance for improving the safety of autonomous driving technology. This study firstly introduces the general framework of YOLO series algorithms, including the network structure, introduces the development history of YOLO series and analyses the characteristics of each generation of algorithms, then discusses the application of YOLO algorithms in the field of traffic sign recognition, and finally summarizes the existing problems and puts forward a few points of possible optimization directions in the future.

References

[1] CAO J L, LI Y L, SUN H Q, et al. A review of visual object detection technology based on deep learning [J]. Chinese Journal of Image and Graphics,2022, 27(06):1680-1730

[2] Maas A L, Hannun A Y, Ng A Y. Rectifier nonlinearities improve neural network acoustic models[C]//Proc. icml. 2013, 30(1): 3.

[3] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

[4] N E U B E C K , G O O L L . E ff i c i e n t n o n - m a x i m u m suppression[C]//International Conference on Pattern Recognition,2006:840-852.

[5] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 2-10.

[6] REDMON J,DIVVALA S,GIRSHICK R,et al.You only Dean&Francis look once:unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:780-790.

[7] REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6520-6525.

[8] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [EB/OL]. (2014-5-1) [2023-5-29].https://ar xiv.org/pdf/1409.1556.pdf.

[9] LIN M, CHEN Q, YAN S C. Network in network [EB/OL]. (2013-12-16) [2023-5-29]. https://arxiv.org/pdf/1312.4400.pdf.

[10] REDMON J,FARHADI A.Yolov3:an incremental improvement[J].arXiv:1804.02767,2018.

[11] LIN T Y, DOLLΆR P, CIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017:940-944. [ 1 2 ] B O C H K O V S K I Y A , WA N G C Y, L I A O H Y M.Yolov4:optimal speed and accuracy of object detection[J]. arXiv:2004.10934,2020.

[13] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection [EB/OL]. (2020- 4-23) [2023-5-29]. https: //arxiv.org/pdf/2004.10934.pdf.

[14] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2020: 1571-1580.

[15] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression [EB/OL]. (2019-11-19) [2023-8-7]. https://arxiv.org/pdf/1911.08287.pdf.

[16] MISRA D. Mish: a self regularized non-monotonic activation function [EB/OL]. (2019-8-23) [2023-5-29].https:// arxiv.org/pdf/1908.08681.pdf.

[17] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9): 1904-1916.

[18] LIN T Y, DOLLΆR P, CIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017:1036-1044.

[19] JOCHERG.Yolov5[EB/OL].[2023-03-20].http//github.com/ ultralytics/yolov5.

[20] LI C Y,LI L L,JIANG H L,et al.Yolov6:a single stage object detection framework for industrial applications[J]. arXiv:2209.02976,2022.

[21] GE Z, LIU S T, LI Z M, et al. OTA: optimal transport assignment for object detection [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 305-310.

[22] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[EB/OL].(2022-5-25)[2023-6-1].https:// arxiv.org/pdf/2205.12740.pdf

[23] Li C,Zhou A, Yao A.Omni-dimensional dynamic convolution[J].Computer Vision and Pattern Recognition,2022.

[24] Benallal M, Meunier J. Real-time color segmentation of road signs[C]. Electrical and Computer Engineering. Toronto, Canada, 2003: 1823-1826.

[25] Zhu S D,Liu L L,LU X F, et al. Color-geometric model for traffic sign recognition[J].Chinese Journal of Scientific Instrument.2007,28(5):954-958.

[26] VAZQUEZ-CORRAL J, GALDRAN A, CYRIAC P. A fast image dehazing method that does not introduce color artifacts[J]. Journal of RealTime Image Processing, 2020, 17(3): 607-622

[27] SHEN Z H,FU M Y,YANG Y, et al. Traffic sign image segmentation method based on background pixels mutation analysis[J]. Application Research of Computers. 2012, 29(9): 3531-3535.

[28] Loy G, Barnes N, Shaw D, et al. Regular polygon detection[C]. IEEE International Conference on Computer Vision. San Diego. CA, USA , 2005: 778-785.

[29] Paulo C F,Correia P L.Automatic detection and classification of traffic signs[C].Eighth International Workshop on Image Analysis for Multimedia Interactive Services. Santorini,Greece,2007: 11-14.

[30] Tang K,Li Shiying,Liu Juan,et al. Traffic Sign Detection Based on Multiple Features Cooperation[J]. Computer Engineering,2015,41(3):211-217.

[31] Chang Faliang1,Huang Cui1,Liu Chengyun1,et al. Traffic sign detection based on Gaussian color model and SVM[J]. Chinese Journal of Scientific Instrument. 2014, 35(1): 43-49.

[32] Girshick R,Donahue J,Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C].IEEE conference on computer vision and pattern recognition. Columbus,OH,USA,2014: 580-590.

[33] He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence. 2015, 37(9): 1904- 1916.

[34] R. Girshick. Fast R-CNN[C]. IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 1440- 1450.

[35] Redmon J, Divvala S, Girshick, R, et al. You only look once: Unified, real-time object detection[C]. IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 780–790.

[36] Zhang J, Xie Z, Sun J, et al. A cascaded R-CNN with multiscale attention and imbalanced samples for traffic sign detection[J]. IEEE access, 2020, 8: 29740-29760.

[37] Zhang J, Wang W, Lu C, et al. Lightweight deep network for traffic sign classification[J]. Annals of Telecommunications, 2020, 75(7): 369-379. Dean&Francis

[38] Li Xudong, Zhang. Jianming,et al.A Fast Traffic Sign Detection Algorithm Based on Three-Scale Nested Residual Structure[J].Journal of Computer Research and Developme nt,2020,57(05):1022-1036.

[39] Zhang J, Huang M, Jin X, et al. A real-time chinese traffic sign detection algorithm based on modified YOLOv2[J]. Algorithms, 2017, 10(4): 127.

[40] BENJUMEA A, TEETI I, CUZZOLIN F, et al. YOLO-Z: improving small object detection in YOLOv5 for autonomous vehicles [EB/OL]. (2021-12-22) [2023-6-3]. https://arxiv.org/ pdf/2112.11798.pdf.

[41] YU J, YE X, TU Q. Traffic sign detection and recognition in multiimages using a fusion model with YOLO and VGG network [J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(9):16630-16642.

[42] DEWI C, CHEN R C, LIU Y T, et al. Yolo V4 for Advanced Traffic Sign Recognition with Synthetic Training Data Generated by Various GAN[J]. IEEE Access, 2021, 9: 97228-97242.

[43] GAO H, WANG W H, YANG C J, et al. Traffic Signal Image Detection Technology Based on YOLO[C]// Journal of Physics: Conference Series, 2021, 1961(1).

[44] PAN H P, WANG M Q, ZHANG F Q. Traffic Sign Detection and Recognition Method Based on Optimized YOLO- V4[J]. Computer Science, 2022, 49(11): 179-184.

[45] Natarajan S, Annamraju A K, Baradkar C S, Traffic signrecognition using weighted multiconvolutional neuralnetwork[J]. IET Intelligent Transport Systems. 2018, 12(10): 1396-1405.

[46] Li Jia, Wang Zengfu. Real-time traffic sign recognitionbased on efficient CNNs in the wild[J].IEEE Transac-tions on Intelligent Transportation Systems. 2019, 20(3): 975-984.

[47] QIAN W, WANG G Z, LI G P. Traffic Light Detection Algorithm Based on Multi Scale YOLOv5[J]. Software Guide, 2022, 21(9): 19-25.

[48] MAO K J, JIN R H, YING L K, et al. SC-YOLO: provide application level recognition and perception capabilities for smart city industrial cyber-physical system [J]. IEEE Systems Journal, 2023:1-12.

[49] O.Nacir, M.Amna, W.Imen and B.Hamdi,”Yolo V5 for Traffic Sign Recognition and Detection Using Transfer Learning,” 2022 IEEE International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM), Tunis, Tunisia, 2022:1-4.

[50] Batool A, Nisar M W, Shah J H, et al. iELMNet: integrating novel improved extreme learning machine and convolutional neural network model for traffic sign detection[J]. Big data, 2022.

Downloads

Published

2024-06-06

Issue

Vol. 2 No. 3 (2024): Volume 2, Issue 3

Section

Articles

License

Copyright (c) 2024 by the authors.

Creative Commons License

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