Traffic Sign Recognition System Based on Improved YOLOv5

Daohan Liu

doi:10.47297/taposatWSP2633-456910.20260707

PDF
导出
分享
收藏
专辑

Traffic Sign Recognition System Based on Improved YOLOv5

7卷第7期

浏览量: 0 Downloads: 0

Traffic Sign Recognition System Based on Improved YOLOv5
Traffic Sign Recognition System Based on Improved YOLOv5
Northwest A&F University, Xianyang, Shaanxi, 712100, China
2026年7卷第7期页码：48-54
网络首发：2026-08-21，

纸质出版：2026-07-30
DOI：10.47297/taposatWSP2633-456910.20260707
Accepted：

Scan QR Code

Daohan Liu. (2026). Traffic Sign Recognition System Based on Improved YOLOv5. 科技理论与实践（英文版）, 7(7), 48-54.

Liu Daohan.Traffic Sign Recognition System Based on Improved YOLOv5[J].Theory and Practice of Science and Technology,2026,07(07):48-54.
Daohan Liu. (2026). Traffic Sign Recognition System Based on Improved YOLOv5. 科技理论与实践（英文版）, 7(7), 48-54. DOI： 10.47297/taposatWSP2633-456910.20260707.

Liu Daohan.Traffic Sign Recognition System Based on Improved YOLOv5[J].Theory and Practice of Science and Technology,2026,07(07):48-54. DOI： 10.47297/taposatWSP2633-456910.20260707.

摘要

Abstract

Aiming at the problems faced by traffic sign recognition in autonomous driving and intelligent transportation systems

such as insufficient detection accuracy

strict real-time performance requirements

and poor robustness in complex environments

this paper designs and implements a traffic sign recognition system based on YOLOv5. The system adopts the PyQt5 framework to build a graphical user interface

and integrates functional modules including image acquisition

object detection

result visualization

and video recording. In terms of detection algorithms

YOLOv5 is taken as the basic detection framework

supporting the inference of multiple model formats such as PT

ONNX

and TensorFlow. In terms of image preprocessing

methods such as Gaussian filtering

edge detection and morphological transformation are introduced to improve image quality. The system is tested in real traffic scenarios

and the results show that it can effectively identify warning signs

prohibition signs and mandatory signs

with the detection speed meeting real-time requirements. Experimental results demonstrate that the system can maintain high recognition accuracy under challenging conditions such as complex illumination and partial occlusion

which provides a feasible technical solution for environmental perception in intelligent driving.

关键词

Keywords

references

Redmon J, Divvala S K, Girshick R B, Farhadi A. (2015). You Only Look Once: Unified, Real-Time Object Detection. CoRR, abs/1506.02640.

Wu X H, Tian Q C. (2020). Review of Traffic Sign Recognition Methods. Computer Engineering and Applications, 56(10), 20-26.

Stallkamp J, Schlipsing M, Salmen J, Igel C. (2011). The German Traffic Sign Recognition Benchmark: A multi-class classification competition. In 2011 International Joint Conference on Neural Networks (Vol.2, pp. 1453-1460). IEEE.

Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y, Berg A C. (2016). SSD: Single Shot MultiBox Detector. In Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I (pp. 21-37). Springer.

Redmon J, Farhadi A. (2016). YOLO9000: Better, Faster, Stronger. CoRR, abs/1612.08242.

Ren S Q, He K M, 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.

He K M, Zhang X Y, Ren S Q, Sun J. (2016). Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) (Vol.2, pp. 770-778). IEEE.

Lin T Y, Dollár P, Girshick R, He K M, Hariharan B, Belongie S. (2017). Feature Pyramid Networks for Object Detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) (Vol.2, pp. 936-944). IEEE.

Zhu Z, Huang X L, Liang D, Li B L, Zhang S H, Hu S M. (2016). Traffic-Sign Detection and Classification in the Wild. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) (Vol.3, pp. 2110-2118). IEEE.

Li M H, Yuan S N. (2024). Improved YOLOv5s Algorithm for Traffic Sign Detection. Journal of Nanjing University of Information Science and Technology, 16(1), 11-19.

Chen C C, Wang H N, Zhao Y, Wang Y P, Li L J, Li K, Zhang T Q. (2021). A New Traffic Sign Recognition Algorithm Based on Deep Learning. Telecommunication Engineering, 61(1), 76-82.

Shao N P. (2018). Traffic Sign Detection and Recognition for Intelligent Driving Vehicles in Natural Scenes [Master's thesis, Xihua University].

Shen Y, Zhao Y. (2021). Traffic Sign Recognition Method Based on Convolutional Neural Network. Journal of Zhejiang University of Science and Technology, 33(1), 16-23.

文章被引用时，请邮件提醒。

Submit

Lightweight Improvements Based on RT-DETR

Research on Road Pothole Detection System Based on Improved YOLOV11

Research Progress in Fringe Image Processing Algorithms

Research on CAN Bus Injection Attack Detection Method for Internet of Vehicles Based on Deep Learning

Physics Informed Neural Networks for PDE Coalescence

Related Author

Tianjun Yi School of Physics and Electronic Sciences, Changsha University of Science and Technology

Jialin Liu School of Information Engineering, North China University of Water Resources and Electric Power

Xiyong Yuan Mechanical Engineering School, University of Shanghai for Science and Technology

Haoyu Liu College of computer science, Beijing Information Science&Technology University

Zhang yu College of Science, China Jiliang University

Weihang Xue Shandong Technology and Business University

Zhaoyu Liu Shandong Technology and Business University

Yifan Li School of Physics, Sun Yat-sen University

Related Institution

School of Physics and Electronic Sciences, Changsha University of Science and Technology

School of Information Engineering, North China University of Water Resources and Electric Power

Mechanical Engineering School, University of Shanghai for Science and Technology

College of computer science, Beijing Information Science&Technology University

College of Science, China Jiliang University

⁰