Scholarlink

With the rapid development of intelligent transportation systems and autonomous driving technologies, accurate recognition of traffic signs has become a key technique to ensure road safety. This paper applies the YOLOv8 model to traffic sign recognition and compares its performance with YOLOv5. Experimental results show that YOLOv8 demonstrates significant advantages in accuracy, speed, and stability, with the YOLOv8l version achieving the best recognition performance. To improve user experience, a graphical user interface (GUI) based on PyQt5 is developed, supporting image, video, and real-time camera input for visualized detection results. The results confirm that the YOLOv8l model can effectively and accurately recognize traffic signs under complex traffic scenarios, proving its high practical value. This research provides strong technical support for intelligent transportation systems and autonomous driving, showcasing the potential of deep learning in the field of traffic sign recognition.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Application Research of YOLO Models in Traffic Sign Recognition

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Haiqian Huang,
  • Qiming Wu

摘要

With the rapid development of intelligent transportation systems and autonomous driving technologies, accurate recognition of traffic signs has become a key technique to ensure road safety. This paper applies the YOLOv8 model to traffic sign recognition and compares its performance with YOLOv5. Experimental results show that YOLOv8 demonstrates significant advantages in accuracy, speed, and stability, with the YOLOv8l version achieving the best recognition performance. To improve user experience, a graphical user interface (GUI) based on PyQt5 is developed, supporting image, video, and real-time camera input for visualized detection results. The results confirm that the YOLOv8l model can effectively and accurately recognize traffic signs under complex traffic scenarios, proving its high practical value. This research provides strong technical support for intelligent transportation systems and autonomous driving, showcasing the potential of deep learning in the field of traffic sign recognition.