In the context of road traffic safety, intelligent driver assistance systems are particularly important. During everyday driving, drivers are influenced by factors such as weather and fatigue, which can prevent them from quickly and accurately reacting to current traffic sign information. Therefore, to enable faster and more precise recognition, this paper designs an efficient traffic sign detection method. Image enhancement technology, particularly the Retinex algorithm, is introduced to improve the visual effect of images and enhance the separability of features. The introduction of the ConvNeXt V2 network further improves the detection speed and accuracy of the YOLOv8 model. Additionally, a self-collected dataset was supplemented to lay a good foundation for subsequent training.
Traffic sign recognition system based on YOLOv8-ConvNeXt
International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2024) ; 2024 ; Shenyang, China
Proc. SPIE ; 13555
2025-04-18
Conference paper
Electronic Resource
English
Traffic Sign Detection Using YOLOv8
IEEE | 2024
|YOLO-TSR: A Novel YOLOv8-Based Network for Robust Traffic Sign Recognition
Transportation Research Record | 2025
|Traffic sign detection and identification method based on YOLOv8
European Patent Office | 2023
|