A YOLOv8-based approach for multi-class traffic sign detection

Abstract

Recognizing traffic signs is a crucial task in autonomous vehicles to improve road safety. In this study, we propose a novel You Only Look Once version 8 (YOLOv8) model for identifying traffic signs. The model has been trained on the Kaggle dataset, which contains multiple traffic signs under different environments. The YOLOv8 model achieved an accuracy of 80.64% and a recall of 65.67% on test data. These metrics highlight the model's capability to recognize traffic signs. Notably, YOLOv8 brought about some notable improvements over earlier versions, such as enhanced detection in difficult situations and enhanced small-scale sign identification. The paper also explores the difficulties that arose throughout the model's training phase and provides workable solutions that were used to overcome these difficulties, improving the model's performance. The encouraging outcomes demonstrate the viability of implementing the YOLOv8-based strategy in practical traffic management systems, which is a positive advancement towards the creation of more sophisticated and dependable traffic sign recognition technology.