A YOLOv8-CE-based real-time traffic sign detection and identification method for autonomous vehicles

Abstract

Traffic sign detection in real scenarios is challenging due to their complexity and small size, often preventing existing deep learning models from achieving both high accuracy and real-time performance. An improved YOLOv8 model for traffic sign detection is proposed. Firstly, by adding Coordinate Attention (CA) to the Backbone, the model gains location information, improving detection accuracy. Secondly, we also introduce EIoU to the localization function to address the ambiguity in aspect ratio descriptions by calculating the width-height difference based on CIoU. Additionally, Focal Loss is incorporated to balance sample difficulty, enhancing regression accuracy. Finally, the model, YOLOv8-CE (YOLOv8-Coordinate Attention-EIoU), is tested on the Jetson Nano, achieving real-time street scene detection and outperforming the Raspberry Pi 4B. Experimental results show that YOLOv8-CE excels in various complex scenarios, improving mAP by 2.8% over the original YOLOv8. The model size and computational effort remain similar, with the Jetson Nano achieving an inference time of 96 ms, significantly faster than the Raspberry Pi 4B.