Title: A road traffic sign recognition method based on improved YOLOv5

Authors: Lu Shi; Haifei Zhang

Addresses: School of Computer and Information Engineering, Nantong Institute of Technology, Nantong 226602, China ' School of Computer and Information Engineering, Nantong Institute of Technology, Nantong 226602, China

Abstract: With the rapid development of artificial intelligence technology, the automatic driving of intelligent vehicles has gradually entered people's lives. The traditional vision will fail in many scenarios, such as snow, lane line wear, occlusion, or haze weather. This study aims to provide an accurate and efficient method for recognising traffic signs in their natural surroundings. The advanced convolutional block attention module attention mechanism is embedded in the infrastructure of you only look once version 5 (YOLOv5), which strengthens the network's ability to capture key features of the image. Then, the transformer module is introduced in the core part of YOLOv5, which uses its self-attention mechanism to effectively enhance the overall context connection, thereby significantly enhancing the model's detection accuracy and achieving an impressive 91% high accuracy performance. According to the most recent experimental data, the enhanced YOLOv5 model performs exceptionally well at recognising traffic signs in various natural settings.

Keywords: deep learning; object detection; traffic sign recognition; YOLOv5.

DOI: 10.1504/IJSNET.2025.143900

International Journal of Sensor Networks, 2025 Vol.47 No.1, pp.47 - 59

Received: 09 Jul 2024
Accepted: 16 Jul 2024
Published online: 13 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article