The proposed MobileNet Architecture with YOLOv5 achieves high accuracy in traffic sign recognition, with 97% training accuracy and 98% validation accuracy.
Authors
V. Lakshmi, Department of Computer Science, Mahindra University, Telangana, Hyderabad, 500043, India
Nagalaxmi Bogem, Department of Computer Science, Mahindra University, Telangana, Hyderabad, 500043, India
Jangirala Srinivas, Associate Professor, Jindal Global Business School, O. P. Jindal Global University, Haryana, Sonepat, India
Summary
The advancement of self-driving vehicles underscores the importance of robust traffic sign recognition systems. Accurate interpretation of traffic signs is pivotal for passenger safety and efficient navigation. To address this, we propose a novel approach employing the MobileNet Architecture and YOLOv5 for traffic sign recognition. Leveraging MobileNet Architecture, we achieved remarkable performance with a Training Accuracy of 97.00% and Validation Accuracy of 98.00%.
Published in: AIP Conference Proceedings
To read the full article, please click here.
