A Comparative Study of Deep Learning Algorithms for Real-time Traffic Sign Recognition in Autonomous Vehicles

Abstract

This article presents a comparative study of deep learning algorithms for real-time traffic sign recognition in autonomous vehicles. Four deep learning models, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and a hybrid model that combines CNN and LSTM, were developed and trained using a dataset of traffic sign images. The models were evaluated based on their accuracy, precision, recall, and F1 score. The results showed that the hybrid model achieved the highest accuracy and fastest processing time among the four models, indicating its potential for real-time traffic sign recognition in autonomous vehicles. The study highlights the importance of selecting the appropriate deep learning algorithm for a specific application and suggests future research to explore the integration of traffic sign recognition with other advanced technologies to enhance the capabilities of autonomous vehicles.