Abstract

Autonomous vehicle development is currently progressing at a very fast pace and traffic sign detection and classification has an important role in it. This paper analyzes a few possible approaches of doing this task in real-time using a portable system. The final solution uses a convolutional neural network for detection and classification combined with a custom optical character recognition algorithm for speed limit signs. The training and testing dataset is based on a combination of the Belgian Dataset, German Dataset, as well as images taken while driving in Illinois, United States.