Evaluating Traffic Signs Detection using Faster R-CNN for Autonomous driving

摘要

Traffic signs, which provide visual representation, play key role in autonomous navigation. Thus, detection and classification of traffic signs are one of the key requirements in autonomous vehicles (AVs). AVs heavily rely on object detection techniques to classify the traffic signs. In recent years, deep convolutional neural networks (CNNs) such as Faster R-CNN have achieved incredible success on object detection such as traffic signs. This paper focuses on the evaluation of state-of-the-art traffic signs detection techniques using deep learning algorithms and determination of the optimal one that can efficiently detect the traffic signs in real-time. Applying Faster R-CNN, the real-time traffic sign detection shall allow the autonomous vehicles to make decisions in real-time.