Towards large-scale traffic sign detection and recognition

Recognition of traffic signs is a well researched field in the computer vision community, with several commercial applications already available. However, a vast majority of existing approaches focuses on recognition of a relatively small number of traffic sign categories (about 50 or less). In this paper, we adopt a convolutional neural network (CNN) approach, i.e., the Faster R-CNN, to address the full pipeline of detection and recognition of more than 100 traffic sign categories, depicted in our novel dataset that was acquired on Slovenian roads. We report promising results on highly challenging traffic sign categories that have not yet been considered in previous works and we provide useful insights for CNN training.