Image classification system based on deep learning applied to the recognition of traffic signs for intelligent robotic vehicle navigation purposes

This paper presents a system for classifying images based on Deep Learning and applied in the recognition of traffic signals aiming to increase road safety increased road safety using autonomous and semi-autonomous intelligent robotic vehicles. This Advanced Driver Assistance System (ADAS) is a system created to automate vehicles, but also to help the human drivers to increase safety and the respect of traffic rules while driving the car. The system must be able to classify several different traffic signs (e.g. maximum speed allowed, stop, slow down, turn ahead, pedestrian), thus helping to make navigation within the local traffic rules. The obtained results are promising and very satisfactory, where we get 97.24% of test accuracy in a well known traffic sign benchmark dataset (INI - German Traffic Sign Benchmark).