Traffic Sign Detection and Recognition System for Autonomous RC Cars

Abstract

Traffic signs play an important role to regulate daily traffic by providing necessary information to the drivers. For unmanned driving systems, real time and robust detection and recognition of traffic signs is one of the main concerns. Therefore, a traffic sign detection and recognition system for autonomous radio controlled cars is proposed. In this work, traditional image processing methods and deep neural networks techniques are combined. First, the online video is streamed from the car camera and the input frame region of interest is detected. Secondly, a convolutional neural network is used to recognize these candidate images. Experimental results show that the proposed system works efficiently up to %87.36 of images. However, calibration is needed for image processing techniques for various environments.