Future Computer Vision Algorithms for Traffic Sign Recognition Systems

Abstract

For the assistance of drivers and for autonomous vehicles an automatic recognition of traffic signs is essential. Today’s traffic sign recognition systems are focusing on circular signs. Because speed limit signs are circular and because the recognition of speed limit signs deliver a high customer benefit, such systems have been realized primarily in series production. But for traffic sign recognition there are still many challenges to be tackled. This contribution presents how research and intelligent development of computer vision algorithms will enable much more advanced traffic sign recognition systems on embedded systems by reducing processing time while simultaneously enlarging functionality. The result is a reduction of hardware cost and energy consumption.