Traffic sign recognition using colour information

In this paper, we present a novel approach for the detection and recognition of traffic signs. Colour images are acquired by a camera mounted in a car. In the first step, these images are colour segmented with a pixel classifier. Colour combinations which are characteristic for traffic signs generate hypotheses. These hypotheses are verified using a pictogram classifier. stem has been successfully tested on thousands of traffic scenes. The processing of a 512 by 512 frame takes approximately 1 second on a Sparc-10. roject is part of the European research programme PROMETHEUS and is being developed by Daimler-Benz in collaboration with various university labs.