Real-time color segmentation of road signs

This subject is part of a more challenging research project aimed at developing a computer vision system, embedded in a car, and capable of identijjing and localing road signs. Several constraints limit the possible solutions are first identified. For instance in such an application, we definite/y need a real-time system: in addition, we wish to limit OUT choice to a single camera methodology to keep the hardware as simple as possible and finally our approach must work efficiently on low cost hardware. For this purpose wefirst rely on a color segmentation strategv to recognize the road signs. We have studied the behavior of the RGB components of several road signsfrom sunrise to sunset. From these results we have shown that the simple comparison of the RGB componenls taken two by two is sufficient to segment road signs in real-time. From this segmentation it should be much easier to identrfy the shape (and meaning} of aparticular sign. 1