Recognition of Traffic Sign for Driver Assistance Systems

Abstract — This paper deals with the automatic detection and recognition of traffic sign boards in Indian roads to alert the driver. A camera fitted in the car captures the video and sends the data to an in-vehicle computing device. We propose a four stage algorithm that detects the traffic signs using YCbCr colour space and shape based filtering. The detected traffic signs are tracked and recognized using interest point descriptors. The algorithm is robust and can detect signs even when the traffic sign board is rotated. The traffic sign template database can be updated easily. The method is aimed at achieving high accuracy in recognizing traffic signs at real-time, with a low computational cost. Reduced computational complexity of the algorithm enables the implementation of the proposed method in embedded systems for driver assistance. Index Terms — Traffic Sign detection,Colour Segmentation, YCbCr Colour space,Interest Point Descriptors