Road Sign Detection and Tracking from Complex Background

Road sign detection and tracking is one of the major tasks in a visual driver-assistance system. This paper describes an approach to detecting and tracking road signs appearing in complex traffic scenes. In the detecting phase, two neural networks are developed to extract color and shape features of traffic signs, respectively, from scenes images. A process characterized by fuzzy-set discipline is then invoked to search for road signs in the images on the basis of the extracted features. In the tracking phase, Kalman filter is employed to predict the positions and sizes of the road signs located earlier. The experimental results show that the proposed method can perform well in both detecting and tracking road signs present in complex scenes and in various weather and illumination conditions. Keyword: Road sign detection and tracking, HSI color model, Neural networks, Fuzzy integration, Kalman filter