DETECTION AND TRACKING OF ROAD SIGNS

This paper describes an approach to detecting and tracking road signs that appear in complex traffic scenes and under various weather and illumination conditions. In the detecting phase, neural networks are used for extracting color and shape features of traffic signs. The signs are then located in the images based on the extracted features using a fuzzy set discipline. In the tracking phase, a Kalman filter is used to track the signs that were located in the detecting phase.