Road sign feature extraction and recognition using dynamic image processing

In the research field of intelligent transportation systems (ITS), various suggestions have been made concerning road signs which can be automatically recognized by driver-support systems. Almost all of the methods proposed for road sign identification and recognition are processes performed using an instantaneously-acquired static image. As a result, the processing time is a problem. The method which this paper proposes assumes the use of an on-board camera, and involves processing of a dynamic image, allowing effective processing in case when the sign is temporarily hidden by another object. In addition, this paper proposes a simple algorithm for sign detection and recognition that reduces the amount of required calculation. In this paper, nine kinds of signs, such as "STOP," "NO ENTRY" and "NO PASSAGE" were prepared, each 1/3 the size of the actual signs. Experiments were then carried out for recognition of these signs under various kinds of measurement conditions.