Traffic sign detection based on visual attention model

Abstract

TSR (Traffic sign recognition) is an important research field in ITS (Intelligent traffic system), which is being paid more and more attention for realizing drivers assisting system and automated navigation etc. Author proposed a new method to detect traffic signs in outdoor scene. The method is divided into 2 step. Firstly, Two-way integration method including both methods drived by task and methods drived by data for coarse segmentation, which improves the accuracy of detection. And then edge extraction and morphological operations are used to obtain enclosed area. The shape of the enclosed area is determined by the circularity and central double cross shape measurement in order to detect the prohibition signs. The results showed the proposed method can effectively detect the prohibition signs.