A shape-based method for traffic sign detection
Gang Wu, Weijie Liu, Xiaohui Xie, Qiang Wei · PROCEEDINGS OF THE 14TH WORLD CONGRESS ON INTELLIGENT TRANSPORT SYSTEMS (ITS), HELD BEIJING, OCTOBER 2007 · 2007
Traffic sign detection is one of the important tasks for a driver assistance system. This paper describes a shape-based method for traffic sign detection. Multiple shapes including circles, regular and non-regular polygons can be detected under a general framework. The novelty of this approach is that different shapes can be simultaneously located and classified. It is implemented through taking account of both voting accumulations and voting directions. It is shown that the approach can reduce false detection and computation burden compared to some existing methods. Moreover, by modeling a shape based on its partial radial symmetry characteristics and the geometrical relationship among the symmetry centers, the approach is extended to detect non-regular polygons. Experiments on traffic sign detection demonstrated good performance of the method. For the covering abstract seeITRD E140665.