Road sign detection based on visual saliency and shape analysis
Tao Zhang, Jingqin Lv, Jie Yang · 2013
Road sign detection plays an important role in driver assistance system. However, it faces problems of high computational cost and low contrast in video sequences. In this paper, we propose a two-level hierarchical algorithm which addresses these problems by making better use of the color and shape information of road signs. In order to solve the problem of low image contrast, we propose to improve the color contrast using our algorithm based on visual saliency. In order to reduce the high computational cost, an improved radial symmetry transform (IRST) is developed for grouping feature points on the basis of their underlying symmetry in an image. Experimental results show that our methods are robust to a broad range of lighting conditions and efficient enough for real-time applications.