Road sign detection and recognition system for real-time embedded applications

Abstract

In this paper, we propose a road sign detection and recognition algorithm for an embedded application, which requires computationally simple but accurate algorithms. The algorithm is developed by using the Hue Saturation Intensity (HSI) color space to segment the road signs color (red, yellow, blue and white) and the regions of interest (ROI) in order to locate and determine the shape of the road sign (diamond, square, hexagonal and circular) in real street-view images. The shape is then used to classify road signs into four categories, i.e. warning, mandatory, prohibitory and informational signs. The characteristics of the shapes such as area and perimeter variables are used to identify the symbols in the road signs. These variables are compared with the template library which we have developed. The proposed algorithm is tested on the Malaysia's road signs which are captured on the roadside in their real environment. Experimental results on the accuracy of the road sign detection are reported in this paper. The proposed algorithm will be implemented in a real time embedded system using Xilinx Video Starter Kit Board- Spartan-3a DSP 3400A Edition.