A Traffic signs' detection method of contour approximation based on concave removal

Abstract

In this paper, a simple and efficient algorithm for detecting deformed and occlusion triangular and circular traffic signs under complex natural scenes is proposed. Firstly, the image is segmented and binarized. Then the convex hull of every contour extracted from the binarized image is calculated. Some concave part of a contour is removed and is replaced by the corresponding convex edge of the convex hull. After that, the contour is approximated to a polygon. Finally, Those contours which can be succeed to approximated to a triangle is the triangular traffic signs, and other contours approximation which can be approximated to a ellipse with random least squares fitting is the circular traffic signs. The experimental results shows the detection rate reaches 86.79%, this algorithm can handle the adverse influence of traffic signs' deformation, occlusion better than hough method. It has better real-time performance and lower error detection rate than template method.