¹Beijing Key Laboratory of Information Services Engineering, Beijing Union University, Beijing 100101, China.
²College of Information Technology, Beijing Union University, Beijing 100101, China.

---

Abstract—We propose an approach for detecting circular traffic signs from images degraded by motion blur recorded in natural scenes. The first step enhances the image using the Laplace algorithm. The second step converts the image color space and identifies circular traffic signs using an adaptive threshold segmentation algorithm. The final step detects the sign area by considering circular and area features. Our experiments demonstrated that the method is robust and adaptable.

Index Terms—Traffic sign, image segmentation, HSV space, adaptive threshold.

[PDF]

Cite: Qi Zhang, Ning He, Yue Chi, "Circular Traffic Sign Detection in Natural Scenes," Journal of Computers vol. 13, no. 1, pp. 69-76, 2018.