A Method of Fast and Robust for Traffic Sign Recognition

Author

Yongping Wang ; Meiping Shi ; Tao Wu

Author_Institution

Dept. of Mechatron. Eng. & Autom., Nat. Univ. of Defense Technolgy, Changsha, China

fYear

2009

fDate

20-23 Sept. 2009

Firstpage

891

Lastpage

895

Abstract

This paper proposes a fast and robust algorithm for traffic sign detection and recognition. The algorithm includes two stages: traffic sign detection and recognition. In the first stage, Adaboost algorithm based red pixels model of speed limit sign in the Lab color space is built. Then the model is used to extract area of latent speed limit signs. After that, the improved Hough Transform is used to locate the signs precisely. In the second stage, the template matching algorithm is used to recognize the traffic sign. At the same time, a new method of rejecting non-signs is presented, which improved the recognition rate in the complex outdoor scenes.

Keywords

Hough transforms; character recognition; driver information systems; image colour analysis; image matching; image recognition; road traffic; Adaboost algorithm; Hough transform; Lab color space; red pixels model; speed limit signs; template matching algorithm; traffic sign detection; traffic sign recognition; Clustering algorithms; Color; Graphics; Image recognition; Information filtering; Information filters; Layout; Robustness; Telecommunication traffic; Traffic control; Hough transform; color filtering; context information; criterion of rejection; traffic sign;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Graphics, 2009. ICIG '09. Fifth International Conference on

Conference_Location

Xi´an, Shanxi

Print_ISBN

978-1-4244-5237-8

Type

conf

DOI

10.1109/ICIG.2009.130

Filename

5437873