Color-based traffic sign detection

Author

Song, Lei ; Liu, Zheyuan

Author_Institution

Sch. of Autom., Northwestern Polytech. Univ., Xi´´an, China

fYear

2012

fDate

15-18 June 2012

Firstpage

353

Lastpage

357

Abstract

According to the characteristic of traffic signs, several color components are used to extract several kinds of traffic signs, which improved the detection efficiency in pre-processing. Then the regions of interest (ROI) are set not only to save process time but also to increase the accuracy of road recognition. Meanwhile the geometric characters of the road signs are represented by morphological skeleton based on which the decision tree is designed to classify road signs. The presented methods are tested on some complex traffic images which are captured under different weather conditions.

Keywords

decision trees; image classification; image colour analysis; mathematical morphology; traffic engineering computing; ROI; color-based traffic sign detection; decision tree; detection efficiency improvement; geometric characters; morphological skeleton; process time; region of interest; road recognition accuracy; road sign classification; traffic images; traffic sign extraction; weather conditions; Brightness; Feature extraction; Image color analysis; Roads; Robustness; Skeleton; Transforms; color space; decision tree; hough transfer; morphological skeleton; region of interest; traffic sign;

fLanguage

English

Publisher

ieee

Conference_Titel

Quality, Reliability, Risk, Maintenance, and Safety Engineering (ICQR2MSE), 2012 International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4673-0786-4

Type

conf

DOI

10.1109/ICQR2MSE.2012.6246253

Filename

6246253