A vision-aided vehicle driving system: establishment of a sign finder system

Author

Fann, Jeun-Hail ; Lee, Gang

Author_Institution

Dept. of Transp. Manage., Tamkang Univ., Taipei, Taiwan

fYear

1994

fDate

31 Aug-2 Sep 1994

Firstpage

33

Lastpage

38

Abstract

The purpose of this article is to build an automatic extraction and classification system for road sign images with color features. Median filtering technique is used to decrease the noises and increase the stability of the color characteristics. According to the color features of road signs, we establish four heuristic decision rules: the range of the hue, the fixed order of the intensity of RGB, the ratio of the intensity of RGB, and the range of the intensity of RGB. Experimental results have achieved a 93.3% correct rate. The system is proved to be successful in recognising the road signs for complex real highway environmental images

Keywords

automobiles; colour; computer vision; feature extraction; filtering theory; image classification; image colour analysis; navigation; RGB intensity; color feature extraction; heuristic decision rules; highway environment; hue range; image classification; median filtering; sign image recognition; vision-aided vehicle driving system; Color; Colored noise; Computer displays; Computer vision; Image edge detection; Image segmentation; Lighting; Pattern recognition; Road transportation; Vehicle driving;

fLanguage

English

Publisher

ieee

Conference_Titel

Vehicle Navigation and Information Systems Conference, 1994. Proceedings., 1994

Conference_Location

Yokohama

Print_ISBN

0-7803-2105-7

Type

conf

DOI

10.1109/VNIS.1994.396870

Filename

396870