By Topic

Automatic Detection and Recognition of Traffic Signs using Geometric Structure Analysis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Vavilin Andrey ; Department of Electrical Engineering, University of Ulsan, Korea. ; Kang Hyun Jo

This paper proposes detection and recognition algorithm for restricting, warning and information road signs. Sign detection is based on color analysis. In actual, traffic signs have specific color information like red border for warning and restricting signs or blue background for information signs. However in images obtained by camera mounted in the car color information was changed due to lighting and weather conditions such as dark illumination, rainy and foggy weather etc. To solve that problem we use RGB color segmentation with two restriction rules: first rule is bounding constraints for each color component which provides good detection results in images with good lighting condition; second rule is using normalized color information and allows sign detection in dark images. Structure of information signs is differs from structure of warning and restricting signs hence recognition process is also different. The meaning of traffic sign lies in shape of symbols inside of it. Recognition process is based on shape analysis. For warning and restricted signs recognition process consists of two stages. We extract sign candidate from image and classify sign as a circle or triangle using background shape histograms. Then we convert the inner part of sign into binary mask and apply template matching algorithm. To understand the meaning of information sign we separate it into basic components: arrows and text, and then analyze positional relationship between those segments. Detection of arrowheads is based on morphological operations such and analysis of spatial features like area and direction. Result of recognition is name of sign for warning and restricting signs and set of pairs direction - place for information signs

Published in:

2006 SICE-ICASE International Joint Conference

Date of Conference:

18-21 Oct. 2006