FIG Peer Review Journal

Back

Automated Traffic Sign Detection for Modern Driver Assitance Systems (3828)
Alexander Reiterer (Austria), Taher Hassan and Naser El-Sheimy (Canada)
Dr. Alexander Reiterer
Univ. Ass.
Vienna University of Technology
Institute of Geodesy and Geophysics
Research Group Engineering Geodesy
Gusshausstr. 27-29 / E128-3
Vienna
1040
Austria
 
Corresponding author Dr. Alexander Reiterer (email: alexander.reiterer[at]tuwien.ac.at, tel.: + 43 1 58801 12845)
 
[ abstract ] [ paper ] [ handouts ]
Published on the web 2010-01-14
Received 2009-11-19 / Accepted 2010-01-14
This paper is one of selection of papers published for the FIG Congress 2010 in Sydney, Australia and has undergone the FIG Peer Review Process.
FIG Congress 2010
ISBN 978-87-90907-87-7 ISSN 2308-3441
http://www.fig.net/resources/proceedings/fig_proceedings/fig2010/index.htm

Abstract
Modern Driver Assistance Systems (DAS) are required to assist, guide, and control vehicles on highways and city streets based on GPS, INS and map matching. They play an important role in the navigation of modern vehicles. Although a GPS-navigation system can be updated in view of the modifications of the roads, it does not include exhaustive information about the traffic signalization. It would be useful to signal to a driver at least some important traffic signs. This paper presents the basic concept of a new approach for the automated detection of traffic signs to be incorporated in DASs. The developed procedure is based on the well known Scale Invariant Feature Transform (SIFT) algorithm. The results of extensive testing on real data sets shows that the presented approach detects over 70% of traffic signs correctly.
 
Keywords: GNSS/GPS; Positioning; Driver Assistance System; Mobile Mapping System; Scale Invariant Feature Transform

Back