Vision method of vehicle localization based on the roadside landmark

Yi-xue Wang; Ying-wei Zhao; Xing-shu Wang; Zhi-guang Xu

doi:10.1117/12.2512032

7 November 2018 Vision method of vehicle localization based on the roadside landmark

Yi-xue Wang, Ying-wei Zhao, Xing-shu Wang, Zhi-guang Xu

Proceedings Volume 10832, Fifth Conference on Frontiers in Optical Imaging Technology and Applications; 108321U (2018) https://doi.org/10.1117/12.2512032
Event: Fifth Conference on Frontiers in Optical Imaging Technology and Applications, 2018, Changchun, China

Abstract

A visual localization method based on roadside landmarks is proposed in this paper. This method uses a single image obtained by a high-speed camera fixed on the top of the vehicle to accomplish real-time positioning. The information and characteristics of roadside landmarks is extracted and recognized from the image obtained. The distance between landmark and camera optical center is calculated according to the shape of the landmark. Finally, the vehicle position is calculated with the distance and the landmark database, which contains the characteristics and position of the landmark. Static and dynamic experiments are carried out and the results demonstrate that the proposed method can achieve vehicle positioning. Under the condition of an actual distance is below 40 m, the average positioning error is below 1m.

Citation Download Citation

Yi-xue Wang, Ying-wei Zhao, Xing-shu Wang, and Zhi-guang Xu "Vision method of vehicle localization based on the roadside landmark", Proc. SPIE 10832, Fifth Conference on Frontiers in Optical Imaging Technology and Applications, 108321U (7 November 2018); https://doi.org/10.1117/12.2512032

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available