Monocular vision for intelligent wheelchair indoor navigation based on natural landmark matching

Xiaodong Xu; Yuan Luo; Weixi Kong

doi:10.1117/12.885245

31 December 2010 Monocular vision for intelligent wheelchair indoor navigation based on natural landmark matching

Xiaodong Xu, Yuan Luo, Weixi Kong

Proceedings Volume 7544, Sixth International Symposium on Precision Engineering Measurements and Instrumentation; 75443F (2010) https://doi.org/10.1117/12.885245
Event: Sixth International Symposium on Precision Engineering Measurements and Instrumentation, 2010, Hangzhou, China

Abstract

This paper presents a real-time navigation system in a behavior-based manner. We show that autonomous navigation is possible in different rooms with the use of a single camera and natural landmarks. Firstly the intelligent wheelchair is manually guided on a path passing through different rooms and a video sequence is recorded with a front-facing camera. A 3D structure map is then gotten from this learning sequence by calculating the natural landmarks. Finally, the intelligent wheelchair uses this map to compute its localization and it follows the learning path or a slightly different path to achieve the real-time navigation. Experimental results indicate that this method is effective even when the viewpoint and scale is changed.

Citation Download Citation

Xiaodong Xu, Yuan Luo, and Weixi Kong "Monocular vision for intelligent wheelchair indoor navigation based on natural landmark matching", Proc. SPIE 7544, Sixth International Symposium on Precision Engineering Measurements and Instrumentation, 75443F (31 December 2010); https://doi.org/10.1117/12.885245

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