By Topic

Validation of stereo matching for robot navigation

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

3 Author(s)
Jörgen Lidholm ; School of Innovation, Design and Engineering, Mälardalen University, Sweden ; Giacomo Spampinato ; Lars Asplund

This paper presents results from experiments on visual stereo matching for robot navigation. Visual features are stereo paired with respect to their pixel position. Stereo triangulating all paired visual features results in a set of landmarks whereof a subset are true landmarks. Constraining the horizontal disparity limits the amount of spurious matches. The stereo matching is validated by finding which landmarks survives short motions measured with a complementary navigation system, like odometry, thus transferring the stereo matching problem from two to three dimensional space and robot motion is estimated from the landmarks surviving the motion. The results from our experiments show that the spurious matching algorithm for stereo matching validation works and that the system is able to estimate the motion.

Published in:

2009 IEEE Conference on Emerging Technologies & Factory Automation

Date of Conference:

22-25 Sept. 2009