Bias Compensation in Visual Odometry - Robotics Institute Carnegie Mellon University

Bias Compensation in Visual Odometry

Gijs Dubbelman and Brett Browning
Conference Paper, Proceedings of (IROS) IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2828 - 2835, October, 2012

Abstract

Empirical evidence shows that error growth in visual odometry is biased. A projective bias model is developed and its parameters are estimated offline from trajectories encompassing loops. The model is used online to compensate for bias and thereby significantly reduces error growth. We validate our approach with more than 25 km of stereo data collected in two very different urban environments from a moving vehicle. Our results demonstrate significant reduction in error, typically on the order of 50%, suggesting that our technique has significant applicability to deployed robot systems in GPS denied environments.

BibTeX

@conference{Dubbelman-2012-7621,
author = {Gijs Dubbelman and Brett Browning},
title = {Bias Compensation in Visual Odometry},
booktitle = {Proceedings of (IROS) IEEE/RSJ International Conference on Intelligent Robots and Systems},
year = {2012},
month = {October},
pages = {2828 - 2835},
keywords = {visual odometry, bias, stereo, autocalibration, recalibration},
}