Real-Time RGBD Odometry for Fused-State Navigation Systems

TL;DR

This paper introduces a real-time RGBD odometry algorithm that estimates both motion and covariance, enhancing the fusion of odometry data in navigation systems, with demonstrated accuracy against ground truth.

Contribution

It provides the first real-time RGBD odometry method that includes covariance estimation, improving localization accuracy in navigation systems.

Findings

Accurate real-time odometry estimates validated against motion capture data.

Covariance estimates effectively characterize measurement uncertainty.

Method enhances sensor fusion in navigation applications.

Abstract

This article describes an algorithm that provides visual odometry estimates from sequential pairs of RGBD images. The key contribution of this article on RGBD odometry is that it provides both an odometry estimate and a covariance for the odometry parameters in real-time via a representative covariance matrix. Accurate, real-time parameter covariance is essential to effectively fuse odometry measurements into most navigation systems. To date, this topic has seen little treatment in research which limits the impact existing RGBD odometry approaches have for localization in these systems. Covariance estimates are obtained via a statistical perturbation approach motivated by real-world models of RGBD sensor measurement noise. Results discuss the accuracy of our RGBD odometry approach with respect to ground truth obtained from a motion capture system and characterizes the suitability of this approach for estimating the true RGBD odometry parameter uncertainty.