A Loosely-Coupled Approach for Metric Scale Estimation in Monocular Vision-Inertial Systems

TL;DR

This paper presents a flexible, loosely-coupled method for estimating metric scale in monocular vision-inertial systems, enhancing pose accuracy and rate by fusing inertial data with monocular odometry.

Contribution

It introduces a modular fusion approach that allows easy replacement of input components, improving metric scale estimation in monocular vision-inertial systems.

Findings

Improved metric scale estimation in UAV data sets.

Enhanced pose estimation rate and accuracy.

Flexible fusion framework adaptable to different inputs.

Abstract

In monocular vision systems, lack of knowledge about metric distances caused by the inherent scale ambiguity can be a strong limitation for some applications. We offer a method for fusing inertial measurements with monocular odometry or tracking to estimate metric distances in inertial-monocular systems and to increase the rate of pose estimates. As we performed the fusion in a loosely-coupled manner, each input block can be easily replaced with one's preference, which makes our method quite flexible. We experimented our method using the ORB-SLAM algorithm for the monocular tracking input and Euler forward integration to process the inertial measurements. We chose sets of data recorded on UAVs to design a suitable system for flying robots.