ADVIO: An authentic dataset for visual-inertial odometry

TL;DR

This paper introduces ADVIO, a comprehensive and realistic dataset for pedestrian visual-inertial odometry, enabling better benchmarking of methods across diverse real-world scenarios using data from smartphones and AR devices.

Contribution

The paper presents a new versatile dataset with high-quality ground-truth and raw sensor data from multiple devices, covering indoor and outdoor environments for visual-inertial odometry research.

Findings

Comparison of visual-inertial tracking methods using the dataset

Demonstration of dataset's versatility across various environments

Benchmarking of existing methods on new challenging data

Abstract

The lack of realistic and open benchmarking datasets for pedestrian visual-inertial odometry has made it hard to pinpoint differences in published methods. Existing datasets either lack a full six degree-of-freedom ground-truth or are limited to small spaces with optical tracking systems. We take advantage of advances in pure inertial navigation, and develop a set of versatile and challenging real-world computer vision benchmark sets for visual-inertial odometry. For this purpose, we have built a test rig equipped with an iPhone, a Google Pixel Android phone, and a Google Tango device. We provide a wide range of raw sensor data that is accessible on almost any modern-day smartphone together with a high-quality ground-truth track. We also compare resulting visual-inertial tracks from Google Tango, ARCore, and Apple ARKit with two recent methods published in academic forums. The data sets cover both indoor and outdoor cases, with stairs, escalators, elevators, office environments, a shopping mall, and metro station.