PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation
Authors:
- Arno SolinASArno Solin
- Santiago CortesSCSantiago Cortes
- Esa RahtuEREsa Rahtu
- Juho KannalaJKJuho Kannala
- 1 March 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 616-625
Abstract
This paper presents a novel method for visual-inertial odometry. The method is based on an information fusion framework employing low-cost IMU sensors and the monocular camera in a standard smartphone. We formulate a sequential inference scheme, where the IMU drives the dynamical model and the camera frames are used in coupling trailing sequences of augmented poses. The novelty in the model is in taking into account all the cross-terms in the updates, thus propagating the inter-connected uncertainties throughout the model. Stronger coupling between the inertial and visual data sources leads to robustness against occlusion and feature-poor environments. We demonstrate results on data collected with an iPhone and provide comparisons against the Tango device and using the EuRoC data set.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Semi-direct visual odometry for a fisheye-stereo camera2016
- Direct visual-inertial odometry with stereo cameras2016
- Semi-direct EKF-based monocular visual-inertial odometry2015
- DT-SLAM: Deferred Triangulation for Robust SLAM2014
- Consistency Analysis and Improvement of Vision-aided Inertial NavigationIEEE Transactions on Robotics, 2014
- Live Metric 3D Reconstruction on Mobile Phones2013
- KinectFusion2011
- Scale Drift-Aware Large Scale Monocular SLAM2010
- Strapdown Inertial Navigation Technology2004
- A four-step camera calibration procedure with implicit image correction2002