Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor Environments

Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, Michael Milford, K. Madhava Krishna

2021

Abstract

Significant recent advances have been made in Visual Place Recognition (VPR), feature correspondence and localization due to deep-learning-based methods. However, existing approaches tend to address, partially or fully, only one of two key challenges: viewpoint change and perceptual aliasing. In this paper, we present novel research that simultaneously addresses both challenges by combining deep-learnt features with geometric transformations based on domain knowledge about navigation on a ground-plane, without specialized hardware (e.g. downwards facing cameras, etc.). In particular, our integration of VPR with SLAM by leveraging the robustness of deep-learnt features and our homography-based extreme viewpoint invariance significantly boosts the performance of VPR, feature correspondence and pose graph sub-modules of the SLAM pipeline. We demonstrate a localization system capable of state-of-the-art performance despite perceptual aliasing and extreme 180-degree-rotated viewpoint change in a range of real-world and simulated experiments. Our system is able to achieve early loop closures that prevent significant drifts in SLAM trajectories.

Paper Citation

in Harvard Style

Tourani S., Desai D., Parihar U., Garg S., Sarvadevabhatla R., Milford M. and Krishna K. (2021). Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor Environments. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 409-416. DOI: 10.5220/0010230804090416

in Bibtex Style

@conference{visapp21,
author={Satyajit Tourani and Dhagash Desai and Udit Singh Parihar and Sourav Garg and Ravi Kiran Sarvadevabhatla and Michael Milford and K. Madhava Krishna},
title={Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor Environments},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={409-416},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010230804090416},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor Environments
SN - 978-989-758-488-6
AU - Tourani S.
AU - Desai D.
AU - Parihar U.
AU - Garg S.
AU - Sarvadevabhatla R.
AU - Milford M.
AU - Krishna K.
PY - 2021
SP - 409
EP - 416
DO - 10.5220/0010230804090416
PB - SciTePress