Unsupervised Domain Adaptation for 6DOF Indoor Localization

Daniele Di Mauro, Antonino Furnari, Giovanni Signorello, Giovanni Farinella

Abstract

Visual Localization is gathering more and more attention in computer vision due to the spread of wearable cameras (e.g. smart glasses) and to the increase of general interest in autonomous vehicles and robots. Unfortunately, current localization algorithms rely on large amounts of labeled training data collected in the specific target environment in which the system needs to work. Data collection and labeling in this context is difficult and time-consuming. Moreover, the process has to be repeated when the system is adapted to a new environment. In this work, we consider a scenario in which the target environment has been scanned to obtain a 3D model of the scene suitable to generate large quantities of synthetic data automatically paired with localization labels. We hence investigate the use of Unsupervised Domain Adaptation techniques exploiting labeled synthetic data and unlabeled real data to train localization algorithms. To carry out the study, we introduce a new dataset composed of synthetic and real images labeled with their 6-DOF poses collected in four different indoor rooms which is available at https://iplab.dmi.unict.it/EGO-CH-LOC-UDA. A new method based on self-supervision and attention modules is hence proposed and tested on the proposed dataset. Results show that our method improves over baselines and state-of-the-art algorithms tackling similar domain adaptation tasks.

Download


Paper Citation


in Harvard Style

Di Mauro D., Furnari A., Signorello G. and Farinella G. (2021). Unsupervised Domain Adaptation for 6DOF Indoor Localization.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 954-961. DOI: 10.5220/0010333409540961


in Bibtex Style

@conference{visapp21,
author={Daniele Di Mauro and Antonino Furnari and Giovanni Signorello and Giovanni Farinella},
title={Unsupervised Domain Adaptation for 6DOF Indoor Localization},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={954-961},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010333409540961},
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 - Volume 4: VISAPP,
TI - Unsupervised Domain Adaptation for 6DOF Indoor Localization
SN - 978-989-758-488-6
AU - Di Mauro D.
AU - Furnari A.
AU - Signorello G.
AU - Farinella G.
PY - 2021
SP - 954
EP - 961
DO - 10.5220/0010333409540961