How to Download
FRDR offers multiple ways to download datasets. Learn more in our documentation.
Multi-Session Visual SLAM for Illumination-Invariant Re-Localization in Indoor Environments
| Description: | For robots navigating using only a camera, illumination changes in indoor environments can cause re-localization failures during autonomous navigation. In this paper, a multi-session visual SLAM approach is presented to create a map made of multiple variations of the same locations in different illumination conditions. The multi-session map can then be used at any hour of the day for improved re-localization capability. The approach presented is independent of the visual features used, and this is demonstrated by comparing re-localization performance between multi-session maps created using the RTAB-Map library with SURF, SIFT, BRIEF, BRISK, KAZE, DAISY and SuperPoint visual features. The approach is tested on six mapping and six localization sessions recorded at 30 minute intervals during sunset using a Google Tango phone in a real apartment, which is the dataset provided here. This dataset has been used to evaluate the approach used in this paper: M. Labbé and F. Michaud, “Multi-Session Visual SLAM for Illumination-Invariant Re-Localization in Indoor Environments,” in Frontiers in Robotics and AI, vol. 9, 2022. |
| Notes: | IntRoLab: https://github.com/introlab/ |
| Authors: | Labbé, Mathieu; Université de Sherbrooke;  0000-0003-0778-5595 |
| Keywords: | Localization SLAM Visual SLAM Feature Matching Mobile Robotics |
| Field of Research: | Electrical engineering, computer engineering, and information engineering > Computer engineering > Computer engineering, not elsewhere classified
|
| Publication Date: | 2024-04-05 |
| Publisher: | Federated Research Data Repository / dépôt fédéré de données de recherche |
| Funder: | Natural Sciences and Engineering Research Council of Canada; RGPIN-2016-05096 Fonds de Recherche du Québec – Nature et Technologies INTER Strategic Network; 2020-RS4-265381, 2018-RS-203302 |
| URI: | https://doi.org/10.20383/103.0931 |
| Related Identifiers: |
This dataset is cited by
This dataset is supplemented by
|
Files in Dataset
No files uploaded
Download entire dataset using Globus Transfer. This method requires a Globus account and installing software. Watch Video: Get Started with FRDR: Download a Dataset
Files for this dataset are currently being backed up so it cannot be approved at this time. Please try later.
Access to this dataset is subject to the following terms:
Creative Commons Public Domain Dedication (CC0 1.0) https://creativecommons.org/publicdomain/zero/1.0/
Citation
Labbé, M. (2024). Multi-Session Visual SLAM for Illumination-Invariant Re-Localization in Indoor Environments. Federated Research Data Repository. https://doi.org/10.20383/103.0931
Footer Second
Footer Third
