BirdSLAM: Monocular Multibody SLAM in Bird’s-eye View

Swapnil Daga, Gokul B. Nair, Anirudha Ramesh, Rahul Sajnani, Junaid Ahmed Ansari, K. Madhava Krishna

2021

Abstract

In this paper, we present BirdSLAM, a novel simultaneous localization and mapping (SLAM) system for the challenging scenario of autonomous driving platforms equipped with only a monocular camera. BirdSLAM tackles challenges faced by other monocular SLAM systems (such as scale ambiguity in monocular reconstruction, dynamic object localization, and uncertainty in feature representation) by using an orthographic (bird’s-eye) view as the configuration space in which localization and mapping are performed. By assuming only the height of the ego-camera above the ground, BirdSLAM leverages single-view metrology cues to accurately localize the ego-vehicle and all other traffic participants in bird’s-eye view. We demonstrate that our system outperforms prior work that uses strictly greater information, and highlight the relevance of each design decision via an ablation analysis.

Download


Paper Citation


in Harvard Style

Daga S., Nair G., Ramesh A., Sajnani R., Ansari J. and Krishna K. (2021). BirdSLAM: Monocular Multibody SLAM in Bird’s-eye View. 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 711-721. DOI: 10.5220/0010199907110721


in Bibtex Style

@conference{visapp21,
author={Swapnil Daga and Gokul B. Nair and Anirudha Ramesh and Rahul Sajnani and Junaid Ahmed Ansari and K. Madhava Krishna},
title={BirdSLAM: Monocular Multibody SLAM in Bird’s-eye View},
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={711-721},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010199907110721},
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 - BirdSLAM: Monocular Multibody SLAM in Bird’s-eye View
SN - 978-989-758-488-6
AU - Daga S.
AU - Nair G.
AU - Ramesh A.
AU - Sajnani R.
AU - Ansari J.
AU - Krishna K.
PY - 2021
SP - 711
EP - 721
DO - 10.5220/0010199907110721
PB - SciTePress