Practical Auto-calibration for Spatial Scene-understanding from Crowdsourced Dashcamera Videos

Hemang Chawla, Matti Jukola, Shabbir Marzban, Elahe Arani, Bahram Zonooz

2021

Abstract

Spatial scene-understanding, including dense depth and ego-motion estimation, is an important problem in computer vision for autonomous vehicles and advanced driver assistance systems. Thus, it is beneficial to design perception modules that can utilize crowdsourced videos collected from arbitrary vehicular onboard or dashboard cameras. However, the intrinsic parameters corresponding to such cameras are often unknown or change over time. Typical manual calibration approaches require objects such as a chessboard or additional scene-specific information. On the other hand, automatic camera calibration does not have such requirements. Yet, the automatic calibration of dashboard cameras is challenging as forward and planar navigation results in critical motion sequences with reconstruction ambiguities. Structure reconstruction of complete visual- sequences that may contain tens of thousands of images is also computationally untenable. Here, we propose a system for practical monocular onboard camera auto-calibration from crowdsourced videos. We show the effectiveness of our proposed system on the KITTI raw, Oxford RobotCar, and the crowdsourced D2-City datasets in varying conditions. Finally, we demonstrate its application for accurate monocular dense depth and ego-motion estimation on uncalibrated videos.

Paper Citation

in Harvard Style

Chawla H., Jukola M., Marzban S., Arani E. and Zonooz B. (2021). Practical Auto-calibration for Spatial Scene-understanding from Crowdsourced Dashcamera Videos. 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 869-880. DOI: 10.5220/0010255808690880

in Bibtex Style

@conference{visapp21,
author={Hemang Chawla and Matti Jukola and Shabbir Marzban and Elahe Arani and Bahram Zonooz},
title={Practical Auto-calibration for Spatial Scene-understanding from Crowdsourced Dashcamera Videos},
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={869-880},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010255808690880},
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 - Practical Auto-calibration for Spatial Scene-understanding from Crowdsourced Dashcamera Videos
SN - 978-989-758-488-6
AU - Chawla H.
AU - Jukola M.
AU - Marzban S.
AU - Arani E.
AU - Zonooz B.
PY - 2021
SP - 869
EP - 880
DO - 10.5220/0010255808690880
PB - SciTePress