Globally Optimal Relative Pose Estimation with Gravity Prior
(2021) 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021- Abstract
- Smartphones, tablets and camera systems used, e.g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately. Using this additional information, the y-axes of the cameras can be aligned, reducing their relative orientation to a single degree-of-freedom. With this assumption, we propose a novel globally optimal solver, minimizing the algebraic error in the least squares sense, to estimate the relative pose in the over-determined case. Based on the epipolar constraint, we convert the optimization problem into solving two polynomials with only two unknowns. Also, a fast solver is proposed using the first-order approximation of the rotation. The proposed solvers are compared... (More)
- Smartphones, tablets and camera systems used, e.g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately. Using this additional information, the y-axes of the cameras can be aligned, reducing their relative orientation to a single degree-of-freedom. With this assumption, we propose a novel globally optimal solver, minimizing the algebraic error in the least squares sense, to estimate the relative pose in the over-determined case. Based on the epipolar constraint, we convert the optimization problem into solving two polynomials with only two unknowns. Also, a fast solver is proposed using the first-order approximation of the rotation. The proposed solvers are compared with the state-of-the-art ones on four real-world datasets with approx. 50000 image pairs in total. Moreover, we collected a dataset, by a smartphone, consisting of 10933 image pairs, gravity directions and ground truth 3D reconstructions. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/b468b126-838b-4fd3-8cb8-c4a173e21590
- author
- Ding, Yaqing LU ; Barath, Daniel ; Yang, Jian ; Kong, Hui and Kukelova, Zuzana
- publishing date
- 2021
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
- conference location
- Virtual, Online, United States
- conference dates
- 2021-06-19 - 2021-06-25
- external identifiers
-
- scopus:85121832015
- ISBN
- 978-1-6654-4510-8
- 978-1-6654-4509-2
- DOI
- 10.1109/CVPR46437.2021.00046
- language
- English
- LU publication?
- no
- id
- b468b126-838b-4fd3-8cb8-c4a173e21590
- date added to LUP
- 2022-09-08 10:22:54
- date last changed
- 2025-04-16 21:50:35
@inproceedings{b468b126-838b-4fd3-8cb8-c4a173e21590, abstract = {{Smartphones, tablets and camera systems used, e.g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately. Using this additional information, the y-axes of the cameras can be aligned, reducing their relative orientation to a single degree-of-freedom. With this assumption, we propose a novel globally optimal solver, minimizing the algebraic error in the least squares sense, to estimate the relative pose in the over-determined case. Based on the epipolar constraint, we convert the optimization problem into solving two polynomials with only two unknowns. Also, a fast solver is proposed using the first-order approximation of the rotation. The proposed solvers are compared with the state-of-the-art ones on four real-world datasets with approx. 50000 image pairs in total. Moreover, we collected a dataset, by a smartphone, consisting of 10933 image pairs, gravity directions and ground truth 3D reconstructions.}}, author = {{Ding, Yaqing and Barath, Daniel and Yang, Jian and Kong, Hui and Kukelova, Zuzana}}, booktitle = {{IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}}, isbn = {{978-1-6654-4510-8}}, language = {{eng}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Globally Optimal Relative Pose Estimation with Gravity Prior}}, url = {{http://dx.doi.org/10.1109/CVPR46437.2021.00046}}, doi = {{10.1109/CVPR46437.2021.00046}}, year = {{2021}}, }