A Direct Least-Squares Solution to Multi-View Absolute and Relative Pose from 2D-3D Perspective Line Pairs

Hichem Abdellali, Robert Frohlich, Zoltan Kato

ICCVW 2019 pp. 2119-2128

doi:10.1109/ICCVW.2019.00267 /iccvw/2019/abdellali2019iccvw-direct/

Abstract

We propose a new algorithm for estimating the absolute and relative pose of a multi-view camera system. We derive a direct least squares solver using Grobner basis which works both for the minimal case (set of 3 line pairs for each camera) and the general case using all inlier 2D-3D line pairs for a multi-view camera system. The algorithm has been validated on a large synthetic dataset as well as real data. Experimental results confirm the stable and real-time performance under realistic outlier ratio and noise on the line parameters. Comparative tests show that our method compares favorably to the latest state of the art algorithms.

ICCVW Semantic Scholar

Cite

Text

Abdellali et al. "A Direct Least-Squares Solution to Multi-View Absolute and Relative Pose from 2D-3D Perspective Line Pairs." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00267

Markdown

[Abdellali et al. "A Direct Least-Squares Solution to Multi-View Absolute and Relative Pose from 2D-3D Perspective Line Pairs." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/abdellali2019iccvw-direct/) doi:10.1109/ICCVW.2019.00267

BibTeX

@inproceedings{abdellali2019iccvw-direct,
  title     = {{A Direct Least-Squares Solution to Multi-View Absolute and Relative Pose from 2D-3D Perspective Line Pairs}},
  author    = {Abdellali, Hichem and Frohlich, Robert and Kato, Zoltan},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {2119-2128},
  doi       = {10.1109/ICCVW.2019.00267},
  url       = {https://mlanthology.org/iccvw/2019/abdellali2019iccvw-direct/}
}