ML Anthology

Line-Based Relative Pose Estimation

Ali Elqursh, Ahmed M. Elgammal
CVPR 2011 pp. 3049-3056
doi:10.1109/CVPR.2011.5995512 /cvpr/2011/elqursh2011cvpr-line/

Abstract

We present an algorithm for calibrated camera relative pose estimation from lines. Given three lines with two of the lines parallel and orthogonal to the third we can compute the relative rotation between two images. We can also compute the relative translation from two intersection points. We also present a framework in which such lines can be detected. We evaluate the performance of the algorithm using synthetic and real data. The intended use of the algorithm is with robust hypothesize-and-test frameworks such as RANSAC. Our approach is suitable for urban and indoor environments where most lines are either parallel or orthogonal to each other.

CVPR Semantic Scholar

Cite

Text

Elqursh and Elgammal. "Line-Based Relative Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995512

Markdown

[Elqursh and Elgammal. "Line-Based Relative Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/elqursh2011cvpr-line/) doi:10.1109/CVPR.2011.5995512

BibTeX

@inproceedings{elqursh2011cvpr-line,
  title     = {{Line-Based Relative Pose Estimation}},
  author    = {Elqursh, Ali and Elgammal, Ahmed M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {3049-3056},
  doi       = {10.1109/CVPR.2011.5995512},
  url       = {https://mlanthology.org/cvpr/2011/elqursh2011cvpr-line/}
}