Detail publikace

Camera Pose Estimation from Lines using Plücker Coordinates

PŘIBYL, B. ZEMČÍK, P. ČADÍK, M.

Originální název

Camera Pose Estimation from Lines using Plücker Coordinates

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Correspondences between 3D lines and their 2D images captured by a camera are often used to determine position and orientation of the camera in space. In this work, we propose a novel algebraic algorithm to estimate the camera pose. We parameterize 3D lines using Plücker coordinates that allow linear projection of the lines into the image. A line projection matrix is estimated using Linear Least Squares and the camera pose is then extracted from the matrix. An algebraic approach to handle mismatched line correspondences is also included. The proposed algorithm is an order of magnitude faster yet comparably accurate and robust to the state-of-the-art, it does not require initialization, and it yields only one solution. The described method requires at least 9 lines and is particularly suitable for scenarios with 25 and more lines, as also shown in the results. The Matlab code of the proposed method is available for download (http://www.fit.vutbr.cz/~ipribyl/prods.php.en?id=410).

Klíčová slova

Camera Pose Estimation, Plücker Coordinates, Linear Least Squares, Direct Linear Transformation, Algebraic Outlier Rejection

Autoři

PŘIBYL, B.; ZEMČÍK, P.; ČADÍK, M.

Rok RIV

2015

Vydáno

7. 9. 2015

Nakladatel

The British Machine Vision Association and Society for Pattern Recognition

Místo

Swansea

ISBN

978-1-901725-53-7

Kniha

Proceedings of the British Machine Vision Conference (BMVC 2015)

Strany od

1

Strany do

12

Strany počet

12

URL

BibTex

@inproceedings{BUT119789,
  author="Bronislav {Přibyl} and Pavel {Zemčík} and Martin {Čadík}",
  title="Camera Pose Estimation from Lines using Plücker Coordinates",
  booktitle="Proceedings of the British Machine Vision Conference (BMVC 2015)",
  year="2015",
  pages="1--12",
  publisher="The British Machine Vision Association and Society for Pattern Recognition",
  address="Swansea",
  doi="10.5244/C.29.45",
  isbn="978-1-901725-53-7",
  url="https://dx.doi.org/10.5244/C.29.45"
}

Dokumenty