Relative pose estimation in binocular vision for a planar scene using inter-image homographies

Marcus Valtonen Örnhag; Anders Heyden

doi:10.5220/0006695305680575

Relative pose estimation in binocular vision for a planar scene using inter-image homographies

Marcus Valtonen Örnhag, Anders Heyden

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

In this paper we consider a mobile platform with two cameras directed towards the floor mounted the same distance from the ground, assuming planar motion and constant internal parameters. Earlier work related to this specific problem geometry has been carried out for monocular systems, and the main contribution of this paper is the generalization to a binocular system and the recovery of the relative translation and orientation between the cameras. The method is based on previous work on monocular systems, using sequences of inter-image homographies. Experiments are conducted using synthetic data, and the results demonstrate a robust method for determining the relative parameters.

Original language	English
Title of host publication	ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods
Editors	Ana Fred, Gabriella Sanniti di Baja, Maria De Marsico
Publisher	SciTePress
Pages	568-575
Number of pages	8
Volume	2018-January
ISBN (Electronic)	9789897582769
DOIs	https://doi.org/10.5220/0006695305680575
Publication status	Published - 2018 Jan 1
Event	7th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2018 - Madeira, Funchal, Portugal Duration: 2018 Jan 16 → 2018 Jan 18

Conference

Conference	7th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2018
Abbreviated title	ICPRAM 2018
Country/Territory	Portugal
City	Funchal
Period	2018/01/16 → 2018/01/18

Subject classification (UKÄ)

Computer Vision and Robotics (Autonomous Systems)

Free keywords

Binocular Vision
Homography
Planar Motion
Relative Pose Estimation
SLAM
Visual Odometry

Access to Document

10.5220/0006695305680575

1 Doctoral Thesis (compilation)

Robust Estimation of Motion Parameters and Scene Geometry: Minimal Solvers and Convexification of Regularisers for Low-Rank Approximation
Valtonen Örnhag, M., 2021, Lund University, Faculty of Engineering. 387 p.
Research output: Thesis › Doctoral Thesis (compilation)

Open Access
File

Cite this

Örnhag, M. V., & Heyden, A. (2018). Relative pose estimation in binocular vision for a planar scene using inter-image homographies. In A. Fred, G. S. di Baja, & M. De Marsico (Eds.), ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods (Vol. 2018-January, pp. 568-575). SciTePress. https://doi.org/10.5220/0006695305680575

@inproceedings{cb9c14fa38f84afca4377797f6f821e3,

title = "Relative pose estimation in binocular vision for a planar scene using inter-image homographies",

abstract = "In this paper we consider a mobile platform with two cameras directed towards the floor mounted the same distance from the ground, assuming planar motion and constant internal parameters. Earlier work related to this specific problem geometry has been carried out for monocular systems, and the main contribution of this paper is the generalization to a binocular system and the recovery of the relative translation and orientation between the cameras. The method is based on previous work on monocular systems, using sequences of inter-image homographies. Experiments are conducted using synthetic data, and the results demonstrate a robust method for determining the relative parameters.",

keywords = "Binocular Vision, Homography, Planar Motion, Relative Pose Estimation, SLAM, Visual Odometry",

author = "{\"O}rnhag, {Marcus Valtonen} and Anders Heyden",

year = "2018",

month = jan,

day = "1",

doi = "10.5220/0006695305680575",

language = "English",

volume = "2018-January",

pages = "568--575",

editor = "Ana Fred and {di Baja}, {Gabriella Sanniti} and {De Marsico}, Maria",

booktitle = "ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods",

publisher = "SciTePress",

note = "7th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2018, ICPRAM 2018 ; Conference date: 16-01-2018 Through 18-01-2018",

}

Örnhag, MV & Heyden, A 2018, Relative pose estimation in binocular vision for a planar scene using inter-image homographies. in A Fred, GS di Baja & M De Marsico (eds), ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods. vol. 2018-January, SciTePress, pp. 568-575, 7th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2018, Funchal, Portugal, 2018/01/16. https://doi.org/10.5220/0006695305680575

Relative pose estimation in binocular vision for a planar scene using inter-image homographies. / Örnhag, Marcus Valtonen; Heyden, Anders.
ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods. ed. / Ana Fred; Gabriella Sanniti di Baja; Maria De Marsico. Vol. 2018-January SciTePress, 2018. p. 568-575.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Relative pose estimation in binocular vision for a planar scene using inter-image homographies

AU - Örnhag, Marcus Valtonen

AU - Heyden, Anders

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this paper we consider a mobile platform with two cameras directed towards the floor mounted the same distance from the ground, assuming planar motion and constant internal parameters. Earlier work related to this specific problem geometry has been carried out for monocular systems, and the main contribution of this paper is the generalization to a binocular system and the recovery of the relative translation and orientation between the cameras. The method is based on previous work on monocular systems, using sequences of inter-image homographies. Experiments are conducted using synthetic data, and the results demonstrate a robust method for determining the relative parameters.

AB - In this paper we consider a mobile platform with two cameras directed towards the floor mounted the same distance from the ground, assuming planar motion and constant internal parameters. Earlier work related to this specific problem geometry has been carried out for monocular systems, and the main contribution of this paper is the generalization to a binocular system and the recovery of the relative translation and orientation between the cameras. The method is based on previous work on monocular systems, using sequences of inter-image homographies. Experiments are conducted using synthetic data, and the results demonstrate a robust method for determining the relative parameters.

KW - Binocular Vision

KW - Homography

KW - Planar Motion

KW - Relative Pose Estimation

KW - SLAM

KW - Visual Odometry

U2 - 10.5220/0006695305680575

DO - 10.5220/0006695305680575

M3 - Paper in conference proceeding

AN - SCOPUS:85052013448

VL - 2018-January

SP - 568

EP - 575

BT - ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods

A2 - Fred, Ana

A2 - di Baja, Gabriella Sanniti

A2 - De Marsico, Maria

PB - SciTePress

T2 - 7th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2018

Y2 - 16 January 2018 through 18 January 2018

ER -

Relative pose estimation in binocular vision for a planar scene using inter-image homographies

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Research output

Robust Estimation of Motion Parameters and Scene Geometry: Minimal Solvers and Convexification of Regularisers for Low-Rank Approximation

Cite this