Recovery of epipolar geometry as a manifold fitting problem

Liran Goshen; Ilan Shimshoni; P. Anandan; Daniel Keren

doi:10.1109/iccv.2003.1238643

Recovery of epipolar geometry as a manifold fitting problem

Liran Goshen, Ilan Shimshoni, P. Anandan, Daniel Keren

Department of Computer Science

Research output: Contribution to journal › Conference article › peer-review

Abstract

The introduction of the joint image manifold allows to treat the problem of recovering camera motion and cpipolar geometry as the problem of fitting a manifold to the data measured in a stereo pair. The manifold has a singularity and boundary, therefore care must be taken when fitting it. This paper reviews the notion of joint image manifold, and how previous motion recovery methods can be viewed in its context, and then offers a new fitting method, which improves upon previous results, especially when the extent of the data and/or the motion are small.

Original language	English
Pages (from-to)	1321-1328
Number of pages	8
Journal	Proceedings of the IEEE International Conference on Computer Vision
Volume	2
DOIs	https://doi.org/10.1109/iccv.2003.1238643
State	Published - 2003
Event	NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION - Nice, France Duration: 13 Oct 2003 → 16 Oct 2003

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/iccv.2003.1238643

Cite this

@article{ce4dd3b2ebb84769a392a85941c337b9,

title = "Recovery of epipolar geometry as a manifold fitting problem",

abstract = "The introduction of the joint image manifold allows to treat the problem of recovering camera motion and cpipolar geometry as the problem of fitting a manifold to the data measured in a stereo pair. The manifold has a singularity and boundary, therefore care must be taken when fitting it. This paper reviews the notion of joint image manifold, and how previous motion recovery methods can be viewed in its context, and then offers a new fitting method, which improves upon previous results, especially when the extent of the data and/or the motion are small.",

author = "Liran Goshen and Ilan Shimshoni and P. Anandan and Daniel Keren",

year = "2003",

doi = "10.1109/iccv.2003.1238643",

language = "English",

volume = "2",

pages = "1321--1328",

journal = "Proceedings of the IEEE International Conference on Computer Vision",

issn = "1550-5499",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION ; Conference date: 13-10-2003 Through 16-10-2003",

}

TY - JOUR

T1 - Recovery of epipolar geometry as a manifold fitting problem

AU - Goshen, Liran

AU - Shimshoni, Ilan

AU - Anandan, P.

AU - Keren, Daniel

PY - 2003

Y1 - 2003

N2 - The introduction of the joint image manifold allows to treat the problem of recovering camera motion and cpipolar geometry as the problem of fitting a manifold to the data measured in a stereo pair. The manifold has a singularity and boundary, therefore care must be taken when fitting it. This paper reviews the notion of joint image manifold, and how previous motion recovery methods can be viewed in its context, and then offers a new fitting method, which improves upon previous results, especially when the extent of the data and/or the motion are small.

AB - The introduction of the joint image manifold allows to treat the problem of recovering camera motion and cpipolar geometry as the problem of fitting a manifold to the data measured in a stereo pair. The manifold has a singularity and boundary, therefore care must be taken when fitting it. This paper reviews the notion of joint image manifold, and how previous motion recovery methods can be viewed in its context, and then offers a new fitting method, which improves upon previous results, especially when the extent of the data and/or the motion are small.

UR - http://www.scopus.com/inward/record.url?scp=0345414474&partnerID=8YFLogxK

U2 - 10.1109/iccv.2003.1238643

DO - 10.1109/iccv.2003.1238643

M3 - Conference article

AN - SCOPUS:0345414474

SN - 1550-5499

VL - 2

SP - 1321

EP - 1328

JO - Proceedings of the IEEE International Conference on Computer Vision

JF - Proceedings of the IEEE International Conference on Computer Vision

T2 - NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION

Y2 - 13 October 2003 through 16 October 2003

ER -

Recovery of epipolar geometry as a manifold fitting problem

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this