A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold

Michel Sarkis; Klaus Diepold; Knut Hüper

doi:10.1109/ICASSP.2007.365999

A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold

Michel Sarkis, Klaus Diepold, Knut Hüper

Chair of Data Processing

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

16 Scopus citations

Abstract

Extracting the motion parameters of a moving camera is an important issue in computer vision. This is due to the need of numerous emerging applications like telepresence and robot navigation. The key issue is to determine a robust estimate of the (3×3) essential matrix with its five degrees of freedom. In this work, a robust technique to compute the essential matrix is suggested under the assumption that the images are calibrated. The algorithm is a combination of the five-point relative pose problem using an optimization technique on a manifold, with the random sample consensus. The results show that the proposed, method delivers faster and more accurate results than the standard techniques.

Original language	English
Title of host publication	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Pages	I681-I684
DOIs	https://doi.org/10.1109/ICASSP.2007.365999
State	Published - 2007
Event	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, United States Duration: 15 Apr 2007 → 20 Apr 2007

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	1
ISSN (Print)	1520-6149

Conference

Conference	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Country/Territory	United States
City	Honolulu, HI
Period	15/04/07 → 20/04/07

Keywords

Differential geometry
Iterative methods
Machine vision

Access to Document

10.1109/ICASSP.2007.365999

Cite this

Sarkis, M., Diepold, K., & Hüper, K. (2007). A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 (pp. I681-I684). Article 4217171 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 1). https://doi.org/10.1109/ICASSP.2007.365999

Sarkis, Michel ; Diepold, Klaus ; Hüper, Knut. / A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold. 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. 2007. pp. I681-I684 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{7aec989a43a848fd96cb69649d64b77f,

title = "A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold",

abstract = "Extracting the motion parameters of a moving camera is an important issue in computer vision. This is due to the need of numerous emerging applications like telepresence and robot navigation. The key issue is to determine a robust estimate of the (3×3) essential matrix with its five degrees of freedom. In this work, a robust technique to compute the essential matrix is suggested under the assumption that the images are calibrated. The algorithm is a combination of the five-point relative pose problem using an optimization technique on a manifold, with the random sample consensus. The results show that the proposed, method delivers faster and more accurate results than the standard techniques.",

keywords = "Differential geometry, Iterative methods, Machine vision",

author = "Michel Sarkis and Klaus Diepold and Knut H{\"u}per",

year = "2007",

doi = "10.1109/ICASSP.2007.365999",

language = "English",

isbn = "1424407281",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "I681--I684",

booktitle = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07",

note = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 ; Conference date: 15-04-2007 Through 20-04-2007",

}

Sarkis, M, Diepold, K & Hüper, K 2007, A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold. in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07., 4217171, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 1, pp. I681-I684, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, Honolulu, HI, United States, 15/04/07. https://doi.org/10.1109/ICASSP.2007.365999

A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold. / Sarkis, Michel; Diepold, Klaus; Hüper, Knut.
2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. 2007. p. I681-I684 4217171 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 1).

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

TY - GEN

T1 - A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold

AU - Sarkis, Michel

AU - Diepold, Klaus

AU - Hüper, Knut

PY - 2007

Y1 - 2007

N2 - Extracting the motion parameters of a moving camera is an important issue in computer vision. This is due to the need of numerous emerging applications like telepresence and robot navigation. The key issue is to determine a robust estimate of the (3×3) essential matrix with its five degrees of freedom. In this work, a robust technique to compute the essential matrix is suggested under the assumption that the images are calibrated. The algorithm is a combination of the five-point relative pose problem using an optimization technique on a manifold, with the random sample consensus. The results show that the proposed, method delivers faster and more accurate results than the standard techniques.

AB - Extracting the motion parameters of a moving camera is an important issue in computer vision. This is due to the need of numerous emerging applications like telepresence and robot navigation. The key issue is to determine a robust estimate of the (3×3) essential matrix with its five degrees of freedom. In this work, a robust technique to compute the essential matrix is suggested under the assumption that the images are calibrated. The algorithm is a combination of the five-point relative pose problem using an optimization technique on a manifold, with the random sample consensus. The results show that the proposed, method delivers faster and more accurate results than the standard techniques.

KW - Differential geometry

KW - Iterative methods

KW - Machine vision

UR - http://www.scopus.com/inward/record.url?scp=34547525087&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2007.365999

DO - 10.1109/ICASSP.2007.365999

M3 - Conference contribution

AN - SCOPUS:34547525087

SN - 1424407281

SN - 9781424407286

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - I681-I684

BT - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

T2 - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

Y2 - 15 April 2007 through 20 April 2007

ER -

Sarkis M, Diepold K, Hüper K. A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. 2007. p. I681-I684. 4217171. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2007.365999

A fast and robust solution to the five-point relative pose problem using Gauss-newton optimization on a manifold

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this