Optimal estimation of vanishing points in a Manhattan world

Faraz M. Mirzaei; Stergios I. Roumeliotis

doi:10.1109/ICCV.2011.6126530

Optimal estimation of vanishing points in a Manhattan world

Faraz M. Mirzaei, Stergios I. Roumeliotis

Computer Science and Engineering

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

89 Scopus citations

Abstract

In this paper, we present an analytical method for computing the globally optimal estimates of orthogonal vanishing points in a "Manhattan world" with a calibrated camera. We formulate this as constrained least-squares problem whose optimality conditions form a multivariate polynomial system. We solve this system analytically to compute all the critical points of the least-squares cost function, and hence the global minimum, i.e., the globally optimal estimate for the orthogonal vanishing points. The same optimal estimator is used in conjunction with RANSAC to generate orthogonal-vanishing- point hypotheses (from triplets of lines) and thus classify lines into parallel and mutually orthogonal groups. The proposed method is validated experimentally on the York Urban Database.

Original language	English (US)
Title of host publication	2011 International Conference on Computer Vision, ICCV 2011
Pages	2454-2461
Number of pages	8
DOIs	https://doi.org/10.1109/ICCV.2011.6126530
State	Published - 2011
Event	2011 IEEE International Conference on Computer Vision, ICCV 2011 - Barcelona, Spain Duration: Nov 6 2011 → Nov 13 2011

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision

Other

Other	2011 IEEE International Conference on Computer Vision, ICCV 2011
Country/Territory	Spain
City	Barcelona
Period	11/6/11 → 11/13/11

Publisher link

10.1109/ICCV.2011.6126530

Find It

Find It at U of M Libraries

Cite this

Mirzaei, FM & Roumeliotis, SI 2011, Optimal estimation of vanishing points in a Manhattan world. in 2011 International Conference on Computer Vision, ICCV 2011., 6126530, Proceedings of the IEEE International Conference on Computer Vision, pp. 2454-2461, 2011 IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, 11/6/11. https://doi.org/10.1109/ICCV.2011.6126530

@inproceedings{2952540ede5f4b5a97cf284c16a3ddbf,

title = "Optimal estimation of vanishing points in a Manhattan world",

abstract = "In this paper, we present an analytical method for computing the globally optimal estimates of orthogonal vanishing points in a {"}Manhattan world{"} with a calibrated camera. We formulate this as constrained least-squares problem whose optimality conditions form a multivariate polynomial system. We solve this system analytically to compute all the critical points of the least-squares cost function, and hence the global minimum, i.e., the globally optimal estimate for the orthogonal vanishing points. The same optimal estimator is used in conjunction with RANSAC to generate orthogonal-vanishing- point hypotheses (from triplets of lines) and thus classify lines into parallel and mutually orthogonal groups. The proposed method is validated experimentally on the York Urban Database.",

author = "Mirzaei, {Faraz M.} and Roumeliotis, {Stergios I.}",

year = "2011",

doi = "10.1109/ICCV.2011.6126530",

language = "English (US)",

isbn = "9781457711015",

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

pages = "2454--2461",

booktitle = "2011 International Conference on Computer Vision, ICCV 2011",

}

TY - GEN

T1 - Optimal estimation of vanishing points in a Manhattan world

AU - Mirzaei, Faraz M.

AU - Roumeliotis, Stergios I.

PY - 2011

Y1 - 2011

N2 - In this paper, we present an analytical method for computing the globally optimal estimates of orthogonal vanishing points in a "Manhattan world" with a calibrated camera. We formulate this as constrained least-squares problem whose optimality conditions form a multivariate polynomial system. We solve this system analytically to compute all the critical points of the least-squares cost function, and hence the global minimum, i.e., the globally optimal estimate for the orthogonal vanishing points. The same optimal estimator is used in conjunction with RANSAC to generate orthogonal-vanishing- point hypotheses (from triplets of lines) and thus classify lines into parallel and mutually orthogonal groups. The proposed method is validated experimentally on the York Urban Database.

AB - In this paper, we present an analytical method for computing the globally optimal estimates of orthogonal vanishing points in a "Manhattan world" with a calibrated camera. We formulate this as constrained least-squares problem whose optimality conditions form a multivariate polynomial system. We solve this system analytically to compute all the critical points of the least-squares cost function, and hence the global minimum, i.e., the globally optimal estimate for the orthogonal vanishing points. The same optimal estimator is used in conjunction with RANSAC to generate orthogonal-vanishing- point hypotheses (from triplets of lines) and thus classify lines into parallel and mutually orthogonal groups. The proposed method is validated experimentally on the York Urban Database.

UR - http://www.scopus.com/inward/record.url?scp=84856682649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856682649&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2011.6126530

DO - 10.1109/ICCV.2011.6126530

M3 - Conference contribution

AN - SCOPUS:84856682649

SN - 9781457711015

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2454

EP - 2461

BT - 2011 International Conference on Computer Vision, ICCV 2011

T2 - 2011 IEEE International Conference on Computer Vision, ICCV 2011

Y2 - 6 November 2011 through 13 November 2011

ER -

Optimal estimation of vanishing points in a Manhattan world

Abstract

Publication series

Other

Publisher link

Find It

Other files and links

Fingerprint

Cite this