A MRF approach to optical flow estimation

J. A. Vlontzos; D. Geiger

doi:10.1109/CVPR.1992.223240

A MRF approach to optical flow estimation

J. A. Vlontzos, D. Geiger

Computer Science

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

Abstract

A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established.

Original language	English (US)
Title of host publication	Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE Computer Society
Pages	853-856
Number of pages	4
ISBN (Electronic)	0818628553
DOIs	https://doi.org/10.1109/CVPR.1992.223240
State	Published - 1992
Event	1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992 - Champaign, United States Duration: Jun 15 1992 → Jun 18 1992

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	1992-June
ISSN (Print)	1063-6919

Conference

Conference	1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992
Country	United States
City	Champaign
Period	6/15/92 → 6/18/92

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.1992.223240

Fingerprint Dive into the research topics of 'A MRF approach to optical flow estimation'. Together they form a unique fingerprint.

Cite this

Vlontzos, J. A., & Geiger, D. (1992). A MRF approach to optical flow estimation. In Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 853-856). [223240] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1992-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.1992.223240

A MRF approach to optical flow estimation. / Vlontzos, J. A.; Geiger, D.

Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1992. p. 853-856 223240 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1992-June).

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

Vlontzos, JA & Geiger, D 1992, A MRF approach to optical flow estimation. in Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 223240, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1992-June, IEEE Computer Society, pp. 853-856, 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992, Champaign, United States, 6/15/92. https://doi.org/10.1109/CVPR.1992.223240

@inproceedings{6ee884b5d05d4c97b04c91f462be3d96,

title = "A MRF approach to optical flow estimation",

abstract = "A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established.",

author = "Vlontzos, {J. A.} and D. Geiger",

year = "1992",

doi = "10.1109/CVPR.1992.223240",

language = "English (US)",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "853--856",

booktitle = "Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

note = "1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992 ; Conference date: 15-06-1992 Through 18-06-1992",

}

TY - GEN

T1 - A MRF approach to optical flow estimation

AU - Vlontzos, J. A.

AU - Geiger, D.

PY - 1992

Y1 - 1992

N2 - A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established.

AB - A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established.

UR - http://www.scopus.com/inward/record.url?scp=84997280601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997280601&partnerID=8YFLogxK

U2 - 10.1109/CVPR.1992.223240

DO - 10.1109/CVPR.1992.223240

M3 - Conference contribution

AN - SCOPUS:84997280601

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 853

EP - 856

BT - Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE Computer Society

T2 - 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992

Y2 - 15 June 1992 through 18 June 1992

ER -