A MRF approach to optical flow estimation

J. A. Vlontzos, Davi Geiger

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish (US)
Title of host publicationProceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages853-856
Number of pages4
ISBN (Electronic)0818628553
DOIs
StatePublished - Jan 1 1992
Event1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992 - Champaign, United States
Duration: Jun 15 1992Jun 18 1992

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1992-June
ISSN (Print)1063-6919

Conference

Conference1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992
CountryUnited States
CityChampaign
Period6/15/926/18/92

Fingerprint

Optical flows

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

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, Davi.

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 proceedingConference 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
Vlontzos JA, Geiger D. A MRF approach to optical flow estimation. In 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). https://doi.org/10.1109/CVPR.1992.223240
Vlontzos, J. A. ; Geiger, Davi. / A MRF approach to optical flow estimation. Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1992. pp. 853-856 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{ebded30f3e7747ceb0a2ac60b84366e7,
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 Davi Geiger",
year = "1992",
month = "1",
day = "1",
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",

}

TY - GEN

T1 - A MRF approach to optical flow estimation

AU - Vlontzos, J. A.

AU - Geiger, Davi

PY - 1992/1/1

Y1 - 1992/1/1

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

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

ER -