Probability distributions of optical flow

Eero Simoncelli, Edward H. Adelson, David Heeger

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Gradient methods are widely used in the computation of optical flow. The authors discuss extensions of these methods which compute probability distributions of optical flow. The use of distributions allows representation of the uncertainties inherent in the optical flow computation, facilitating the combination with information from other sources. Distributed optical flow for a synthetic image sequence is computed, and it is demonstrated that the probabilistic model accounts for the errors in the flow estimates. The distributed optical flow for a real image sequence is computed.

Original languageEnglish (US)
Title of host publicationProc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit
PublisherPubl by IEEE
Pages310-315
Number of pages6
ISBN (Print)0818621486
StatePublished - 1991
EventProceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Maui, HI
Duration: Jun 3 1991Jun 6 1991

Other

OtherProceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CityMaui, HI
Period6/3/916/6/91

Fingerprint

Optical flows
Probability distributions
Gradient methods

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Simoncelli, E., Adelson, E. H., & Heeger, D. (1991). Probability distributions of optical flow. In Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit (pp. 310-315). Publ by IEEE.

Probability distributions of optical flow. / Simoncelli, Eero; Adelson, Edward H.; Heeger, David.

Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit. Publ by IEEE, 1991. p. 310-315.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Simoncelli, E, Adelson, EH & Heeger, D 1991, Probability distributions of optical flow. in Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit. Publ by IEEE, pp. 310-315, Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Maui, HI, 6/3/91.
Simoncelli E, Adelson EH, Heeger D. Probability distributions of optical flow. In Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit. Publ by IEEE. 1991. p. 310-315
Simoncelli, Eero ; Adelson, Edward H. ; Heeger, David. / Probability distributions of optical flow. Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit. Publ by IEEE, 1991. pp. 310-315
@inproceedings{f56b53253f63421b9b212ce6859b38fb,
title = "Probability distributions of optical flow",
abstract = "Gradient methods are widely used in the computation of optical flow. The authors discuss extensions of these methods which compute probability distributions of optical flow. The use of distributions allows representation of the uncertainties inherent in the optical flow computation, facilitating the combination with information from other sources. Distributed optical flow for a synthetic image sequence is computed, and it is demonstrated that the probabilistic model accounts for the errors in the flow estimates. The distributed optical flow for a real image sequence is computed.",
author = "Eero Simoncelli and Adelson, {Edward H.} and David Heeger",
year = "1991",
language = "English (US)",
isbn = "0818621486",
pages = "310--315",
booktitle = "Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Probability distributions of optical flow

AU - Simoncelli, Eero

AU - Adelson, Edward H.

AU - Heeger, David

PY - 1991

Y1 - 1991

N2 - Gradient methods are widely used in the computation of optical flow. The authors discuss extensions of these methods which compute probability distributions of optical flow. The use of distributions allows representation of the uncertainties inherent in the optical flow computation, facilitating the combination with information from other sources. Distributed optical flow for a synthetic image sequence is computed, and it is demonstrated that the probabilistic model accounts for the errors in the flow estimates. The distributed optical flow for a real image sequence is computed.

AB - Gradient methods are widely used in the computation of optical flow. The authors discuss extensions of these methods which compute probability distributions of optical flow. The use of distributions allows representation of the uncertainties inherent in the optical flow computation, facilitating the combination with information from other sources. Distributed optical flow for a synthetic image sequence is computed, and it is demonstrated that the probabilistic model accounts for the errors in the flow estimates. The distributed optical flow for a real image sequence is computed.

UR - http://www.scopus.com/inward/record.url?scp=0026404688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026404688&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818621486

SP - 310

EP - 315

BT - Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit

PB - Publ by IEEE

ER -