Probability distributions of optical flow

Eero P. Simoncelli; Edward H. Adelson; David J. Heeger

Probability distributions of optical flow

Eero P. Simoncelli, Edward H. Adelson, David J. Heeger

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit
Publisher	Publ by IEEE
Pages	310-315
Number of pages	6
ISBN (Print)	0818621486
State	Published - 1991
Event	Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Maui, HI Duration: Jun 3 1991 → Jun 6 1991

Publication series

Name	Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit

Other

Other	Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
City	Maui, HI
Period	6/3/91 → 6/6/91

ASJC Scopus subject areas

General Engineering

Cite this

@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 = "Simoncelli, {Eero P.} and Adelson, {Edward H.} and Heeger, {David J.}",

year = "1991",

language = "English (US)",

isbn = "0818621486",

series = "Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit",

publisher = "Publ by IEEE",

pages = "310--315",

booktitle = "Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit",

note = "Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition ; Conference date: 03-06-1991 Through 06-06-1991",

}

TY - GEN

T1 - Probability distributions of optical flow

AU - Simoncelli, Eero P.

AU - Adelson, Edward H.

AU - Heeger, David J.

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

AN - SCOPUS:0026404688

SN - 0818621486

T3 - Proc 91 IEEE Comput Soc Conf Comput Vision Pattern Recognit

SP - 310

EP - 315

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

PB - Publ by IEEE

T2 - Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Y2 - 3 June 1991 through 6 June 1991

ER -

Probability distributions of optical flow

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this