Stochastic models for DIV-CURL optical flow methods

Sandeep N. Gupta, Jerry Ladd Prince

Research output: Contribution to journalArticle

Abstract

In this letter, we consider Suter's DIV-CURL optical flow methods, wherein the problem of computing a velocity field from an image sequence is regularized using smoothness conditions based on the divergence and curl of the field. In particular, we develop stochastic formulations of DIV-CURL splines using the linear smoothing theory of Adams, Willsky, and Levy. Our models are shown to be well posed and thus can be used in both simulating and estimating velocity fields having known stochastic properties. As a special case, our stochastic model reduces to that developed by Rougee, Levy, and Willsky for the classical Horn and Schunck's optical flow.

Original languageEnglish (US)
Pages (from-to)32-34
Number of pages3
JournalIEEE Signal Processing Letters
Volume3
Issue number2
DOIs
StatePublished - Feb 1996

Fingerprint

Optical flows
Optical Flow
Stochastic models
Velocity Field
Stochastic Model
Curl
Image Sequence
Splines
Spline
Smoothing
Smoothness
Divergence
Formulation
Computing
Model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing

Cite this

Stochastic models for DIV-CURL optical flow methods. / Gupta, Sandeep N.; Prince, Jerry Ladd.

In: IEEE Signal Processing Letters, Vol. 3, No. 2, 02.1996, p. 32-34.

Research output: Contribution to journalArticle

@article{4c0c834be2b4475298f7afc4c51f9409,
title = "Stochastic models for DIV-CURL optical flow methods",
abstract = "In this letter, we consider Suter's DIV-CURL optical flow methods, wherein the problem of computing a velocity field from an image sequence is regularized using smoothness conditions based on the divergence and curl of the field. In particular, we develop stochastic formulations of DIV-CURL splines using the linear smoothing theory of Adams, Willsky, and Levy. Our models are shown to be well posed and thus can be used in both simulating and estimating velocity fields having known stochastic properties. As a special case, our stochastic model reduces to that developed by Rougee, Levy, and Willsky for the classical Horn and Schunck's optical flow.",
author = "Gupta, {Sandeep N.} and Prince, {Jerry Ladd}",
year = "1996",
month = "2",
doi = "10.1109/97.484208",
language = "English (US)",
volume = "3",
pages = "32--34",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Stochastic models for DIV-CURL optical flow methods

AU - Gupta, Sandeep N.

AU - Prince, Jerry Ladd

PY - 1996/2

Y1 - 1996/2

N2 - In this letter, we consider Suter's DIV-CURL optical flow methods, wherein the problem of computing a velocity field from an image sequence is regularized using smoothness conditions based on the divergence and curl of the field. In particular, we develop stochastic formulations of DIV-CURL splines using the linear smoothing theory of Adams, Willsky, and Levy. Our models are shown to be well posed and thus can be used in both simulating and estimating velocity fields having known stochastic properties. As a special case, our stochastic model reduces to that developed by Rougee, Levy, and Willsky for the classical Horn and Schunck's optical flow.

AB - In this letter, we consider Suter's DIV-CURL optical flow methods, wherein the problem of computing a velocity field from an image sequence is regularized using smoothness conditions based on the divergence and curl of the field. In particular, we develop stochastic formulations of DIV-CURL splines using the linear smoothing theory of Adams, Willsky, and Levy. Our models are shown to be well posed and thus can be used in both simulating and estimating velocity fields having known stochastic properties. As a special case, our stochastic model reduces to that developed by Rougee, Levy, and Willsky for the classical Horn and Schunck's optical flow.

UR - http://www.scopus.com/inward/record.url?scp=0030085909&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030085909&partnerID=8YFLogxK

U2 - 10.1109/97.484208

DO - 10.1109/97.484208

M3 - Article

VL - 3

SP - 32

EP - 34

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 2

ER -