Anisotropic fluid solver for robust optical flow smoothing

Ashish Doshi; Adrian G. Bors

doi:10.1109/WIAMIS.2009.5031446

Anisotropic fluid solver for robust optical flow smoothing

Ashish Doshi, Adrian G. Bors

Computer Science

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

Abstract

Computational fluid dynamics provides the framework for explaining fluid motion. The methodology proposed in this paper applies partial differential equations such as Navier-Stokes for modelling the optical flow in image sequences displaying complex motion. The proposed robust stable fluid solver has the following components: robust diffusion, advection and mass conservation. We employ a robust diffusion kernel which combines the geometry preserving property of the heat kernel with an outlier rejection mechanism. The proposed methodology is applied on the artificially generated Von Karman flows, after considering additive noise, and onto the optical flow extracted from real image sequences.

Original language	English
Title of host publication	2009 10TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES
Place of Publication	NEW YORK
Publisher	IEEE
Pages	117-120
Number of pages	4
ISBN (Print)	978-1-4244-3609-5
DOIs	https://doi.org/10.1109/WIAMIS.2009.5031446
Publication status	Published - 6 May 2009
Event	International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) - London, United Kingdom Duration: 6 May 2009 → 8 May 2009

Conference

Conference	International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)
Country/Territory	United Kingdom
Period	6/05/09 → 8/05/09

Access to Document

10.1109/WIAMIS.2009.5031446

Cite this

@inproceedings{8aa651821fc442b2ba9a5e32e5ae3a2d,

title = "Anisotropic fluid solver for robust optical flow smoothing",

abstract = "Computational fluid dynamics provides the framework for explaining fluid motion. The methodology proposed in this paper applies partial differential equations such as Navier-Stokes for modelling the optical flow in image sequences displaying complex motion. The proposed robust stable fluid solver has the following components: robust diffusion, advection and mass conservation. We employ a robust diffusion kernel which combines the geometry preserving property of the heat kernel with an outlier rejection mechanism. The proposed methodology is applied on the artificially generated Von Karman flows, after considering additive noise, and onto the optical flow extracted from real image sequences.",

author = "Ashish Doshi and Bors, {Adrian G.}",

year = "2009",

month = may,

day = "6",

doi = "10.1109/WIAMIS.2009.5031446",

language = "English",

isbn = "978-1-4244-3609-5",

pages = "117--120",

booktitle = "2009 10TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES",

publisher = "IEEE",

address = "United States",

note = "International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) ; Conference date: 06-05-2009 Through 08-05-2009",

}

TY - GEN

T1 - Anisotropic fluid solver for robust optical flow smoothing

AU - Doshi, Ashish

AU - Bors, Adrian G.

PY - 2009/5/6

Y1 - 2009/5/6

N2 - Computational fluid dynamics provides the framework for explaining fluid motion. The methodology proposed in this paper applies partial differential equations such as Navier-Stokes for modelling the optical flow in image sequences displaying complex motion. The proposed robust stable fluid solver has the following components: robust diffusion, advection and mass conservation. We employ a robust diffusion kernel which combines the geometry preserving property of the heat kernel with an outlier rejection mechanism. The proposed methodology is applied on the artificially generated Von Karman flows, after considering additive noise, and onto the optical flow extracted from real image sequences.

AB - Computational fluid dynamics provides the framework for explaining fluid motion. The methodology proposed in this paper applies partial differential equations such as Navier-Stokes for modelling the optical flow in image sequences displaying complex motion. The proposed robust stable fluid solver has the following components: robust diffusion, advection and mass conservation. We employ a robust diffusion kernel which combines the geometry preserving property of the heat kernel with an outlier rejection mechanism. The proposed methodology is applied on the artificially generated Von Karman flows, after considering additive noise, and onto the optical flow extracted from real image sequences.

U2 - 10.1109/WIAMIS.2009.5031446

DO - 10.1109/WIAMIS.2009.5031446

M3 - Conference contribution

SN - 978-1-4244-3609-5

SP - 117

EP - 120

BT - 2009 10TH INTERNATIONAL WORKSHOP ON IMAGE ANALYSIS FOR MULTIMEDIA INTERACTIVE SERVICES

PB - IEEE

CY - NEW YORK

T2 - International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)

Y2 - 6 May 2009 through 8 May 2009

ER -