An Implementation of Combined Local-Global Optical Flow

Optical Flow (OF) approaches for motion estimation calculate vector fields for the apparent velocities of objects in image sequences. In 1981 Horn and Schunck (HS) introduced two basic assumptions: 'brightness value constancy' and 'smooth variation' to estimate a smooth OF field...

Full description

Bibliographic Details
Main Authors: Jorge Jara-Wilde, Mauricio Cerda, José Delpiano, Steffen Härtel
Format: Article
Language:English
Published: Image Processing On Line 2015-06-01
Series:Image Processing On Line
Online Access:http://www.ipol.im/pub/art/2015/44/
_version_ 1819266788577247232
author Jorge Jara-Wilde
Mauricio Cerda
José Delpiano
Steffen Härtel
author_facet Jorge Jara-Wilde
Mauricio Cerda
José Delpiano
Steffen Härtel
author_sort Jorge Jara-Wilde
collection DOAJ
description Optical Flow (OF) approaches for motion estimation calculate vector fields for the apparent velocities of objects in image sequences. In 1981 Horn and Schunck (HS) introduced two basic assumptions: 'brightness value constancy' and 'smooth variation' to estimate a smooth OF field over the entire image -global approach-. In parallel, Lucas and Kanade (LK) assumed constant motion patterns for image patches, estimating piecewise-homogeneous OF fields -local approach-. Several variations of these approaches exist today. Here we present the combined local-global (CLG) approach by Bruhn et al. which encompasses properties of HS-OF and LK-OF, aiming to improve the OF accuracy for small-scale variations, while delivering the HS-OF dense and smooth fields. A multiscale implementation is provided for 2D images, together with two numerical solvers: Successive Over-Relaxation and the faster Pointwise-Coupled Gauss-Seidel by Bruhn et al.. The algorithm works on gray-scale (single channel) images, with color images being converted prior to the OF computation.
first_indexed 2024-12-23T21:06:50Z
format Article
id doaj.art-5f85e39116b14ebb9ec2352dec0812c5
institution Directory Open Access Journal
issn 2105-1232
language English
last_indexed 2024-12-23T21:06:50Z
publishDate 2015-06-01
publisher Image Processing On Line
record_format Article
series Image Processing On Line
spelling doaj.art-5f85e39116b14ebb9ec2352dec0812c52022-12-21T17:31:12ZengImage Processing On LineImage Processing On Line2105-12322015-06-01513915810.5201/ipol.2015.44An Implementation of Combined Local-Global Optical FlowJorge Jara-Wilde Mauricio CerdaJosé DelpianoSteffen HärtelOptical Flow (OF) approaches for motion estimation calculate vector fields for the apparent velocities of objects in image sequences. In 1981 Horn and Schunck (HS) introduced two basic assumptions: 'brightness value constancy' and 'smooth variation' to estimate a smooth OF field over the entire image -global approach-. In parallel, Lucas and Kanade (LK) assumed constant motion patterns for image patches, estimating piecewise-homogeneous OF fields -local approach-. Several variations of these approaches exist today. Here we present the combined local-global (CLG) approach by Bruhn et al. which encompasses properties of HS-OF and LK-OF, aiming to improve the OF accuracy for small-scale variations, while delivering the HS-OF dense and smooth fields. A multiscale implementation is provided for 2D images, together with two numerical solvers: Successive Over-Relaxation and the faster Pointwise-Coupled Gauss-Seidel by Bruhn et al.. The algorithm works on gray-scale (single channel) images, with color images being converted prior to the OF computation.http://www.ipol.im/pub/art/2015/44/
spellingShingle Jorge Jara-Wilde
Mauricio Cerda
José Delpiano
Steffen Härtel
An Implementation of Combined Local-Global Optical Flow
Image Processing On Line
title An Implementation of Combined Local-Global Optical Flow
title_full An Implementation of Combined Local-Global Optical Flow
title_fullStr An Implementation of Combined Local-Global Optical Flow
title_full_unstemmed An Implementation of Combined Local-Global Optical Flow
title_short An Implementation of Combined Local-Global Optical Flow
title_sort implementation of combined local global optical flow
url http://www.ipol.im/pub/art/2015/44/
work_keys_str_mv AT jorgejarawilde animplementationofcombinedlocalglobalopticalflow
AT mauriciocerda animplementationofcombinedlocalglobalopticalflow
AT josedelpiano animplementationofcombinedlocalglobalopticalflow
AT steffenhartel animplementationofcombinedlocalglobalopticalflow
AT jorgejarawilde implementationofcombinedlocalglobalopticalflow
AT mauriciocerda implementationofcombinedlocalglobalopticalflow
AT josedelpiano implementationofcombinedlocalglobalopticalflow
AT steffenhartel implementationofcombinedlocalglobalopticalflow