Multilevel optimization for dense motion estimation
This research has been oriented towards the design of a new technique for fast and reliable dense motion estimation. We used variational models of optical flow computation to estimate the dense motion in a sequence of images.We have been interested in developing a multilevel optimization solver to p...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Monograph |
Language: | English English |
Published: |
Universiti Utara Malaysia
2011
|
Subjects: | |
Online Access: | http://repo.uum.edu.my/8135/1/MOFDME.pdf http://repo.uum.edu.my/8135/3/1.Azizan%20Saaban.pdf http://repo.uum.edu.my/8135/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uum.repo.8135 |
---|---|
record_format |
eprints |
spelling |
my.uum.repo.81352014-07-06T02:59:20Z http://repo.uum.edu.my/8135/ Multilevel optimization for dense motion estimation Saaban, Azizan Kalmoun, El Mostafa Ibrahim, Haslinda Ramli, Razamin Omar, Zurni QA76 Computer software This research has been oriented towards the design of a new technique for fast and reliable dense motion estimation. We used variational models of optical flow computation to estimate the dense motion in a sequence of images.We have been interested in developing a multilevel optimization solver to produce accurate optical flow estimation for real-time applications.To the best of our knowledge, two-ways multilevel optimization techniques are used for the first time in the context of a computer vision problem. We evaluated the performance of different optimization techniques developed in the context of optical flow computation with different variational models.In particular, based on truncated Newton methods (TN) that have been an effective approach for large-scale unconstrained optimization, we developed the use of efficient multilevel schemes for computing the optical flow.More precisely, we evaluated the performance of a standard unidirectional multilevel algorithm - called multiresolution optimization (MR/Opt), to a bidrectional multilevel algorithm - called full multigrid optimization (FMG/Opt).The FMG/Opt algorithm treats the coarse grid correction as an optimization search direction and eventually scales it using a line search. Experimental results on three image sequences using four models of optical flow with different computational efforts show that the FMG/Opt algorithm outperforms significantly both the TN and MR/Opt algorithms in terms of the computational work and the quality of the optical flow estimation. Universiti Utara Malaysia 2011-06 Monograph NonPeerReviewed application/pdf en http://repo.uum.edu.my/8135/1/MOFDME.pdf application/pdf en http://repo.uum.edu.my/8135/3/1.Azizan%20Saaban.pdf Saaban, Azizan and Kalmoun, El Mostafa and Ibrahim, Haslinda and Ramli, Razamin and Omar, Zurni (2011) Multilevel optimization for dense motion estimation. Project Report. Universiti Utara Malaysia. (Unpublished) |
institution |
Universiti Utara Malaysia |
building |
UUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Utara Malaysia |
content_source |
UUM Institutionali Repository |
url_provider |
http://repo.uum.edu.my/ |
language |
English English |
topic |
QA76 Computer software |
spellingShingle |
QA76 Computer software Saaban, Azizan Kalmoun, El Mostafa Ibrahim, Haslinda Ramli, Razamin Omar, Zurni Multilevel optimization for dense motion estimation |
description |
This research has been oriented towards the design of a new technique for fast and reliable dense motion estimation. We used variational models of optical flow computation to estimate the dense motion in a sequence of images.We have been interested in developing a multilevel optimization solver to produce accurate optical flow estimation for real-time applications.To the best of our knowledge, two-ways multilevel optimization techniques are used for the first time in the context of a computer vision problem. We evaluated the performance of different optimization
techniques developed in the context of optical flow computation with different variational models.In particular, based on truncated Newton methods (TN) that have
been an effective approach for large-scale unconstrained optimization, we developed the use of efficient multilevel schemes for computing the optical flow.More precisely, we evaluated the performance of a standard unidirectional multilevel algorithm - called multiresolution optimization (MR/Opt), to a bidrectional multilevel algorithm - called full multigrid optimization (FMG/Opt).The FMG/Opt algorithm
treats the coarse grid correction as an optimization search direction and eventually scales it using a line search. Experimental results on three image sequences using four models of optical flow with different computational efforts show that the FMG/Opt algorithm outperforms significantly both the TN and MR/Opt algorithms in terms of the computational work and the quality of the optical flow estimation. |
format |
Monograph |
author |
Saaban, Azizan Kalmoun, El Mostafa Ibrahim, Haslinda Ramli, Razamin Omar, Zurni |
author_facet |
Saaban, Azizan Kalmoun, El Mostafa Ibrahim, Haslinda Ramli, Razamin Omar, Zurni |
author_sort |
Saaban, Azizan |
title |
Multilevel optimization for dense motion estimation |
title_short |
Multilevel optimization for dense motion estimation |
title_full |
Multilevel optimization for dense motion estimation |
title_fullStr |
Multilevel optimization for dense motion estimation |
title_full_unstemmed |
Multilevel optimization for dense motion estimation |
title_sort |
multilevel optimization for dense motion estimation |
publisher |
Universiti Utara Malaysia |
publishDate |
2011 |
url |
http://repo.uum.edu.my/8135/1/MOFDME.pdf http://repo.uum.edu.my/8135/3/1.Azizan%20Saaban.pdf http://repo.uum.edu.my/8135/ |
_version_ |
1644279744395476992 |
score |
13.160551 |