Performance of dynamic texture segmentation using GPU
This work is focused on the assessment of the use of GPU computation in dynamic texture segmentation under the mixture of dynamic textures (MDT) model. In this generative video model, the observed texture is a time-varying process commanded by a hidden state process. The use of mixtures in this mode...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | JOUR |
Materias: | |
Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_18618200_v11_n2_p375_GomezFernandez |
Aporte de: |
id |
todo:paper_18618200_v11_n2_p375_GomezFernandez |
---|---|
record_format |
dspace |
spelling |
todo:paper_18618200_v11_n2_p375_GomezFernandez2023-10-03T16:33:22Z Performance of dynamic texture segmentation using GPU Gómez Fernández, F. Buemi, M.E. Rodríguez, J.M. Jacobo-Berlles, J.C. Dynamic textures Expectation maximization GPU Graphical model Video segmentation Algorithms Image segmentation Matrix algebra Maximum principle Mixtures Motion analysis Video signal processing Dynamic textures Expectation - maximizations GPU GraphicaL model Video segmentation Time and motion study This work is focused on the assessment of the use of GPU computation in dynamic texture segmentation under the mixture of dynamic textures (MDT) model. In this generative video model, the observed texture is a time-varying process commanded by a hidden state process. The use of mixtures in this model allows simultaneously handling of different visual processes. Nowadays, the use of GPU computing is growing in high-performance applications, but the adaptation of existing algorithms in such a way as to obtain a benefit from its use is not an easy task. In this paper, we made two implementations, one in CPU and the other in GPU, of a known segmentation algorithm based on MDT. In the MDT algorithm, there is a matrix inversion process that is highly demanding in terms of computing power. We make a comparison between the gain in performance obtained by porting to GPU this matrix inversion process and the gain obtained by porting to GPU the whole MDT segmentation process. We also study real-time motion segmentation performance by separating the learning part of the algorithm from the segmentation part, leaving the learning stage as an off-line process and keeping the segmentation as an online process. The results of performance analyses allow us to decide the cases in which the full GPU implementation of the motion segmentation process is worthwhile. © 2013, Springer-Verlag Berlin Heidelberg. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_18618200_v11_n2_p375_GomezFernandez |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
Dynamic textures Expectation maximization GPU Graphical model Video segmentation Algorithms Image segmentation Matrix algebra Maximum principle Mixtures Motion analysis Video signal processing Dynamic textures Expectation - maximizations GPU GraphicaL model Video segmentation Time and motion study |
spellingShingle |
Dynamic textures Expectation maximization GPU Graphical model Video segmentation Algorithms Image segmentation Matrix algebra Maximum principle Mixtures Motion analysis Video signal processing Dynamic textures Expectation - maximizations GPU GraphicaL model Video segmentation Time and motion study Gómez Fernández, F. Buemi, M.E. Rodríguez, J.M. Jacobo-Berlles, J.C. Performance of dynamic texture segmentation using GPU |
topic_facet |
Dynamic textures Expectation maximization GPU Graphical model Video segmentation Algorithms Image segmentation Matrix algebra Maximum principle Mixtures Motion analysis Video signal processing Dynamic textures Expectation - maximizations GPU GraphicaL model Video segmentation Time and motion study |
description |
This work is focused on the assessment of the use of GPU computation in dynamic texture segmentation under the mixture of dynamic textures (MDT) model. In this generative video model, the observed texture is a time-varying process commanded by a hidden state process. The use of mixtures in this model allows simultaneously handling of different visual processes. Nowadays, the use of GPU computing is growing in high-performance applications, but the adaptation of existing algorithms in such a way as to obtain a benefit from its use is not an easy task. In this paper, we made two implementations, one in CPU and the other in GPU, of a known segmentation algorithm based on MDT. In the MDT algorithm, there is a matrix inversion process that is highly demanding in terms of computing power. We make a comparison between the gain in performance obtained by porting to GPU this matrix inversion process and the gain obtained by porting to GPU the whole MDT segmentation process. We also study real-time motion segmentation performance by separating the learning part of the algorithm from the segmentation part, leaving the learning stage as an off-line process and keeping the segmentation as an online process. The results of performance analyses allow us to decide the cases in which the full GPU implementation of the motion segmentation process is worthwhile. © 2013, Springer-Verlag Berlin Heidelberg. |
format |
JOUR |
author |
Gómez Fernández, F. Buemi, M.E. Rodríguez, J.M. Jacobo-Berlles, J.C. |
author_facet |
Gómez Fernández, F. Buemi, M.E. Rodríguez, J.M. Jacobo-Berlles, J.C. |
author_sort |
Gómez Fernández, F. |
title |
Performance of dynamic texture segmentation using GPU |
title_short |
Performance of dynamic texture segmentation using GPU |
title_full |
Performance of dynamic texture segmentation using GPU |
title_fullStr |
Performance of dynamic texture segmentation using GPU |
title_full_unstemmed |
Performance of dynamic texture segmentation using GPU |
title_sort |
performance of dynamic texture segmentation using gpu |
url |
http://hdl.handle.net/20.500.12110/paper_18618200_v11_n2_p375_GomezFernandez |
work_keys_str_mv |
AT gomezfernandezf performanceofdynamictexturesegmentationusinggpu AT buemime performanceofdynamictexturesegmentationusinggpu AT rodriguezjm performanceofdynamictexturesegmentationusinggpu AT jacoboberllesjc performanceofdynamictexturesegmentationusinggpu |
_version_ |
1782023607970430976 |