Performance of dynamic texture segmentation using GPU

Mostrar todas las versiones(2)

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...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gómez Fernández, F., Buemi, M.E., Rodríguez, J.M., Jacobo-Berlles, J.C.
Formato: INPR
Lenguaje:English
Materias:
Dynamic textures
Expectation maximization
GPU
Graphical model
Video segmentation
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_18618200_v_n_p1_GomezFernandez
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id todo:paper_18618200_v_n_p1_GomezFernandez
record_format dspace
spelling todo:paper_18618200_v_n_p1_GomezFernandez2023-10-03T16:33:23Z 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 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. Fil:Gómez Fernández, F. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Buemi, M.E. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Jacobo-Berlles, J.C. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. INPR English info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_18618200_v_n_p1_GomezFernandez
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
language English
orig_language_str_mv English
topic Dynamic textures
Expectation maximization
GPU
Graphical model
Video segmentation
spellingShingle Dynamic textures
Expectation maximization
GPU
Graphical model
Video segmentation
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
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 INPR
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_v_n_p1_GomezFernandez
work_keys_str_mv AT gomezfernandezf performanceofdynamictexturesegmentationusinggpu
AT buemime performanceofdynamictexturesegmentationusinggpu
AT rodriguezjm performanceofdynamictexturesegmentationusinggpu
AT jacoboberllesjc performanceofdynamictexturesegmentationusinggpu
_version_ 1782027874264416256

Ejemplares similares