Dynamic textures segmentation with GPU

This work addresses the problem of motion segmentation in video sequences using dynamic textures. Motion can be globally modeled as a statistical visual process know as dynamic texture. Specifically, we use the mixtures of dynamic textures model which can simultaneously handle different visual proce...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gómez Fernández, Francisco, Buemi, María Elena, Jacobo Berlles, Julio C. A.
Publicado: 2012
Materias:
Computer vision applications
Cost benefit ratio
Dynamic textures
GPU implementation
GPU programming
Motion segmentation
Performance analysis
Video sequences
Visual process
Computer vision
Image analysis
Textures
Acceso en línea:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p607_Rodriguez
http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p607_Rodriguez
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id paper:paper_03029743_v7441LNCS_n_p607_Rodriguez
record_format dspace
spelling paper:paper_03029743_v7441LNCS_n_p607_Rodriguez2023-06-08T15:28:47Z Dynamic textures segmentation with GPU Gómez Fernández, Francisco Buemi, María Elena Jacobo Berlles, Julio C. A. Computer vision applications Cost benefit ratio Dynamic textures GPU implementation GPU programming Motion segmentation Performance analysis Video sequences Visual process Computer vision Image analysis Textures This work addresses the problem of motion segmentation in video sequences using dynamic textures. Motion can be globally modeled as a statistical visual process know as dynamic texture. Specifically, we use the mixtures of dynamic textures model which can simultaneously handle different visual processes. Nowadays, GPU are becoming increasingly popular in computer vision applications because of their cost-benefit ratio. However, GPU programming is not a trivial task and not all algorithms can be easily switched to GPU. In this paper, we made two implementations of a known motion segmentation algorithm based on mixtures of dynamic textures. One using CPU and the other ported to GPU. The performance analyses show the scenarios for which it is worthwhile to do the full GPU implementation of the motion segmentation process. © 2012 Springer-Verlag. 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. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2012 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p607_Rodriguez http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p607_Rodriguez
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Computer vision applications
Cost benefit ratio
Dynamic textures
GPU implementation
GPU programming
Motion segmentation
Performance analysis
Video sequences
Visual process
Computer vision
Image analysis
Textures
spellingShingle Computer vision applications
Cost benefit ratio
Dynamic textures
GPU implementation
GPU programming
Motion segmentation
Performance analysis
Video sequences
Visual process
Computer vision
Image analysis
Textures
Gómez Fernández, Francisco
Buemi, María Elena
Jacobo Berlles, Julio C. A.
Dynamic textures segmentation with GPU
topic_facet Computer vision applications
Cost benefit ratio
Dynamic textures
GPU implementation
GPU programming
Motion segmentation
Performance analysis
Video sequences
Visual process
Computer vision
Image analysis
Textures
description This work addresses the problem of motion segmentation in video sequences using dynamic textures. Motion can be globally modeled as a statistical visual process know as dynamic texture. Specifically, we use the mixtures of dynamic textures model which can simultaneously handle different visual processes. Nowadays, GPU are becoming increasingly popular in computer vision applications because of their cost-benefit ratio. However, GPU programming is not a trivial task and not all algorithms can be easily switched to GPU. In this paper, we made two implementations of a known motion segmentation algorithm based on mixtures of dynamic textures. One using CPU and the other ported to GPU. The performance analyses show the scenarios for which it is worthwhile to do the full GPU implementation of the motion segmentation process. © 2012 Springer-Verlag.
author Gómez Fernández, Francisco
Buemi, María Elena
Jacobo Berlles, Julio C. A.
author_facet Gómez Fernández, Francisco
Buemi, María Elena
Jacobo Berlles, Julio C. A.
author_sort Gómez Fernández, Francisco
title Dynamic textures segmentation with GPU
title_short Dynamic textures segmentation with GPU
title_full Dynamic textures segmentation with GPU
title_fullStr Dynamic textures segmentation with GPU
title_full_unstemmed Dynamic textures segmentation with GPU
title_sort dynamic textures segmentation with gpu
publishDate 2012
url https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v7441LNCS_n_p607_Rodriguez
http://hdl.handle.net/20.500.12110/paper_03029743_v7441LNCS_n_p607_Rodriguez
work_keys_str_mv AT gomezfernandezfrancisco dynamictexturessegmentationwithgpu
AT buemimariaelena dynamictexturessegmentationwithgpu
AT jacoboberllesjulioca dynamictexturessegmentationwithgpu
_version_ 1768546067389874176

Ejemplares similares