A Comparative Study of Implementation Strategies for Real-Time Video Processing

Autores
Odorico, Pablo; Touceda, Tomás; Delrieux, Claudio
Año de publicación
2010
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
We present a comparative study of the efficiency and effectiveness of different implementation strategies for real-time video processing. In particular, we tested the performance of GPU processors (using the CUDA library) against the performance of quad-core PC Intel processors (using the Intel Performance Primitives library). The test consisted on applying a standard group of image processing algorithms, including histogram equalization, and convolution filtering, to a number of high definition video sequences and measuring the performance of each implementation. The results show that GPU processing is extremely cost-effective, but with the drawback that the underlying programming framework is very architecture-dependent, making it prone to the hardware idiosyncrasies, and therefore less abstract and reusable.
Sociedad Argentina de Informática e Investigación Operativa
Materia
Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/152704
Acceder
id SEDICI_8888ffa1dfd88d20094b7a838642312a
oai_identifier_str oai:sedici.unlp.edu.ar:10915/152704
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling A Comparative Study of Implementation Strategies for Real-Time Video ProcessingOdorico, PabloTouceda, TomásDelrieux, ClaudioCiencias InformáticasVideo ProcessingGPGPUMany-Core ComputingWe present a comparative study of the efficiency and effectiveness of different implementation strategies for real-time video processing. In particular, we tested the performance of GPU processors (using the CUDA library) against the performance of quad-core PC Intel processors (using the Intel Performance Primitives library). The test consisted on applying a standard group of image processing algorithms, including histogram equalization, and convolution filtering, to a number of high definition video sequences and measuring the performance of each implementation. The results show that GPU processing is extremely cost-effective, but with the drawback that the underlying programming framework is very architecture-dependent, making it prone to the hardware idiosyncrasies, and therefore less abstract and reusable.Sociedad Argentina de Informática e Investigación Operativa2010info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf1542-1550http://sedici.unlp.edu.ar/handle/10915/152704enginfo:eu-repo/semantics/altIdentifier/url/http://39jaiio.sadio.org.ar/sites/default/files/39-jaiio-ast-02.pdfinfo:eu-repo/semantics/altIdentifier/issn/1850-2806info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-17T10:21:59Zoai:sedici.unlp.edu.ar:10915/152704Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-17 10:21:59.878SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv A Comparative Study of Implementation Strategies for Real-Time Video Processing
title A Comparative Study of Implementation Strategies for Real-Time Video Processing
spellingShingle A Comparative Study of Implementation Strategies for Real-Time Video Processing
Odorico, Pablo
Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
title_short A Comparative Study of Implementation Strategies for Real-Time Video Processing
title_full A Comparative Study of Implementation Strategies for Real-Time Video Processing
title_fullStr A Comparative Study of Implementation Strategies for Real-Time Video Processing
title_full_unstemmed A Comparative Study of Implementation Strategies for Real-Time Video Processing
title_sort A Comparative Study of Implementation Strategies for Real-Time Video Processing
dc.creator.none.fl_str_mv Odorico, Pablo
Touceda, Tomás
Delrieux, Claudio
author Odorico, Pablo
author_facet Odorico, Pablo
Touceda, Tomás
Delrieux, Claudio
author_role author
author2 Touceda, Tomás
Delrieux, Claudio
author2_role author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
topic Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
dc.description.none.fl_txt_mv We present a comparative study of the efficiency and effectiveness of different implementation strategies for real-time video processing. In particular, we tested the performance of GPU processors (using the CUDA library) against the performance of quad-core PC Intel processors (using the Intel Performance Primitives library). The test consisted on applying a standard group of image processing algorithms, including histogram equalization, and convolution filtering, to a number of high definition video sequences and measuring the performance of each implementation. The results show that GPU processing is extremely cost-effective, but with the drawback that the underlying programming framework is very architecture-dependent, making it prone to the hardware idiosyncrasies, and therefore less abstract and reusable.
Sociedad Argentina de Informática e Investigación Operativa
description We present a comparative study of the efficiency and effectiveness of different implementation strategies for real-time video processing. In particular, we tested the performance of GPU processors (using the CUDA library) against the performance of quad-core PC Intel processors (using the Intel Performance Primitives library). The test consisted on applying a standard group of image processing algorithms, including histogram equalization, and convolution filtering, to a number of high definition video sequences and measuring the performance of each implementation. The results show that GPU processing is extremely cost-effective, but with the drawback that the underlying programming framework is very architecture-dependent, making it prone to the hardware idiosyncrasies, and therefore less abstract and reusable.
publishDate 2010
dc.date.none.fl_str_mv 2010
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/152704
url http://sedici.unlp.edu.ar/handle/10915/152704
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://39jaiio.sadio.org.ar/sites/default/files/39-jaiio-ast-02.pdf
info:eu-repo/semantics/altIdentifier/issn/1850-2806
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
1542-1550
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1843532930032336896
score 13.001348

Publicaciones similares