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

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 Perf...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Odorico, Pablo, Touceda, Tomás, Delrieux, Claudio
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2010
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/152704
http://39jaiio.sadio.org.ar/sites/default/files/39-jaiio-ast-02.pdf
Aporte de:
id I19-R120-10915-152704
record_format dspace
spelling I19-R120-10915-1527042023-05-10T20:04:38Z http://sedici.unlp.edu.ar/handle/10915/152704 http://39jaiio.sadio.org.ar/sites/default/files/39-jaiio-ast-02.pdf issn:1850-2806 A Comparative Study of Implementation Strategies for Real-Time Video Processing Odorico, Pablo Touceda, Tomás Delrieux, Claudio 2010 2010 2023-05-10T13:47:04Z en Ciencias Informáticas Video Processing GPGPU Many-Core Computing 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 Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 1542-1550
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
spellingShingle Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
Odorico, Pablo
Touceda, Tomás
Delrieux, Claudio
A Comparative Study of Implementation Strategies for Real-Time Video Processing
topic_facet Ciencias Informáticas
Video Processing
GPGPU
Many-Core Computing
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.
format Objeto de conferencia
Objeto de conferencia
author Odorico, Pablo
Touceda, Tomás
Delrieux, Claudio
author_facet Odorico, Pablo
Touceda, Tomás
Delrieux, Claudio
author_sort Odorico, Pablo
title A Comparative Study of Implementation Strategies for Real-Time Video Processing
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 comparative study of implementation strategies for real-time video processing
publishDate 2010
url http://sedici.unlp.edu.ar/handle/10915/152704
http://39jaiio.sadio.org.ar/sites/default/files/39-jaiio-ast-02.pdf
work_keys_str_mv AT odoricopablo acomparativestudyofimplementationstrategiesforrealtimevideoprocessing
AT toucedatomas acomparativestudyofimplementationstrategiesforrealtimevideoprocessing
AT delrieuxclaudio acomparativestudyofimplementationstrategiesforrealtimevideoprocessing
AT odoricopablo comparativestudyofimplementationstrategiesforrealtimevideoprocessing
AT toucedatomas comparativestudyofimplementationstrategiesforrealtimevideoprocessing
AT delrieuxclaudio comparativestudyofimplementationstrategiesforrealtimevideoprocessing
_version_ 1765660140139184128