Detail publikace

Real-Time PCA Calculation for Spectral Imaging (using SIMD and GP-GPU)

Originální název

Real-Time PCA Calculation for Spectral Imaging (using SIMD and GP-GPU)

Anglický název

Real-Time PCA Calculation for Spectral Imaging (using SIMD and GP-GPU)

Jazyk

en

Originální abstrakt

This article presents two optimized implementations of the PCA algorithm, primarily targeted on spectral image analysis in real time. One of them utilizes the SSE instruction set of contemporary CPUs, the other one runs on graphics processors (GPUs), using the CUDA environment. The implementations are evaluated and compared with a multithreaded C implementation compiled by an optimizing compiler and the results show speed-ups of around 10x which allows for using PCA on RGB and spectral images in real time. The discussed implementations are made available in a dynamically linked library, including a MATLAB plug-in interface so that they can be used by the professional public.

Anglický abstrakt

This article presents two optimized implementations of the PCA algorithm, primarily targeted on spectral image analysis in real time. One of them utilizes the SSE instruction set of contemporary CPUs, the other one runs on graphics processors (GPUs), using the CUDA environment. The implementations are evaluated and compared with a multithreaded C implementation compiled by an optimizing compiler and the results show speed-ups of around 10x which allows for using PCA on RGB and spectral images in real time. The discussed implementations are made available in a dynamically linked library, including a MATLAB plug-in interface so that they can be used by the professional public.

BibTex


@article{BUT50549,
  author="Radovan {Jošth} and Jukka {Antikainen} and Jiří {Havel} and Adam {Herout} and Pavel {Zemčík} and Markku {Hauta-Kasari}",
  title="Real-Time PCA Calculation for Spectral Imaging (using SIMD and GP-GPU)",
  annote="This article presents two optimized implementations of the PCA algorithm,
primarily targeted on spectral image analysis in real time. One of them utilizes
the SSE instruction set of contemporary CPUs, the other one runs on graphics
processors (GPUs), using the CUDA environment. The implementations are evaluated
and compared with a multithreaded C implementation compiled by an optimizing
compiler and the results show speed-ups of around 10x which allows for using PCA
on RGB and spectral images in real time. The discussed implementations are made
available in a dynamically linked library, including a MATLAB plug-in interface
so that they can be used by the professional public.",
  address="NEUVEDEN",
  chapter="50549",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="2",
  volume="7",
  year="2012",
  month="january",
  pages="95--103",
  publisher="NEUVEDEN",
  type="journal article - other"
}