Grid computing for hyperspectral data processing

Stefan Robila, Nicholas A. Senedzuk

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

1 Citation (Scopus)

Abstract

We investigate the use of a flexible grid architecture for hyperspectral image processing. Recording data in tens or hundreds of narrow contiguous spectral intervals, hyperspectral data outperform multispectral imagery by allowing the detection of relatively small differences in material composition and of targets occupying a surface smaller than the one covered by a pixel (called subpixel targets). However, with increased spatial and spectral resolution, processing such data often leads to computational costs prohibitive to regular computer systems. While distributed or parallel computing are often found as solutions, many current configurations are still unable to reach the computational complexity level that is required for exhaustive search solutions. In this environment, grid computing becomes a viable alternative. Grid computing, an emerging computing model, is based on the concept of distributing processes across a parallel infrastructure. Throughput is further increased by networking many heterogeneous resources across administrative boundaries to model a virtual computer architecture. Compared to distributed clusters or parallel machines, grid systems are often inexpensive or even free since they can consist of non-dedicated computer systems that are underutilized and have extra CPU cycles that can be spared. We present general considerations on grid architectures and discuss the current grid environment we have deployed. Next, we investigate exhaustive band search, a data processing problems that suffers from large computational requirements and present our grid based solutions for it. Our experimental results indicate a significant speedup in obtaining results and even solving of problems otherwise not tractable in regular computing environments.

Original languageEnglish
Title of host publicationNext-Generation Spectroscopic Technologies
DOIs
StatePublished - 1 Dec 2007
EventNext-Generation Spectroscopic Technologies - Boston, MA, United States
Duration: 10 Sep 200711 Sep 2007

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6765
ISSN (Print)0277-786X

Other

OtherNext-Generation Spectroscopic Technologies
CountryUnited States
CityBoston, MA
Period10/09/0711/09/07

Fingerprint

Hyperspectral Data
Grid computing
Grid Computing
grids
Grid
Computer systems
Data recording
Computer architecture
Spectral resolution
Distributed computer systems
Parallel processing systems
Program processors
Computational complexity
architecture (computers)
Image processing
data recording
Pixels
Throughput
Target
Computer Architecture

Keywords

  • Distributed computing
  • Grid processing
  • Hyperspectral data
  • Spectral distances

Cite this

Robila, S., & Senedzuk, N. A. (2007). Grid computing for hyperspectral data processing. In Next-Generation Spectroscopic Technologies [67650A] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6765). https://doi.org/10.1117/12.734746
Robila, Stefan ; Senedzuk, Nicholas A. / Grid computing for hyperspectral data processing. Next-Generation Spectroscopic Technologies. 2007. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{a408f6e908af405e8fe3fd7e180e1f73,
title = "Grid computing for hyperspectral data processing",
abstract = "We investigate the use of a flexible grid architecture for hyperspectral image processing. Recording data in tens or hundreds of narrow contiguous spectral intervals, hyperspectral data outperform multispectral imagery by allowing the detection of relatively small differences in material composition and of targets occupying a surface smaller than the one covered by a pixel (called subpixel targets). However, with increased spatial and spectral resolution, processing such data often leads to computational costs prohibitive to regular computer systems. While distributed or parallel computing are often found as solutions, many current configurations are still unable to reach the computational complexity level that is required for exhaustive search solutions. In this environment, grid computing becomes a viable alternative. Grid computing, an emerging computing model, is based on the concept of distributing processes across a parallel infrastructure. Throughput is further increased by networking many heterogeneous resources across administrative boundaries to model a virtual computer architecture. Compared to distributed clusters or parallel machines, grid systems are often inexpensive or even free since they can consist of non-dedicated computer systems that are underutilized and have extra CPU cycles that can be spared. We present general considerations on grid architectures and discuss the current grid environment we have deployed. Next, we investigate exhaustive band search, a data processing problems that suffers from large computational requirements and present our grid based solutions for it. Our experimental results indicate a significant speedup in obtaining results and even solving of problems otherwise not tractable in regular computing environments.",
keywords = "Distributed computing, Grid processing, Hyperspectral data, Spectral distances",
author = "Stefan Robila and Senedzuk, {Nicholas A.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1117/12.734746",
language = "English",
isbn = "9780819469250",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Next-Generation Spectroscopic Technologies",

}

Robila, S & Senedzuk, NA 2007, Grid computing for hyperspectral data processing. in Next-Generation Spectroscopic Technologies., 67650A, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6765, Next-Generation Spectroscopic Technologies, Boston, MA, United States, 10/09/07. https://doi.org/10.1117/12.734746

Grid computing for hyperspectral data processing. / Robila, Stefan; Senedzuk, Nicholas A.

Next-Generation Spectroscopic Technologies. 2007. 67650A (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6765).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Grid computing for hyperspectral data processing

AU - Robila, Stefan

AU - Senedzuk, Nicholas A.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - We investigate the use of a flexible grid architecture for hyperspectral image processing. Recording data in tens or hundreds of narrow contiguous spectral intervals, hyperspectral data outperform multispectral imagery by allowing the detection of relatively small differences in material composition and of targets occupying a surface smaller than the one covered by a pixel (called subpixel targets). However, with increased spatial and spectral resolution, processing such data often leads to computational costs prohibitive to regular computer systems. While distributed or parallel computing are often found as solutions, many current configurations are still unable to reach the computational complexity level that is required for exhaustive search solutions. In this environment, grid computing becomes a viable alternative. Grid computing, an emerging computing model, is based on the concept of distributing processes across a parallel infrastructure. Throughput is further increased by networking many heterogeneous resources across administrative boundaries to model a virtual computer architecture. Compared to distributed clusters or parallel machines, grid systems are often inexpensive or even free since they can consist of non-dedicated computer systems that are underutilized and have extra CPU cycles that can be spared. We present general considerations on grid architectures and discuss the current grid environment we have deployed. Next, we investigate exhaustive band search, a data processing problems that suffers from large computational requirements and present our grid based solutions for it. Our experimental results indicate a significant speedup in obtaining results and even solving of problems otherwise not tractable in regular computing environments.

AB - We investigate the use of a flexible grid architecture for hyperspectral image processing. Recording data in tens or hundreds of narrow contiguous spectral intervals, hyperspectral data outperform multispectral imagery by allowing the detection of relatively small differences in material composition and of targets occupying a surface smaller than the one covered by a pixel (called subpixel targets). However, with increased spatial and spectral resolution, processing such data often leads to computational costs prohibitive to regular computer systems. While distributed or parallel computing are often found as solutions, many current configurations are still unable to reach the computational complexity level that is required for exhaustive search solutions. In this environment, grid computing becomes a viable alternative. Grid computing, an emerging computing model, is based on the concept of distributing processes across a parallel infrastructure. Throughput is further increased by networking many heterogeneous resources across administrative boundaries to model a virtual computer architecture. Compared to distributed clusters or parallel machines, grid systems are often inexpensive or even free since they can consist of non-dedicated computer systems that are underutilized and have extra CPU cycles that can be spared. We present general considerations on grid architectures and discuss the current grid environment we have deployed. Next, we investigate exhaustive band search, a data processing problems that suffers from large computational requirements and present our grid based solutions for it. Our experimental results indicate a significant speedup in obtaining results and even solving of problems otherwise not tractable in regular computing environments.

KW - Distributed computing

KW - Grid processing

KW - Hyperspectral data

KW - Spectral distances

UR - http://www.scopus.com/inward/record.url?scp=42449125338&partnerID=8YFLogxK

U2 - 10.1117/12.734746

DO - 10.1117/12.734746

M3 - Conference contribution

SN - 9780819469250

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Next-Generation Spectroscopic Technologies

ER -

Robila S, Senedzuk NA. Grid computing for hyperspectral data processing. In Next-Generation Spectroscopic Technologies. 2007. 67650A. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.734746