Skip to main navigation Skip to search Skip to main content

GPU acceleration of simplex volume algorithm for hyperspectral endmember extraction

  • Harbin Institute of Technology
  • Liaoning Technical University
  • University of Wisconsin-Madison

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

Abstract

The simplex volume algorithm (SVA) 1 is an endmember extraction algorithm based on the geometrical properties of a simplex in the feature space of hyperspectral image. By utilizing the relation between a simplex volume and its corresponding parallelohedron volume in the high-dimensional space, the algorithm extracts endmembers from the initial hyperspectral image directly without the need of dimension reduction. It thus avoids the drawback of the N-FINDER algorithm, which requires the dimension of the data to be reduced to one less than the number of the endmembers. In this paper, we take advantage of the large-scale parallelism of CUDA (Compute Unified Device Architecture) to accelerate the computation of SVA on the NVidia GeForce 560 GPU. The time for computing a simplex volume increases with the number of endmembers. Experimental results show that the proposed GPU-based SVA achieves a significant 112.56x speedup for extracting 16 endmembers, as compared to its CPU-based single-threaded counterpart.

Original languageEnglish
Title of host publicationHigh-Performance Computing in Remote Sensing II
DOIs
StatePublished - 2012
EventHigh-Performance Computing in Remote Sensing II - Edinburgh, United Kingdom
Duration: 26 Sep 201227 Sep 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8539
ISSN (Print)0277-786X

Conference

ConferenceHigh-Performance Computing in Remote Sensing II
Country/TerritoryUnited Kingdom
CityEdinburgh
Period26/09/1227/09/12

Keywords

  • CUDA
  • GPU
  • Simplex volume algorithm
  • endmember extraction

Fingerprint

Dive into the research topics of 'GPU acceleration of simplex volume algorithm for hyperspectral endmember extraction'. Together they form a unique fingerprint.

Cite this