• DocumentCode
    2769569
  • Title

    Flexible allocation approach for GPU implementation of 2D IIR filters in satellite images processing

  • Author

    Fursov, V. ; Nikonorov, A. ; Yakimov, P.

  • Author_Institution
    Samara State Aerosp. Univ., Samara, Russia
  • fYear
    2012
  • fDate
    11-11 Nov. 2012
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    This paper considers a GPU implementation of a two-dimensional infinite impulse-response filter. The presented flexible allocation approach makes it possible to efficiently implement the polytope model in a single GPU kernel. Some theoretical performance estimations of the proposed flexible allocation algorithm are given in the paper. The proposed IIR filtering technique is efficient when applied to de-blurring satellite images of large size.
  • Keywords
    IIR filters; geophysical image processing; graphics processing units; image restoration; 2D IIR filters; GPU implementation; IIR filtering technique; flexible allocation approach; polytope model; satellite image deblurring; satellite image processing; single GPU kernel; theoretical performance estimations; two-dimensional infinite impulse-response filter; Algorithm design and analysis; Graphics processing units; IIR filters; Indexes; Kernel; Mathematical model; Resource management;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition in Remote Sensing (PRRS), 2012 IAPR Workshop on
  • Conference_Location
    Tsukuba
  • Print_ISBN
    978-1-4673-4960-4
  • Type

    conf

  • DOI
    10.1109/PPRS.2012.6398323
  • Filename
    6398323