This article is cited in 1 paper

ПЛЕНАРНЫЕ ДОКЛАДЫ

Grid based high performance computing in satellite imagery. Case study — Perona–Malik filter

B. Belean^a, C. Belean^b, C. Floare^a, C. Varodi^a, A. Bot^a, G. Adam<sup>cd

a</sup> National Institute for R\&D of Isotopic and Molecular Technolgies, 67-103 Donat St., PO 5 Box 700, Cluj-Napoca, 400293, Romania
^b Babes-Bolyai University, Faculty of Mathematics and Computer Science, Department of Mathematics, 1 M. Kogalniceanu St., Cluj-Napoca, 400084, Romania
^c Laboratory of Information Technologies, Joint Institute for Nuclear Research, 6 Joliot Curie St., Dubna, 141980, Russia
^d Horia Hulubei National Institute for Physics and Nuclear Engineering (IFIN-HH), 30 Reactorului St., Magurele-Bucharest, 077125, Romania

Abstract: The present paper discusses an approach to the efficient satellite image processing which involves two steps. The first step assumes the distribution of the steadily increasing volume of satellite collected data through a Grid infrastructure. The second step assumes the acceleration of the solution of the individual tasks related to image processing by implementing execution codes which make heavy use of spatial and temporal parallelism. An instance of such execution code is the image processing by means of the iterative Perona–Malik filter within FPGA application specific hardware architecture.

UDC: 004.021

Received: 04.12.2014

Language: English

DOI: 10.20537/2076-7633-2015-7-3-399-406