Share Email Print

Proceedings Paper

Parallel strategies for SAR processing
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This article proposes a series of strategies for improving the computer process of the Synthetic Aperture Radar (SAR) signal treatment, following the three usual lines of action to speed up the execution of any computer program. On the one hand, it is studied the optimization of both, the data structures and the application architecture used on it. On the other hand it is considered a hardware improvement. For the former, they are studied both, the usually employed SAR process data structures, proposing the use of parallel ones and the way the parallelization of the algorithms employed on the process is implemented. Besides, the parallel application architecture classifies processes between fine/coarse grain. These are assigned to individual processors or separated in a division among processors, all of them in their corresponding architectures. For the latter, it is studied the hardware employed on the computer parallel process used in the SAR handling. The improvement here refers to several kinds of platforms in which the SAR process is implemented, shared memory multicomputers, and distributed memory multiprocessors. A comparison between them gives us some guidelines to follow in order to get a maximum throughput with a minimum latency and a maximum effectiveness with a minimum cost, all together with a limited complexness. It is concluded and described, that the approach consisting of the processing of the algorithms in a GNU/Linux environment, together with a Beowulf cluster platform offers, under certain conditions, the best compromise between performance and cost, and promises the major development in the future for the Synthetic Aperture Radar computer power thirsty applications in the next years.

Paper Details

Date Published: 30 December 2004
PDF: 8 pages
Proc. SPIE 5652, Passive Optical Remote Sensing of the Atmosphere and Clouds IV, (30 December 2004); doi: 10.1117/12.579802
Show Author Affiliations
Jesus Alonso Segoviano, Univ. Politecnica de Madrid (Spain)

Published in SPIE Proceedings Vol. 5652:
Passive Optical Remote Sensing of the Atmosphere and Clouds IV
Si Chee Tsay; Tatsuya Yokota; Myoung-Hwan Ahn, Editor(s)

© SPIE. Terms of Use
Back to Top