Title :
Resilient image fusion
Author :
Achalakul, Tiranee ; Lee, Joohan ; Taylor, Stephen
Author_Institution :
Syracuse Univ., NY, USA
Abstract :
The paper describes a distributed spectral-screening PCT algorithm for fusing hyper-spectral images in remote sensing applications. The algorithm provides intrusion tolerance from information warfare attacks using the notion of computational resiliency. This concept uses replication to achieve fault tolerance, but goes further to dynamically regenerate replication in response to an attack or failure. The concepts of resiliency are incorporated through library technology that is application independent. This library hides the details of communication protocols required to achieve dynamic replication and reconfiguration in distributed applications. The paper provides a status report on our progress in developing the concept and applying it to image fusion. In particular it examines the performance of the PCT algorithm and compares the results with and without resiliency to assess the associated overheads
Keywords :
distributed algorithms; fault tolerant computing; image processing; performance evaluation; principal component analysis; remote sensing; sensor fusion; workstation clusters; communication protocols; computational resiliency; distributed applications; distributed spectral-screening PCT algorithm; fault tolerance; hyper-spectral image fusion; information warfare; library technology; performance evaluation; remote sensing applications; resilient image fusion; Capacitive sensors; Command and control systems; Fault tolerance; Image fusion; Libraries; Local area networks; Military computing; Protocols; Remote sensing; Workstations;
Conference_Titel :
Parallel Processing, 2000. Proceedings. 2000 International Workshops on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7695-0771-9
DOI :
10.1109/ICPPW.2000.869115