Title :
A fine-grained parallel pipelined Karhunen-Loeve transform
Author :
Fleury, Martin ; Self, Bob ; Downton, Andy
Author_Institution :
Electron. Syst. Eng. Dept., Essex Univ., Colchester, UK
Abstract :
A high-performance Karhunen-Loeve transform for multi-spectral imagery suitable for remote-sensing applications has been prototyped on a platform FPGA, by means of a PC-based development board. Performance estimates suggest that the design will already outperform implementation on a high-end microprocessor, given due attention to I/O (input/output). General conclusions are reached for the utility of this architecture for fine-grained parallel processing, when the design is extended to massively parallel processing.
Keywords :
Karhunen-Loeve transforms; field programmable gate arrays; image processing; parallel algorithms; parallel architectures; performance evaluation; pipeline processing; remote sensing; FPGA; Karhunen-Loeve transform; PC-based development board; fine-grained parallel architecture; fine-grained parallel processing; high-performance transform; image processing; massively parallel processing; multi-spectral imagery; parallel pipelined transform; remote-sensing applications; Algorithm design and analysis; Discrete transforms; Field programmable gate arrays; Karhunen-Loeve transforms; Kernel; Microprocessors; Parallel processing; Prototypes; Remote sensing; Satellites;
Conference_Titel :
Parallel and Distributed Processing Symposium, 2003. Proceedings. International
Print_ISBN :
0-7695-1926-1
DOI :
10.1109/IPDPS.2003.1213476
