Share Email Print

Proceedings Paper

Design of FPGA ICA for hyperspectral imaging processing
Author(s): Anis Nordin; Charles C. Hsu; Harold H. Szu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The remote sensing problem which uses hyperspectral imaging can be transformed into a blind source separation problem. Using this model, hyperspectral imagery can be de-mixed into sub-pixel spectra which indicate the different material present in the pixel. This can be further used to deduce areas which contain forest, water or biomass, without even knowing the sources which constitute the image. This form of remote sensing allows previously blurred images to show the specific terrain involved in that region. The blind source separation problem can be implemented using an Independent Component Analysis algorithm. The ICA Algorithm has previously been successfully implemented using software packages such as MATLAB, which has a downloadable version of FastICA. The challenge now lies in implementing it in a form of hardware, or firmware in order to improve its computational speed. Hardware implementation also solves insufficient memory problem encountered by software packages like MATLAB when employing ICA for high resolution images and a large number of channels. Here, a pipelined solution of the firmware, realized using FPGAs are drawn out and simulated using C. Since C code can be translated into HDLs or be used directly on the FPGAs, it can be used to simulate its actual implementation in hardware. The simulated results of the program is presented here, where seven channels are used to model the 200 different channels involved in hyperspectral imaging.

Paper Details

Date Published: 26 March 2001
PDF: 11 pages
Proc. SPIE 4391, Wavelet Applications VIII, (26 March 2001); doi: 10.1117/12.421225
Show Author Affiliations
Anis Nordin, George Washington Univ. (United States)
Charles C. Hsu, Trident Systems Inc. (United States)
Harold H. Szu, George Washington Univ. (United States)

Published in SPIE Proceedings Vol. 4391:
Wavelet Applications VIII
Harold H. Szu; David L. Donoho; Adolf W. Lohmann; William J. Campbell; James R. Buss, Editor(s)

© SPIE. Terms of Use
Back to Top