Design of FPGA ICA for hyperspectral imaging processing

Anis Nordin; Charles C. Hsu; Harold H. Szu

doi:10.1117/12.421225

26 March 2001 Design of FPGA ICA for hyperspectral imaging processing

Anis Nordin, Charles C. Hsu, Harold H. Szu

Proceedings Volume 4391, Wavelet Applications VIII; (2001) https://doi.org/10.1117/12.421225
Event: Aerospace/Defense Sensing, Simulation, and Controls, 2001, Orlando, FL, United States

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.

Citation Download Citation

Anis Nordin, Charles C. Hsu, and Harold H. Szu "Design of FPGA ICA for hyperspectral imaging processing", Proc. SPIE 4391, Wavelet Applications VIII, (26 March 2001); https://doi.org/10.1117/12.421225

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available