Use of FPGA or GPU-based architectures for remotely sensed hyperspectral image processing

Carlos Gonzalez, Sergio Sanchez, Abel Paz, Javier Resano, Daniel Mozos, Antonio Plaza
Department of Computer Architecture and Automatics, Computer Science Faculty, Complutense University of Madrid, 28040 Madrid, Spain
Integration, the VLSI Journal, 2012


   title={Use of FPGA or GPU-based architectures for remotely sensed hyperspectral image processing},

   author={Gonz{‘a}lez, C. and S{‘a}nchez, S. and Paz, A. and Resano, J. and Mozos, D. and Plaza, A.},

   journal={Integration, the VLSI Journal},




Download Download (PDF)   View View   Source Source   



Hyperspectral imaging is a growing area in remote sensing in which an imaging spectrometer collects hundreds of images (at different wavelength channels) for the same area on the surface of the Earth. Hyperspectral images are extremely high-dimensional, and require advanced on-board processing algorithms able to satisfy near real-time constraints in applications such as wildland fire monitoring, mapping of oil spills and chemical contamination, etc. One of the most widely used techniques for analyzing hyperspectral images is spectral unmixing, which allows for sub-pixel data characterization. This is particularly important since the available spatial resolution in hyperspectral images is typically of several meters, and therefore it is reasonable to assume that several spectrally pure substances (called endmembers in hyperspectral imaging terminology) can be found within each imaged pixel. In this paper we explore the role of hardware accelerators in hyperspectral remote sensing missions and further inter-compare two types of solutions: field programmable gate arrays (FPGAs) and graphics processing units (GPUs). A full spectral unmixing chain is implemented and tested in this work, using both types of accelerators, in the context of a real hyperspectral mapping application using hyperspectral data collected by NASA’s Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS). The paper provides a thoughtful perspective on the potential and emerging challenges of applying these types of accelerators in hyperspectral remote sensing missions, indicating that the reconfigurability of FPGA systems (on the one hand) and the low cost of GPU systems (on the other) open many innovative perspectives toward fast on-board and on-the-ground processing of remotely sensed hyperspectral images.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: