FPGA Implementation of Endmember Extraction Algorithms
from Hyperspectral Imagery: Pixel Purity Index versus
N-FINDR
Carlos Gonz´ alez
a
, Daniel Mozos
a
, Javier Resano
b
and Antonio Plaza
c
a
Department of Computer Architecture and Automatics, Complutense University of Madrid,
C/ Profesor Jos´ e Garc´ ıa Santesmases s/n 28040 Madrid (Spain)
b
Department of Computer Architecture, University of Zaragoza, C/ de Mar´ ıa de Luna 3, 50018
Zaragoza (Spain)
c
Department of Technology of Computers and Communications, University of Extremadura,
Avda. de la Universidad s/n E-10071 C´ aceres (Spain)
ABSTRACT
Endmember extraction is an important task for remotely sensed hyperspectral data exploitation. It comprises
the identification of spectral signatures corresponding to macroscopically pure components in the scene, so that
mixed pixels (resulting from limited spatial resolution, mixing phenomena happening at different scales, etc.) can
be decomposed into combinations of pure component spectra weighted by an estimation of the proportion (abun-
dance) of each endmember in the pixel. Over the last years, several algorithms have been proposed for automatic
extraction of endmembers from hyperspectral images. These algorithms can be time-consuming (particularly for
high-dimensional hyperspectral images). Parallel computing architectures have offered an attractive solution for
fast endmember extraction from hyperspectral data sets, but these systems are expensive and difficult to adapt
to on-board data processing scenarios, in which low-weight and low-power hardware components are essential to
reduce mission payload, overcome downlink bandwidth limitations in the transmission of the hyperspectral data
to ground stations on Earth, and obtain analysis results in (near) real-time.
In this paper, we perform an inter-comparison of the hardware implementations of two widely used techniques
for automatic endmember extraction from remotely sensed hyperspectral images: the pixel purity index (PPI)
and the N-FINDR. The hardware versions have been developed in field programmable gate arrays (FPGAs). Our
study reveals that these reconfigurable hardware devices can bridge the gap towards on-board processing of re-
motely sensed hyperspectral data and provide implementations that can significantly outperform the (optimized)
equivalent software versions of the considered endmember extraction algorithms.
Keywords: Hyperspectral image analysis, endmember extraction, pixel purity index (PPI), N-FINDR, field
programmable gate arrays (FPGAs).
1. INTRODUCTION
Hyperspectral imaging, also known as imaging spectroscopy, is a technique that has been widely used during
recent years in Earth and planetary remote sensing.
1
It generates hundreds of images, corresponding to different
wavelength channels, for the same area on the surface of the Earth. The concept of hyperspectral imaging
originated at NASA’s Jet Propulsion Laboratory in California, which developed instruments such as the Airborne
Imaging Spectrometer (AIS), then called AVIRIS (for Airborne Visible Infra-Red Imaging Spectrometer
2
). This
system is now able to cover the wavelength region from 400 to 2500 nanometers using 224 spectral channels,
at nominal spectral resolution of 10 nanometers. As a result, each pixel (considered as a vector) collected by a
hyperspectral instrument can be seen as a spectral signature or ‘fingerprint’ of the underlying materials within
the pixel (see Figure 1).
Further author information: (Send correspondence to Carlos Gonz´ alez)
Carlos Gonz´alez: carlosgonzalez@fdi.ucm.es, Daniel Mozos: mozos@fis.ucm.es, Javier Resano: jresano@unizar.es, Antonio
Plaza: aplaza@unex.es
High-Performance Computing in Remote Sensing, edited by Bormin Huang, Antonio J. Plaza,
Proc. of SPIE Vol. 8183, 81830F · © 2011 SPIE · CCC code: 0277-786X/11/$18 · doi: 10.1117/12.897384
Proc. of SPIE Vol. 8183 81830F-1