EOS 740 Hyperspectral Imaging Systems

1
EOS 740 - Hyperspectral Imaging Systems
Class Instructors Dr. Richard B.
Gomez rgomez_at_gmu.edu Dr. Ronald G.
Resmini ronald.g.resmini_at_boeing.com
LECTURE 8 (25 March 05)
George Mason University School of Computational
Sciences Spring Semester 2005 28 January 6 May
2
Outline

• Homework
• Review (very briefly!)
• Some more ENVI Functionality
• Scatter plots
• ROIs
• Spectral Mixture Analysis (SMA)
• The mixed pixel
• OSP/LPD/DSR/other...
• NP Detection Theory
• Spectral matched filters more detail
• How are your projects going?

3
Homework
Read the Schmidt and Skidmore (2003) paper.

• Interesting findings and conclusions
• A study based on spectroscopy thinking about
  spectral data
• A study on vegetation RS an important topic
• Vegetation spectra are challenging thinking
  about spectra
• Good introductory comments frames problem/issues
  well
• Lots of spectral signatures are shown
• Introduces continuum removal (in ENVI)
• Introduces JM and B distances (in ENVI)
• Use of alternate techniques wavelet smoothing
  (not in ENVI), statistics
• Methodologies employed are good topics for
  discussion
• A fairly brief paper published in a respected,
  prestigious scientific journal
• Table 2 a confusion matrix-like data structure
• Not all HSI RS studies require data cubes and ENVI

4
Review

• Review of ELM
• Other techniques uncertainties
• Principal Components Analysis (PCA)
• Data statistics
• Spectral Mixture Analysis (SMA)
• The mixed pixel introduction
• The ENVI Matched Filter introduction

5
A Day at the Office with HSI and ENVI

• Given
• See/have completed RS problem actions (see Feb.
  25 notes)
• Checklists (data and sensor see Feb. 25, 2005
  notes...)
• Youre given an HSI cube the fun begins!
• Open it/import it in ENVI
• Look at the data spectra, animation, interactive
  stretching, statistics
• Apply a PCA and/or MNF inspect results, link,
  mouse about
• What are you to do with the data? Devise a
  strategy.
• Gather ancillary information build/acquire
  spectral library(ies)
• Apply atmospheric compensation this may be (is!)
  iterative
• Look at the data spectra, animation, interactive
  stretching, statistics
• Apply algorithms SAM, ED, MF, SMA, other this
  is iterativelink mouse about
• In-scene spectra, library spectra
• Apply fusion with ancillary data and information
• Problem not solved? May have to resort to other
  techniques...
• Build products/reports

6
A Progression
Traditional MSI Classification Methods
7
The Mixed Pixel Spectral Mixture Analysis (SMA)
8

• The mixed pixel
• a basis concept a very important
  conceptdescription of a mixed pixel
• determining quantity of material
• building a mixed pixel - spectral math
• building a mixed pixel - MS Excel
• mixing trends in hyperspace

9

• Linear spectral mixture analysis
• applications
• scene characterization
• material mapping
• anomaly detection
• other...

10
Linear Spectral Unmixing
The reflectance of an image pixel is a linear
combination of reflectances from (typically)
several pure substances (or endmembers)
contained within the ground-spot sampled by
the remote sensing system
where Ri is the reflectance of a pixel in band
i, fj is the fractional abundance of endmember j
in the pixel, Mj,i is the reflectance of
endmember substance j in band i, ri is the
unmodeled reflectance for the pixel in band i,
and n is the number of endmembers.
11
Linear Spectral Unmixing Theory
Spectral unmixing theory states that the
reflectance of an image pixel is a linear
combination of reflectances from the (typically)
several pure substances (or endmembers)
contained within the ground-spot sampled by the
remote sensing system. This is indicated below
where Ri is the reflectance of a pixel in band
i, fj is the fractional abundance of substance
(or endmember) j in the pixel, and Mj,i is the
reflectance of endmember substance j in band i.
ri is the band-residual or unmodeled reflectance
for the pixel in band i, and n is the number of
endmembers. A spectral unmixing analysis results
in n fraction-plane images showing the
quantitative areal distribution of each of the
endmember substances and one root mean squared
(RMS) image showing an overall or global goodness
of fit of the suite of endmembers for each pixel.
The RMS image is formed, on a pixel-by-pixel
basis, by
Objects may also be detected as anomalies in the
RMS image.
12
Spectral Mixture Analysis (SMA)

• An area of ground of, say 1.5 m by 1.5 m may
  contain 3 materials A, B. and C.
• An HSI sensor with a GSD of 1.5 m would measure
  the Mixture spectrum
• SMA is an inversion technique to determine the
  quantities of A, B, and Cin the Mixture
  spectrum
• SMA is physically-based on the spectral
  interaction of photons of light and matter
• SMA is in widespread use today in all sectors
  utilizing spectral remote sensing
• Variations include different constraints on the
  inversion linear SMA nonlinear SMA

13

• Endmember selection
• manual
• convex hull
• Pixel-Purity Index (PPI)
• adaptive/updating/pruning...
• other (e.g., N-FINDR, ORASIS,URSSA, etc...)
• wild outliers

14

• Unmixing inversion
• interpretation of results
• RMS, RSS, algebraic and geometricinterpretations
• are RMS, RSS, etc. the best measures?
• residual correlation analysis (RCA)
• band residual cube
• can we build a band residual cubewith ENVI?

15

• iterative process
• the inversion in Matlab a closer lookat the
  math
• fraction-plane color-composites
• change detection with fraction planes
• constraints on inversion
• is it a linear mixture?

16

• application strategies (i.e., in-scenespectra/lib
  rary spectra)
• directed search? anomaly detection?
• Shade/shadow
• shade endmember
• shade removal
• Other...
• objective endmember determinationTompkins et al.

17

• Non-linear spectral mixture analysis
• checker-board mixtures
• intimate mixtures
• building a non-linear mixture
• spectral transformations (e.g., SSA)and use of
  ENVI

18
A linear equation...
x
A
b
5 endmembers in a 7-band spectral data set
19
MS Excel and Matlab Commands
s1, s2, and s3 are column vectors Ms1, s2,
s3 x0.25 0.35 0.40T b0.25s10.35s20.40s3
Copy/paste s1, s2, s3, b into Matlab As1 s2
s3 xinv(AA)Ab
20
Prelude to Other Algorithms Statistical Spectral
Matched Filters OSP OBS

• Orthogonal Subspace Projection (OSP)
• Derivation in detail (next several slides...)
• Application of the filter
• Endmembers
• Statistics
• Interpretation of results
• OSP w/endmembers unconstrained SMA
• Different ways to apply the filter/application
  strategies(i.e., in-scene spectra/library
  spectra)

21
OSP/LPD/DSR Scene-Derived Endmembers
(Harsanyi et al., 1994 see also ch. 3 of Chang,
2003)
22
(No Transcript)
23
(No Transcript)
24
The value of xT which maximizes l is given by xT
dT
This is equivalent to Unconstrained SMA
25
MS Excel and Matlab Commands
s1, s2, and d are column vectors Ms1, s2,
d x0.25 0.35 0.40T r0.25s10.35s20.40d Co
py/paste s1, s2, d, r into Matlab Us1
s2 Ieye(348) P(I-Upinv(U)) qdP this
is actually qT qr qd (qr)/(qd)
26
Statistical Characterization of the
Background (LPD/DSR)
(Harsanyi et al., 1994)
27
(No Transcript)
28

• The statistical spectral matched filter (SSMF)
• Derivation in detail
• Application of the filter
• Statistics
• Endmembers (FBA/MCEM)
• Interpretation of results
• Many algorithms are actually the basic SSMF
• Different ways to apply the filter/application
  strategies(i.e., in-scene spectra/library
  spectra)
• Matched filter in ENVI

29
Constrained Energy Minimization (CEM)

• The description of CEM is similar to that of
  OSP/DSR (previous slides)
• Like OSP and DSR, CEM is an Orthogonal Subspace
  Projection (OSP)family algorithm
• CEM differs from OSP/DSR in the following,
  important ways
• CEM does not simply project away the first n
  eigenvectors
• The CEM operator is built using a weighted
  combination of theeigenvectors (all or a subset)
• Though an OSP algorithm, the structure of CEM is
  equally readily observed bya formal derivation
  using a Lagrange multiplier

• CEM is a commonly used statistical spectral
  matched filter
• CEM for spectral remote sensing has been
  published on for over 10 years
• CEM has a much longer history in the
  multi-dimensional/array signalprocessing
  literature
• Just about all HSI tools today contain CEM or a
  variant of CEM
• If an algorithm is using M-1d as the heart of its
  filter kernel (where M is thedata covariance
  matrix and d is the spectrum of the target of
  interest), thenthat algorithm is simply a CEM
  variant

30
Derivation taken from
Stocker, A.D., Reed, I.S., and Yu, X., (1990).
Multi-dimensional signal processing for
electro-Optical target detection. In Signal
and Data Processing of Small Targets 1990,
Proceedingsof the SPIE, v. 1305, pp. 218-231.
J of Bands
Form the log-likelihood ratio test of Hº and H1
31
Some algebra...
32
A trick...recast as a univariable problem
After lots of simple algebra applied to the r.h.s
Now, go back to matrix-vector notation
33
Take the natural log
34
The vector QTx is a projection of the original
spectraldata onto the eigenvectors of the
covariance matrix, M, which corresponds to the
principal axes of clutterdistribution. Stocker
et al., 1990.
35
Further SCR gain is obtained by forming the
optimumweighted combination of principal
components usingthe weight vector
Direct quote from Stocker et al., 1990.
36
Constrained Energy Minimization (CEM)
(Harsanyi et al., 1994)
37
(No Transcript)
38
An Endnote...

• Previous techniques exploit shape and albedo
• this can cause problems...
• Sub-classes of algorithms developed to mitigate
  this
• shape, only, operators
• MED, RSD of ASIT, Inc.
• MTMF of ENVI (ITT/RSI)

39
Another Endnote...

• Performance prediction/scoring/NP-Theory, etc...
• Hybrid techniques
• still some cream to be skimmed...
• Caveat emptor...
• lots of reproduction of work already accomplished
• who invented what? when?
• waste of resources
• please do your homework!read the lit.!

40
Backup Slides
41
A Bit More RT...
42
A key point
Apply lots of simple algebra
43
Lagrange Multiplier Derivation of CEM Filter
Minimizing E is equivalent to minimizing each yi2
(for k 1, 2, 3, ... )
44
In Matrix Notation
45
(No Transcript)