Hyperspectral Image Classification

Jonatan Gefen
 Introduction to classification
 Whole Pixel
 Subpixel Classification
 Linear Unmixing
 Matched Filtering (partial unmixing)
 More Classification techniques
Image Classification
Spatial Classification
Spectral Classification
 Spatial Image classification:
 Based on the structures in the
image (clear edges)
 Based on neighbor pixels
 Depends on the spatial resolution
 Can be done manually
 Spectral Image classification:
 Increase of information per pixel
 Increase of dimensionality
 Can’t be done manually (but can
be done Automatically)
 Based on spectral sig.
 Based on single pixel
Spectral Classification
Whole Pixel
Others (advanced)
Supervised / Unsupervised
 Based on known a priori through a combination of
fieldwork, map analysis, and personal experience
 On-screen selection of polygonal training data (ROI),
 On-screen seeding of training
 The seed program begins at a single x, y location
 Expands as long as it finds pixels with spectral similar to
the original seed pixel
 This is a very effective way of collecting homogeneous
training information
 From spectral library of field measurements
Whole Pixel classification
Assumes that each pixel contains
single material and noise
Tries to determine if a Target is in
the pixel
Whole Pixel classification
 Euclidean Distance
 Spectral Feature Fitting
 Tries to measure the
abundance of the Target in
the pixel
 Assumes that a pixel can
represent more than one
 Linear Unmixing
 Filter Match
Spectral classification
 Definitions:
 Target
 Endmember
 Infeasibility
Linear Unmixing
A model assumption that each pixel is a
Linear-Combination of materials

 ∗  + 
 – is the pixel value at band 
 – spectral value of the  endmember
 – the abundance factor of the  endmember
 – noise
Linear Unmixing
Linear Unmixing is trying to solve 
linear equations to find possible
endmembers and their fraction of the
 – the number of bands
General Linear Unmixing
 Minimizing:
 ,  =
 Find Least min square.

L1 Unmixing
 Assumes that all the elements are non negative.
 Minimizing:
called regulator
 Using NMF (Nonnegative matrix factorization)
NMF(original form)
  ,  =
 Algorithm:
  =   , 
  =   , 
   = 1  
  = .∗   ./(  + 10−9 )
  = .∗   ./(  + 10−9 ) (in our case already
Match Filter(Partial Unmixing)
 This technique is used to find specific Targets in the
image only user chosen targets are mapped.
 Matched Filtering “filters” the input image for good
matches to the chosen target spectrum
 The technique is best used on rare Targets in the
Match Filter(Partial Unmixing)
 Likelihood Ratio
 Using a threshold to decide if signal is present at the
Match Filter(Partial Unmixing)
 The Matched Filter result calculation:
 The T(x) will hold the MF value of the endmember at
pixel x if > 0 the endmember present.
MNF (Minimum Noise Fraction)
 Λ is a diagonal matrix containing the eigenvalues
corresponding to V
 MNF:
is the covariance matrix of the signal (generally
taken to be the covariance matrix of the image)
is the covariance matrix of the noise (can be
estimated using various procedures)
Match Filter(Partial Unmixing)
 Mixture-Tuned Matched Filtering
  − matched filter vector
  - MNF Covariance matrix
  − the target vector in MNF space
Match Filter(Partial Unmixing)
  − infeasibility value
  − the interpolated vector of
  − the target vector component
  - the MNF spectra for pixel
After filter result
More techniques
 Non-linear mixing
 Linear unmixing
 Non Linear unmixing
Sub-Pixel Summery
 Can allow search of item that is a very small part of a
given pixel
 Can give data about abundance of Targets
 Issues:
 Highly dependent on the contrast of the target to the
background of the pixel
 One potential problem with Matched Filtering is that it
is possible to end up with false positive results
More techniques
 Spatial-spectral classification
 N. Keshava - “A Survey of Spectral Unmixing Algorithms”
 P. Shippert, “Introduction to Hyperspectral Image Analysis” , Earth Science
Applications Specialist Research Systems, Inc.
Uttam Kumar, Norman Kerle , and Ramachandra T V – “Constrained
Linear Spectral Unmixing Technique for Regional Land Cover Mapping
Using MODIS Data”
Yuliya Tarabalka, Jón Atli Benediktsson , Jocelyn Chanussot, James C.
Tilton – “Hyperspectral Data Classification Using Spectral-Spatial
Jacob T. Mundt, David R. Streutker, Nancy F. Glenn – “PARTIAL
B. Ball, A. Brooks, A. Langville - Nonnegative matrix factorization
Z. Guo, T. Wittman and S. Osher - L1 Unmixing and its Application to
Hyperspectral Image Enhancement

similar documents