Particle%20Swarm%20Optimization-based%20Dimensionality%20Reduction%20for%20Hyperspectral%20Image%20Classification

1
Particle Swarm Optimization-based Dimensionality
Reduction for Hyperspectral Image Classification

• He Yang, Jenny Q. Du
• Department of Electrical and Computer Engineering
• Mississippi State University, MS 39762, USA

2
Outline

• ? Motivation
• ? Existing band selection approaches
• ? Unsupervised band selection
• ? Supervised band selection
• ? Particle swarm optimization (PSO)
• ? PSO for hyperspectral band selection
• ? Experimental results
• ? Conclusion

3
Motivation

• ? The vast data volume of hyperspectral imagery
  brings about problems in data transmission and
  storage. In particular, the very high data
  dimensionality presents a challenge to many
  traditional image analysis algorithms.
• ? One approach of reducing the data
  dimensionality is to transform the data onto a
  low-dimensional space using certain criteria
  (e.g., PCA, LDA). But these methods usually
  change the physical meaning of the original data
  since the channels in the low-dimensional space
  do not correspond to individual original bands
  but their linear combinations.
• ? Another dimensionality reduction approach is
  band selection. It is to select a subset of the
  original bands without losing their physical
  meaning.

4
Motivation (Contd)

• ? In terms of object information availability,
  band selection techniques can be divided into two
  categories supervised and unsupervised.
  Supervised methods are to preserve the desired
  object information, which is known a priori
  while unsupervised methods do not assume any
  object information.
• ? Supervised techniques clearly aim at
  selecting the bands that include important object
  information and the selected bands can provide
  better detection or classification than those
  from unsupervised techniques. When the prior
  knowledge is unavailable, we have to apply an
  unsupervised method that can generally offer good
  performance regardless of the objects to be
  detected or classified in the following step.

5
Motivation (Contd)

• ? In this research, dimensionality reduction is
  achieved by supervised band selection, and we
  propose to use particle swarm optimization (PSO)
  in conjunction with simple but effective
  objective functions for optimal band searching.
• ? We will demonstrate that using data
  dimensionality reduction as a pre-processing
  step, support vector machine (SVM)-based
  classification accuracy (either before or after
  decision fusion) can be greatly improved.

6
Unsupervised Band Selection

• ? The basic idea of an unsupervised band
  selection is to select distinctive and
  informative bands.
• ? Information Entropy
• ? First Spectral Derivative
• ? Second Spectral Derivative
• ? Spectral Angle
• ? Spectral Correlation
• ? Uniform Spectral Spacing
• ? Unsupervised band selection can be achieved by
  evaluating band similarity.
• ? Q. Du and H. Yang, Similarity-based
  unsupervised band selection for hyperspectral
  image analysis, IEEE Geoscience and Remote
  Sensing Letters, vol. 5, no. 4, pp. 564-568, Oct.
  2008.
• ? H. Yang, Q. Du, and G. Chen, Unsupervised
  hyperspectral band selection using graphics
  processing units, IEEE Journal of Selected
  Topics in Earth Observation and Remote Sensing,
  vol. 4, no. 3, July 2011.

7
Supervised Band Selection

• ? When class information is known, supervised
  band selection is applied to preserve the desired
  object information.
• ? A supervised band selection algorithm
  maximizes class separability when a subset of
  bands is selected.
• ? Class separability may be measured with
• - Divergence
• - Transformed divergence
• - Bhattacharyya distance
• - Jeffries-Matusita (JM) distance
• ? Recently, we proposed a new metric based on
  minimum endmember abundance covariance (MEAC).
• ? H. Yang, Q. Du, H. Su, and Y. Sheng, An
  efficient method for supervised hyperspectral
  band selection, IEEE Geoscience and Remote
  Sensing Letters, vol. 8, no. 1, pp. 138-142, Jan.
  2011.

8
Band Searching

• ? To avoid testing all the possible band
  combinations, subset searching strategies can be
  used
• ? Sequential forward selection (SFS)
• ? Sequential forward floating selection (SFFS)
• ? Branch and Bound
• ? An advanced but simple searching strategy is
  particle swarm optimization (PSO).

9
Particle Swarm Optimization

• ? PSO is a computational optimization technique
  developed by Kennedy and Eberhart in 1995. It
  uses a simple mechanism that mimics swarm
  behavior in birds flocking and fish schooling to
  guide the particles to search for global optimal
  solutions.
• ? PSO is proved to be a very efficient
  optimization algorithm by searching an entire
  high-dimensional problem space.
• ? PSO does not use the gradient of the problem
  being optimized, so it does not require that the
  optimization problem be differential as required
  by classic optimization methods. PSO can be
  useful for optimization of irregular problems.

10
Iteration 1
Iteration 25
Iteration 50
Iteration 75
? PSO is used to search the solution of
. ? The initial
particles are spread sparsely in the whole
problem space in iteration 1. ? The particles
start to be pulled by the update procedure to the
optimal regions from iteration 25 to iteration
75. ? All the particles are gathered at the
optimum point by the updating procedure.
11
PSO for Band Selection

• ? Assume p bands are to be selected. Let a
  particle xid (of size p1) denote the selected
  band indices, and vid the update for selected
  band indices. The historically best local
  solution is vid, and the historically best global
  solution among all the particles is pgd.
  
• Particle update
• ? It calculates the new velocity for each
  particle based on the previous velocity vid, the
  particles location (pid) that it has reached so
  far so best for the objective function, and the
  particles location among the global searched
  solutions (pgd) that has reached so far so best.
• Particles are updated as
• ? c1 and c2 control the contributions from local
  and global solutions respectively, r1 and r2 are
  independent random variables and w is used as
  the scalar of previous velocity vid in particle
  update.

12
PSO for Band Selection
? Algorithm 1. Assume p bands are to be
selected. Randomly initialize M particles xid,
and each particle includes p indices of the bands
to be selected. 2. Evaluate the objective
function for each particle, and determine the
local and global optimal solution pid and pgd
respectively. 3. Update all the particles. 4. If
the algorithm is converged, then stop otherwise,
go to step 2. 5. The particle yielding the global
optimum solution pgd is the final result.
? Objective function
? MEAC
? JM distance
13
Illustration of PSO-based band selection (Selectin
g 6 bands from L bands)
14
Convergence curves of PSO-based band selection
(MEAC)
15
Convergence curve of PSO-based band selection (JM
distance)
16
Decision Fusion
Hyperspectral Image Data
Supervised classifier (SVM)
Unsupervised classifier (Kmeans, Mean-Shift)
Use unsupervised result to segment supervised
result
(Weighted) Majority Voting
Final Decision
? H. Yang, Q. Du, and B. Ma, Decision fusion on
supervised and unsupervised classifiers for
hyperspectral imagery, IEEE Geoscience and
Remote Sensing Letters, vol. 7, no. 4, pp.
875-879, Oct. 2010.
17
Experiments

• ? The hyperspectral data used in the experiments
  was taken by the airborne Hyperspectral Digital
  Imagery Collection Experiment (HYDICE) sensor. It
  was collected for the Mall in Washington, DC with
  210 bands covering 0.4-2.4 µm spectral region.
  The water-absorption bands were deleted,
  resulting in 191 bands. The original data has
  1280307 pixels.
• ? Another hyperspectral data used in the
  experiments was the 126-band HyMap data about a
  residential area near the campus of Purdue
  University. The image size is 377512.

18
HYDICE Experiment

• six classes road, grass, shadow, trail, tree,
  roof

19
HYDICE Experiment
Training Test
Road 55 892
Grass 57 910
Shadow 50 567
Trail 46 624
Tree 49 656
Roof 52 1123
20

• SVM classification accuracy using MEAC-selected
  bands
• in the HYDICE experiment

21

• SVM classification accuracy using JM-selected
  bands
• in the HYDICE experiment

22
SVM
Mean-Shift

• Majority-voting Fused result

Road Grass
Shadow Trail Tree Roof
23
Classification accuracy from different methods in
HYDICE experiment (with 6 bands or 6 PCs)
Road Grass Shadow Trail Tree Roof OA AA Kappa
svm(pca) 99.0 98.6 82.0 92.3 98.8 84.8 92.6 92.6 91.1
svm(pso) 98.1 98.9 94.7 92.5 99.4 95.4 96.6 96.5 95.9
svm(pca)ms 100.0 99.0 81.3 94.9 98.9 89.3 94.3 93.9 93.0
svm(pso)ms 90.7 99.0 100.0 100.0 98.9 98.9 97.5 97.9 97.0
svm(pca)kmeans 99.9 96.9 75.7 96.6 98.8 95.3 94.8 93.9 93.6
svm(pso)kmeans 94.8 99.2 98.9 99.7 95.9 99.3 97.9 98.0 97.5
24
HyMap Experiment

• six classes road, grass, shadow, soil, tree, roof

25
HyMap Experiment
Training Test
Road 73 1231
Grass 72 1072
Shadow 49 215
Soil 69 380
Tree 67 1321
Roof 74 1244
26

• SVM classification accuracy using MEAC-selected
  bands
• in the HyMap experiment

27

• SVM classification accuracy using JM-selected
  bands
• in the HyMap experiment

28
SVM
Mean-Shift

• Majority-volting Fused result

Road Grass
Shadow Soil Tree Roof
29
Classification accuracy from different methods in
HyMap experiment (with 6 bands or 6 PCs)
Road Grass Shadow Soil Tree Roof OA AA Kappa
svm(pca) 92.4 98.9 97.2 90.8 96.4 81.4 92.2 92.8 90.3
svm(pso) 94.9 98.3 98.1 85.2 93.9 89.6 93.6 93.3 91.9
svm(pca)ms 96.3 100.0 98.1 100.0 97.7 85.5 95.2 96.3 94.0
svm(pso)ms 97.3 96.0 100.0 98.7 98.9 100.0 98.2 98.5 97.7
svm(pca)kmeans 99.2 99.7 86.9 71.7 98.7 81.8 92.9 89.7 91.0
svm(pso)kmeans 96.1 96.6 95.9 98.1 99.5 98.2 97.6 97.4 96.9
30
Conclusion

• ? The experimental results demonstrate that PSO
  can greatly improve band selection performance in
  terms of SVM classification accuracy, compared to
  the frequently used SFS and SFFS searching
  strategies. The classification improvement can be
  magnified through decision fusion.
• ? The searching criterion called MEAC without
  requiring training samples is considered more
  advanced than the JM distance. In the SFS
  searching, the JM performance is much worse than
  MEAC however, after using PSO searching, its
  performance can be as good as MEAC. This means
  the employed searching strategy does play an
  important role in band selection performance.