Image Classification: IntroductionLecture Notes 7

prepared by R. Lathrop 11/99

updated 3/04

Readings:

ERDAS Field Guide 5th Ed. CH. 6:217-234

Where in the World?

Learning objectives• Remote sensing science concepts

– Rationale and theory behind image classification– Image spectral vs. information classes– Unsupervised (ISODATA) algorithm– Clusterbusting

• Math Concepts– Calculating mage distance

• Skills– Applying ISODATA algorithm

Image Classification

One of the major applications of remotely sensed imagery is to provide information on the amount and spatial distribution of various types of land use and land cover

land cover - the biophysical material covering the land surface

land use - the use to which land is put by humans

Move toward more automated procedures using digital image processing to map land use-land cover

Computer-assisted classification of remotely sensed images

• Automatically categorize all pixels in an image into land cover classes or themes

Convert image data into information

• Normally uses multi-spectral data and spectral pattern recognition techniques as compared to spatial or temporal pattern recognition to aid in identification

Objective: Image to Thematic Map

Remotely Sensed Image Classification

• 1st step: identify classification scheme to be applied

• Hierarchical approach of increasing specificity Level I: most general

Level II: more specific• Level of classification depends on the spatial,

spectral, temporal and radiometric resolution of the image data

National Land Cover Dataset Classification system: 21 classes

• Water • 11 Open Water

12 Perennial Ice/Snow • Developed • 21 Low Intensity Residential

22 High Intensity Residential23 Commercial/Industrial/Transportation

• Barren • 31 Bare Rock/Sand/Clay

32 Quarries/Strip Mines/Gravel Pits33 Transitional

• Forested Upland • 41 Deciduous Forest

42 Evergreen Forest43 Mixed Forest

• Shrubland • 51 Shrubland• Non-Natural Woody • 61 Orchards/Vineyards/Other • Herbaceous Upland Natural/Semi-natural Vegetation • 71 Grasslands/Herbaceous • Herbaceous Planted/Cultivated • 81 Pasture/Hay

82 Row Crops83 Small Grains84 Fallow85 Urban/Recreational Grasses

• Wetlands • 91 Woody Wetlands

92 Emergent Herbaceous Wetlands http://landcover.usgs.gov/prodescription.asp

Feature Space Image

• Visualization of 2 bands of image data simultaneously through a 2 band scatterplot - the graph of the data file values of one band of data against the values of another band

• Feature space - abstract space that is defined by spectral units

Red Reflectance

NIRReflectance

Spectral Feature Space

Each dot represents a pixel; the warmer the colors, the higher the frequency of pixels in that portion of the feature space

Spectral Pattern Recognition

• Numerical process whereby elements of multi-spectral image data sets are categorized into a limited number of spectrally separable, discrete classes:

• 1) show (train) the computer the multiple spectral band data associated with land cover type of interest

• 2) the computer decides, using some form of classification decision rule, which land cover type each pixel most looks like

Red Reflectance

NIRReflectance

Grass

Trees

water

ImperviousSurface &Bare Soil

Spectral Feature Space

Classification can be thought of as trying to relate spectral classes or locations in the feature space with the appropriate information class

Spectral vs. Information Class

• Spectral class - group (cluster) of spectrally "like" pixels

• Information class - land use/land cover class of interest

• May take many spectral classes to describe one information class. One spectral class may represent more than 1 information class.

Spectral vs. Information Classes: May take many spectral classes to describe

one information class. One spectral class may represent more than 1 information class.

Spectral Class Information Class

Sunlit conifer Upland Conifer

Hillside shadowed conifers

Upland Deciduous

Deciduous broadleaf Lowland Deciduous

Spectral Classes: pixels of one land cover type tend to cluster together

Red reflectance

NIR

reflectance

Soil 1

Soil 2

Soil 3

Water 1

Water 2

Veg 1

Veg 2

Veg3

Adapted from J.A. Richards, 1986

Spectral vs. Information Classes

Red reflectance

NIR

reflectance

Soil 1

Soil 2

Soil 3

Water 1

Water 2

Veg 1

Veg 2

Veg3

Soil Information class

Adapted from J.A. Richards, 1986

Spectral & information classes do not always have a 1-to-1 match

Red reflectance

NIR

reflectance

Soil 1

Soil 2

Soil 3

Water 1

Water 2

Veg 1

Veg 2

Veg3

Same spectral class may belong to more than one information class

Adapted from J.A. Richards, 1986

Developed 1

Developed 2

Developed 3

Classification Process• 1) Training/Clustering Stage - the process of defining

criteria by which spectral patterns are recognized, developing a numerical description for each spectral class

• 2) Classification Stage - each pixel in the image data set is categorized into the spectral class it most closely resembles based on a mathematical decision rule

• 3) Output Stage - results are presented in a variety of forms (tables, graphics, etc.)

Multispectral classification

Multispectral image classification using spectral pattern recognition often relies on measuring the “likelihood” that a pixel belongs to one class vs. another. This likelihood generally relies on some measure of distance between a pixel and the various spectral classes clusters. For example, if a pixel is “closest” to Spectral Class 1 vs. Spectral Class2, then the pixel is classified into spectral Class 1.

Spectral distance can be measured in several ways:

- as simple euclidean distance in multispectral space

- as a statistical distance or probability

Spectral distance

• Spectral distance - the Euclidean distance in n-dimensional spectral space

• D = SQRT[(sum (dk - ek)2] where dk = BV of pixel d in band k

where ek = BV of pixel e in band k

• the equation is summed across k = 1 to n bands

What is the spectral distance between Pixel A and Cluster 1?

X

Y 92, 153

180, 85

Pixel A

Cluster 1

Spectral Distance example

Distance between [x1,y1] & [x2, y2][180, 85] & [92, 153]

D = SQRT[(sum (dk - ek)2]

D = SQRT[(180-92)2 + (85-153)2] = SQRT[(88)2 + (-68)2] = SQRT[7744 + 4624] = SQRT[12,368] = 111.2

Spectral Distance example

X

Y 92, 153

180, 85

Xd = 180 -92

Yd = 85-153

Supervised vs. Unsupervised Approaches

• Supervised - image analyst "supervises" the selection of spectral classes that represent patterns or land cover features that the analyst can recognize

Prior Decision

• Unsupervised - statistical "clustering" algorithms used to select spectral classes inherent to the data, more computer-automated

Posterior Decision

Supervised vs. Unsupervised

Red

NIR

Supervised Prior Decision: from Information classes in the Image to Spectral Classes in Feature Space

Unsupervised Posterior Decision: from Spectral Classes in Feature Space to Information Classes in the Image

Supervised vs. Unsupervised

Edit/evaluate signatures

Select Training fields

Classify image

Evaluate classification

Identify classes

Run clustering algorithm

Evaluate classification

Edit/evaluate signatures

ISODATA (Iterative Self-Organizing Data

Analysis Technique) Clustering Algorithm • User specified Input (as implemented in ERDAS)

• maximum number of clusters

• Initial allocation of cluster center locations

• maximum % of pixels whose class values are allowed to be unchanged between iterations.

• maximum number of iterations

• Other possible constraints (not implemented in ERDAS)

• minimum number of members in a cluster, if fall below threshold then that cluster eliminated

• maximum standard deviation: if the std dev exceeds the threshold then that cluster is split into two

• minimum distance between cluster means

Initial Cluster Allocation

• clusters allocated along the mean n-dimensional vector

• spaced according to std dev distance away from central mean

Red

NIR

Algorithm Operation• each pixel is compared to each cluster mean and

assigned to the cluster whose mean is closest in Euclidean distance ________________________________ \/(DNb1i-DNb1m)2 + ... + (DNbxi - DNbxm)2))

and a new cluster center is computed by averaging the locations of all the pixels assigned to that cluster.

•ISODATA: multiple iterations from initial allocation to final assignment

•The algorithm will stop either when the # iteration threshold is reached Or the max % of unchanged pixel threshold is reached

Red

NIR

Initial clusters Final clusters

Red

NIR

Adapted from Jensen 2nd ed, 1996

Example: ISODATA clustering

Distance between Unclassified Pixel Squared distance Sum Sqr Root

Band 4 Band 5 Band 4 Band 5Cluster 1 30-10 = 20 10-10 = 0 400 0 400 20Cluster 2 30-20 = 10 10-20 = -10 100 100 200 14Cluster 3 30-30 = 0 10-20 = -10 0 100 100 10

Unclassified Pixel Assigned to Cluster 3

2. Calculating new cluster means

- Cluster 1 & 2 unchanged

- Cluster 3 migrates to Band 4mean, Band 5mean = 30, 15

1. Assigning unclassified pixels to cluster means

Initial clusters: 1 (10,10), 2 (20,20) 3 (30,20)

Unclassified Pixel (30,10)

Example of Naturally Clustered Data

Adapted from Swain

Green Vegetation

Senesced Vegetation

Red

NIR

Red

NIR

Red

NIR

Red

NIR

Red

NIR

x

x x

x

x

x

x

x

Initial cluster centers

After 1st iteration

After 2nd iteration

Final cluster centers

Final Cluster Centers

Adapted from Swain

Green Vegetation

Senesced Vegetation

Red

NIR

X

X

Red Reflectance

NI

R

Re f l e c tance

Grass

Trees

water

Impervious Surface & Bare Soil

Spectral Feature Space

In spectral feature space, generally no distinct, isolated clusters, rather a continuous gradient. Classification can be thought of as trying to subdivide the feature space into appropriate spectral regions

Algorithm Operation• The objective is to minimize the Sum of Squared Errors

(SSE) across the entire set of clusters and the original pixel data

• The Sum of Squared Errors (SSE): is the cumulative squared difference (i.e., spectral distance across all the various bands) of each pixel from its assigned cluster center

• An optimal arrangement has been reached that minimizes the distance between every pixel and a cluster center (based on that number of clusters)

HWK Example: SSE calculationInitial clusters (2,1) & (4,2) 1st iteration

X Y DistA DistB SSE

1 2 1.41 3.00 2.0

2 3 2.00 2.24 4.0

2 4 3.00 2.83 8.0

3 4 3.16 2.24 5.0

4 3 2.83 1.00 1.0

4 4 3.60 2.00 4.0

4 6 5.38 4.00 16.0

5 7 6.71 5.10 26.0

6 5 5.66 3.60 13.0 = 79

New cluster centers (1.5, 2.5)

(4, 4.6)

Post-clustering Assignment

• The analyst must then assign each spectral cluster to an information class based on available ancillary information (e.g., field reference data, maps, aerial photos, analyst experience) Posterior Decision process

• If one and only one information class can not be unequivocally assigned to a cluster then assign the cluster to a “mixed” class

Post Clustering Assignment: what information class can be assigned to each spectral cluster?

Red

NIR

Adapted from Jensen 2nd ed, 1996

31:Bare rock

84:fallow

71:grass

11:water

42 evergreen forest

41:decidous forest

33:transitional

91:wetlands

21:low intensity residential

23: Commercial

32: Quarries

22: high intensity residential

ISODATA Clustering: Pros

• clustering not geographically biased to any particular portion of the image

• highly successful at finding inherent spectral clusters

• results similar to a minimum-distance-to-means classifier

ISODATA Clustering: Cons

• analyst doesn’t know a priori number of spectral classes

• number of iterations needed, can be time consuming

• does not account for pixel spatial homogeneity

• Insensitive to variance/covariance

Cluster-busting• technique to iteratively “bust up” spectrally “mixed”

classes

• separate “good” vs. “bad” classified pixels into a binary mask

• mask out the “good” image, extract the “bad” image data and re-run the unsupervised process

• re-evaluate new clusters, keep good, toss out “bad”, cluster bust again

• create final cluster map by using a GIS overlay with a maximum dominate function

Cluster-busting: in feature space

Red

NIR

Red

NIR

Cluster-busting: in geographic space- separate “good” vs. “bad” classified pixels into a binary mask- mask out the “good” (green) image- extract the “bad”(red) image data - re-run the unsupervised process

Cluster-busting- re-evaluate new clusters, keep good, toss out “bad”, cluster bust again (if needed)- create final cluster map by using a GIS overlay with a maximum dominate function

Overlay

Cluster busting

Recode

“good” class(es) = 0

“bad” class(es) > 1

Mask original image file

Cluster bustingNew clusters = the holes

Old clusters – “bad” = swiss cheese

Overlay