Image Classification
Why classify? Make sense of a landscape Place landscape into categories (classes) Forest, Agriculture, Water, etc Classification scheme = structure of classes Depends on needs of users
Example Uses
Provide context Landscape planning or assessment Research projects Drive models Global carbon budgets Meteorology Biodiversity
Example: Near Marys Peak
Derived from a 1988 Landsat TM image
Distinguish types of forest
Classification: Critical Point
LAND COVER not necessarily equivalent to LAND USE We focus on whats there: LAND COVER Many users are interested in how whats there is being used: LAND USE Example Grass is land cover; pasture and recreational parks are land uses of grass
Classification
TODAYS PLAN
Basic strategy for classifying remotelysensed images using spectral information
Supervised Classification
Unsupervised Classification
Lab 4
Next class: Important considerations when classifying; improving classifications; assessing accuracy of classified maps
Basic Strategy: How do you do it?
Use radiometric properties of remote sensor Different objects have different spectral signatures
40 35 30 25 20 15 10 5 0 Band 1 Band 2 Band 3 Band 4 Band 5 Band 7 Vegetation Soil
Basic Strategy: How do you do it?
In an easy world, all Vegetation pixels would have exactly the same spectral signature Then we could just say that any pixel in an image with that signature was vegetation Wed do the same for soil, etc. and end up with a map of classes
Basic Strategy: How do you do it? But in reality, that isnt the case. Looking at several pixels with vegetation, youd see variety in spectral signatures.
40 35 30 25 20 15 10 5 0 Band 1 Band 2 Band 3 Band 4 Band 5 Band 7 Veg 1 Veg 2 Veg 2 Veg 3 Veg 4 Veg 5 Veg 6 Veg 7
The same would happen for other types of pixels, as well.
The Classification Trick: Deal with variability
Different ways of dealing with the variability lead to different ways of classifying images To talk about this, we need to look at spectral signatures a little differently
40 35 30 25 20 15 10 5 0 Band 1 Band 2 Band 3 Band 4 Band 5 Band 7 Vegetation Soil
Think of a pixels reflectance in 2-dimensional space. The pixel occupies a point in that space. The vegetation pixel and the soil pixels occupy different points in 2-d space
40 35 30 25 20 15 10 5 0 0 5 10 Band 3 15 20
Band 4
Vegetation Soil
In a Landsat scene, instead of two dimensions, we have six spectral dimensions Each pixel represents a point in 6-dimensional space To be generic to any sensor, we say n-dimensional space For examples that follow, we use 2-d space to illustrate, but principles apply to any n-dimensional space
Feature space image
A graphical representation of the pixels by plotting 2 bands vs. each other For a 6-band Landsat image, there are 15 feature space images
Band 4
Band 3
Basic Strategy: Dealing with variability
45 40 35 30 25 20 15 10 5 0 Band 1 Band 2 Band 3 Band 4 Band 5
45 40 35 30
With variability, the vegetation pixels now occupy a region, not a point, of n-dimensional space
Band 7
Band 4
25 20 15 10 5 0 0 2 4 6 8 10 Band 3 12 14 16 18 20
Soil pixels occupy a different region of ndimensional space
Basic strategy: Dealing with variability
Classification: Delineate boundaries of classes in ndimensional space Assign class names to pixels using those boundaries
45 40 35 30
Band 4
25 20 15 10 5 0 0 2 4 6 8 10 Band 3 12 14 16 18 20
Classification Strategies
Two basic strategies Supervised classification We impose our perceptions on the spectral data Unsupervised classification Spectral data imposes constraints on our interpretation
Supervised Classification
Supervised classification requires the analyst to select training areas where he/she knows what is on the ground and then digitize a polygon within that area
The computer then creates...
Mean Spectral Signatures
Conifer
Known Conifer Area
Water
Known Water Area
Deciduous
Known Deciduous Area Digital Image
Supervised Classification
Mean Spectral Signatures
Conifer
Multispectral Image
Information (Classified Image)
Deciduous
Water
Unknown
Spectral Signature of Next Pixel to be Classified
The Result is Information--in this case a Land Cover map...
Land Cover Map
Legend: Water Conifer Deciduous
Supervised Classification
Common Classifiers: Parallelpiped Minimum distance to mean Maximum likelihood
Supervised Classification
Parallelepiped Approach Pros: Simple Makes few assumptions about character of the classes
45 40 35 30
Band 4
25 20 15 10 5 0 0 2 4 6 8 10 Band 3 12 14 16 18 20
Supervised Classification
Cons: When we look at all the pixels in image, we find that they cover a continuous region in ndimensional space: the parallelepiped approach may not be able to classify those regions
Band 4
Band 3
Supervised Classification
Cons: Parallelepipeds are rectangular, but spectral space is diagonal, so classes may overlap
Band 4
Band 3
Supervised Classification: Statistical Approaches
Minimum distance to mean Find mean value of pixels of training sets in n-dimensional space All pixels in image classified according to the class mean to which they are closest
45 40 35 30
Band 4
25 20 15 10 5 0 0 2 4 6 8 10 Band 3 12 14 16 18 20
Supervised Classification: Minimum Distance
Band 4
All pixels below line called soil
Band 3
Supervised Classification: Minimum Distance
Minimum distance Pros: All regions of n-dimensional space are classified Allows for diagonal boundaries (and hence no overlap of classes)
Supervised Classification
Minimum distance Con: Assumes that spectral variability is same in all directions, which is not the case
Band 4
Band 3 For most pixels, Band 4 is much more variable than Band 3
Supervised Classification: Maximum Likelihood
Maximum likelihood classification: another statistical approach Assume multivariate normal distributions of pixels within classes For each class, build a discriminant function For each pixel in the image, this function calculates the probability that the pixel is a member of that class Takes into account mean and covariance of training set Each pixel is assigned to the class for which it has the highest probability of membership
Maximum Likelihood Classifier
Mean Signature 1 Candidate Pixel Mean Signature 2
It appears that the candidate pixel is closest to Signature 1. However, when we consider the variance around the signatures
Blue
Green
Red
Near-IR
Mid-IR
Maximum Likelihood Classifier
Mean Signature 1 Candidate Pixel Mean Signature 2
The candidate pixel clearly belongs to the signature 2 group.
Blue
Green
Red
Near-IR
Mid-IR
Supervised Classification
Maximum likelihood Pro: Most sophisticated; achieves good separation of classes Con: Requires strong training set to accurately describe mean and covariance structure of classes
Supervised Classification
In addition to classified image, you can construct a distance image For each pixel, calculate the distance between its position in n-dimensional space and the center of class in which it is placed Regions poorly represented in the training dataset will likely be relatively far from class center points May give an indication of how well your training set samples the landscape
Supervised Classification
Some advanced techniques Neural networks Use flexible, not-necessarily-linear functions to partition spectral space Contextual classifiers Incorporate spatial or temporal conditions Linear regression Instead of discrete classes, apply proportional values of classes to each pixel; ie. 30% forest + 70% grass
Unsupervised Classification
Recall: In unsupervised classification, the spectral data imposes constraints on our interpretation How? Rather than defining training sets and carving out pieces of n-dimensional space, we define no classes beforehand and instead use statistical approaches to divide the n-dimensional space into clusters with the best separation After the fact, we assign class names to those clusters
Unsupervised Classification
The analyst requests the computer to examine the image and extract a number of spectrally distinct clusters Spectrally Distinct Clusters
Cluster 3 Cluster 6
Cluster 5
Cluster 2
Cluster 1
Cluster 4
Digital Image
Unsupervised Classification
Saved Clusters
Cluster 3 Cluster 6
Output Classified Image
Cluster 5
Cluster 2
Next Pixel to be Classified
Cluster 1
Cluster 4 Unknown
Unsupervised Classification
The result of the unsupervised classification is not yet information until The analyst determines the ground cover for each of the clusters
???
Water Water
??? ??? ???
??? ???
Conifer
Conifer Hardwood Hardwood
Unsupervised Classification
It is a simple process to regroup (recode) the clusters into meaningful information classes (the legend).
Labels
Water Water Conifer Conifer
The result is essentially the same as that of the supervised classification:
Land Cover Map
Legend Water
Conif.
Hardw.
Hardwood
Hardwood
Unsupervised Classification
Pros Takes maximum advantage of spectral variability in an image Cons The maximally-separable clusters in spectral space may not match our perception of the important classes on the landscape
ISODATA -- A Special Case of Minimum Distance Clustering
Iterative Self-Organizing Data Analysis Technique Parameters you must enter include: N - the maximum number of clusters that you want T - a convergence threshold and M - the maximum number of iterations to be performed.
ISODATA Procedure
N arbitrary cluster means are established, The image is classified using a minimum distance classifier A new mean for each cluster is calculated The image is classified again using the new cluster means Another new mean for each cluster is calculated The image is classified again...
ISODATA Procedure
After each iteration, the algorithm calculates the percentage of pixels that remained in the same cluster between iterations When this percentage exceeds T (convergence threshold), the program stops or If the convergence threshold is never met, the program will continue for M iterations and then stop.
ISODATA Pros and Cons
Not biased to the top pixels in the image (as sequential clustering can be) Non-parametric--data does not need to be normally distributed Very successful at finding the true clusters within the data if enough iterations are allowed Cluster signatures saved from ISODATA are easily incorporated and manipulated along with (supervised) spectral signatures Slowest (by far) of the clustering procedures.
Unsupervised Classification
Critical issue: where to place initial k cluster centers
Along diagonal axis
Along principal axis
Unsupervised Classification
Important issue: How to distribute cluster centers along axis
Distribute normally Distribute at tails of distribution
Unsupervised Classification
After iterations finish, youre left with a map of distributions of pixels in the clusters How do you assign class names to clusters? Requires some knowledge of the landscape Ancillary data useful, if not critical (aerial photos, personal knowledge, etc.) Covered in more depth in the Lab 4
Unsupervised Classification
Alternatives to ISODATA approach K-means algorithm assumes that the number of clusters is known a priori, while ISODATA allows for different number of clusters Non-iterative Identify areas with smooth texture Define cluster centers according to first occurrence in image of smooth areas Agglomerative hierarchical Group two pixels closest together in spectral space Recalculate position as mean of those two; group Group next two closest pixels/groups Repeat until each pixel grouped
Classification: Summary
Use spectral (radiometric) differences to distinguish objects Land cover not necessarily equivalent to land use Supervised classification Training areas characterize spectral properties of classes Assign other pixels to classes by matching with spectral properties of training sets Unsupervised classification Maximize separability of clusters Assign class names to clusters after classification
Spectral Clusters and Spectral Signatures
Recall that clusters are spectrally distinct and signatures are informationally distinct When using the supervised procedure, the analyst must ensure that the informationally distinct signatures are spectrally distinct When using the unsupervised procedure, the analyst must supply the spectrally distinct clusters with information (label the clusters).
Spectrally Distinct Signatures
Most image processing software have a set of programs which allow you to: Graphically view the spectral signatures Compute a distance matrix (measuring the spectral distance between all pairs of signature means) Analyze statistics and histograms etc... After you analyze the signatures, the software should allow you to: Modify merge or delete any signatures Remember--they must be spectrally distinct! Finally, you can then classify the imagery (using a maximum likelihood classifier).
Evaluating Signatures--Signature Plots
Evaluating Signatures--Signature Ellipses
Evaluating Signatures--Signature Ellipses
Classification -- Final Thoughts
Classifications are never complete -- they end when time and money run out Classification is iterative -- its tough to get it right the first few iterations Consider a hybrid classification -- part supervised, part unsupervised Manual Classification and/or Editing is not cheating!
Classification
References: ERDAS Online Help Lillesand and Kiefer (at SLC): Chapter 7 Richards, John. Remote Sensing Digital Image Analysis: An introduction. 2nd Edition. 1993. SpringVerlag, Berlin: Chapters 8 and 9
Lab 4: Classification
Work in groups Some groups use 1999 image, some use 1988 image: assigned today Reference photos will be on reserve at SLC, in Peavy 252 5 sets of aerial photo stereo pairs under FOR 420/520 June 1993 photography Lab due: Oct. 28 Review of classified images: 5 min. presentation for each group, person
Lab 4: Classification
Part I: Subset full image to small area around Corvallis Part II: Build an unsupervised classification Part III: Apply spectral signatures from unsupervised classification of subset image to the whole scene in a maximum likelihood supervised classification approach
Please copy the image to your folder before working on it, if one copy of the image is open, nobody else can use it.
