RS_classify by pengtt

VIEWS: 56 PAGES: 32

									Introduction to Classification of
Remotely Sensed Imagery
            John Porter
Example – Thematic Mapper
  The Thematic Mapper is a satellite
   sensor used in recent LANDSAT
   satellites
  It captures 7 bands
     • ~30 m spatial resolution for bands 1-5 &7,
       ~120 m in band 6
     • Extent:
Thematic Mapper Spectral Bands
 Wavelengths in micrometers
 Band 1 = 0.45-0.52
 Band 2 = 0.52-0.60
 Band 3 = 0.63-0.69
 Band 4 = 0.76-0.90
 Band 5 = 1.55-1.75
 Band 6 = 10.40-12.50
 Band 7 = 2.08-2.35
Remote Sensing to GIS
                  Radiometric      Geometric
Raw Image                          Correction
                   Correction




                      Recoding        Raster GIS
 Classification
                                      Data Layer


                      Raster to        Polygon GIS
                       Vector          Data Layer
                      Conversion
Remote Sensing to GIS
                             Geometric
Raw Image   Classification
                             Correction



Sometimes steps are
omitted or reordered,        Raster GIS
depending on the             Data Layer

purpose of the
analysis
    Automated Image Processing
   This lecture will focus on automated
    image processing:
    • Unsupervised Classification
    • Supervised Classification
    • Tools for Image Processing
Classification
    Classification is the process of taking the
     “brightness values” associated with each
     pixel and using them into assign a class to
     the corresponding output pixels
     • Output pixels are NOT continuous. Instead they
       are discrete values that represent a class or
       category (e.g. land cover classes)
     • For example, we might decide that pixels with the
       value (20,30,190) (in band 1 thru 3 , respectively)
       indicate that the output pixel should be assigned a
       value of “10” – corresponding to class “10”=forest
    Classification
   The trick in classification is to come up
    with “rules” that will allow us to translate
    image values (e.g., 10,20,190) into
    classes (forest, grass, water, marsh,
    urban)
    • Usually the land cover classes are
      associated with numerical codes: e.g.,
      1=forest, 2=grass, 3=water, 4=urban
    Classification Methods
   There are two fundamental
    approaches to classification:
    1. Unsupervised
      •   The computer selects classes based on
          clustering of brightness values
    2. Supervised
      •   You specify the classes to be used and
          provide “signatures” for each class
    Unsupervised Classification
   Unsupervised classification refers to a variety
    of different techniques that share some
    features in common
    • They use statistical “clustering” techniques to
      decide which pixels should be grouped together
    • With luck, these clusters of pixels will correspond
      to land cover classes
       – But the correspondence may not be 1:1
       – One land cover class may be represented by more than
         one cluster (easily fixed by recoding)
       – One cluster may represent more than one land cover
         type (not easily fixed – may need to specify more
         clusters)
    Example
   The “Image Analyst” extension in
    ArcView uses the ISODATA
    unsupervised clustering technique
    where all you need to specify is the
    number of desired classes
Each color
represents a
different “cluster”
pixels that may
correspond to the
land cover classes
you are interested
in
    Recoding
   Following an unsupervised classification, you
    need to go through and assign “meaning” to
    each of the classes (e.g., class 1 = water)
   You can use editing functions to set multiple
    classes that represent the same land cover
    type to a common value
    • E.g., if both class 1 and class 5 are water (albeit,
      deep water vs. shallow water), you may want to
      edit all the 5’s and change them to 1’s
    Supervised Classification
   In supervised classification you help the
    computer to select “signatures” that represent
    each land cover class
   Signatures are statistical descriptions of the
    brightness values of a given land cover type
    (e.g., the mean band 1 value, the mean band
    2 value etc.)
   You select signatures using a tool that
    provides “seed” values
Signature Selection
  The key to a good supervised
   classification is proper selection of
   “signatures”
  What makes for a good signature?
     • Characterizes a land cover type of interest
     • Separability – needs to be distinguishable
       from other signatures
Collecting Signatures
    There are two main methods for
     obtaining signatures
     • Area-based – where you use a box on the
       screen to select the area to be statistically
       characterized as a signature
     • Growing an area – where you select a
       point and other “similar” adjacent points
       are added to the sample
        – Note: choice of minimum similarity can have a
          big effect on the results of this method
Used the “seed tool”
and clicked here.
The highlighted
marsh area was
similar in color and
connected to the
point so it was added
to the data used to
calculate the
signature.
The “Find Like
Areas”
command
highlighted all
the other areas
that have a
similar color (i.e.
similar spectral
values) – with
skill they will all
be Marsh
    Classification                 Added Water

   The process is
    repeated to add new
    classes
   Due to color
    variations within a
    class, often multiple
    signatures will be
    needed to capture a
    single cover class
   The classes can be
    recoded and lumped
    (using basic editing    But not all water was “captured”
    functions) so that        by the class- requiring
    they correspond to        additional “signatures”
    the desired classes.
    Classification
   Once you have a group of signatures
    defined, you can classify your image.
    There are several methods for doing
    this:
    •   Paralleliped
    •   Mahalanobis Distance
    •   Maximum Likelihood
    •   And others……….
    Paralleliped Classification
   use maximum and minimum values on each
    individual band (as derived from each signature) to
    decide which pixels fall within a given class
   Advantages
    • Fast
    • Can be used one signature at a time
    • Used by ARCVIEW Image Analyst
   Disadvantages
    • Does poorer job separating classes
    • Uses only a fraction of the information contained
      in the signature data
    Maximum Likelihood
   Uses statistical techniques to decide which
    class a pixel falls into
   Advantages
    • Uses full signature information (mean, variation &
      inter-band covariation) to tease apart similar
      classes
   Disadvantages
    • More computer intensive
    • Not available in ARCVIEW
     Graphical Description
   We can use                    Pixel dim on
                                  band 1, but bright
    a graph to    255             on band 2
    display
    where
    pixels fall    Band 2       Pixel bright on both bands
    on two
    bands at
    once                           Pixel dim on both bands
                        0
                            0                           255
                                   Band 1
Graphical Display
   Here is a
    sample display
    where Marsh is 255
    dark, beach is                Water
    light on both
    bands and       Band 2
    water is bright                       Beach
    on one band
    (presumably                      Marsh
    blue) and dim     0
    on the other
                             0                    255
                                 Band 1
    Paralleliped
                            Here, paralleliped
   Paralleliped            would work well
    classification 255
    uses boxes
    based on

                   Band 2
    statistical
    measures of                              Min.   Max
    the range                                on     on
                                             band   band
    (e.g.                                    1      1
    maximum
                      0
    and minimum
    values)             0                           255
                                Band 1
    Paralleliped
                                 Areas of overlap lead to
   However,                     uncertain results
    sometimes
                   255
    paralleliped
    may do a

                    Band 2
    poor job
    separating
    classes

                         0
                             0                          255
                                   Band 1
Maximum Likelihood
    Maximum
     likelihood
                   255
     uses seed
     statistics to
     define        Band 2
     ellipses for
     each class

                        0
                            0            255
                                Band 1
Maximum Likelihood
    Ellipses
     make it
                 255
     easier to
     separate

                  Band 2
     similar
     classes


                       0
                           0            255
                               Band 1
    Software for Image Classification

   ArcView Image Analyst
    • Provides basic image classification
      capabilities
      – Unsupervised: ISODATA method
      – Supervised: Paralleliped only
    • Also supports georeferencing and some
      image processing (e.g., sharpen edges)
    • Relatively easy to use
    Software
   ERDAS Imagine
    • Full suite of advanced image processing
      and classification features
      – Unsupervised: many different clustering
        techniques available (including ISODATA)
      – Supervised: better tools for capturing and
        analyzing signatures, many classification
        methods (including paralleliped and maximum
        likelihood)
    • Harder to use (with power comes
      complexity)

								
To top