This task performs a matched filter supervised classification. See Matched Filtering for details.

Example


This example performs the following steps:

  1. Opens an AVIRIS hyperspectral image subset.
  2. Runs a forward minimum noise transform (MNF) to reduce noise in the data.
  3. Defines three regions of interest (ROIs), each containing nine pixels of a common material.
  4. Retrieves the spectra from the ROIs and uses their means as endmembers for matched filtering.
  5. Runs the MatchedFilter task.
  6. Displays the result. To see all of the bands, open the Data Manager. ENVI creates three MF Score images (one for each ROI) and three Infeasibility images.
; Start the application
e = ENVI()
 
; Open an input file
File = Filepath('AVIRISReflectanceSubset.dat', $
  SUBDIR=['data', 'hyperspectral'], $
  ROOT_DIR=e.Root_Dir)
Raster = e.OpenRaster(File)
 
; First run a Forward MNF on the data
Task = ENVITask('ForwardMNFTransform')
Task.INPUT_RASTER = Raster
Task.Execute
 
; Use the first 25 MNF bands to run a matched filter
Subset = ENVISubsetRaster(Task.OUTPUT_RASTER, BANDS=LINDGEN(25))
 
; Define three ROIs, each containing 9 pixels of a common material.
nSpectra = 9d
roi1 = ENVIROI(NAME='Green Field')
pixelAddr1 = [[77,182],[78,182],[79,182], $
  [77,183],[78,183],[79,183], $
  [77,184],[78,184],[79,184]]
roi1.AddPixels, pixelAddr1, SPATIALREF=Subset.SPATIALREF
 
roi2 = ENVIROI(NAME='Soil')
pixelAddr2 = [[386,285],[387,285],[388,285], $
  [386,286],[387,286],[388,286], $
  [386,287],[387,287],[388,287]]
roi2.AddPixels, pixelAddr2, SPATIALREF=Subset.SPATIALREF
 
roi3 = ENVIROI(NAME='Ground')
pixelAddr3 = [[296,326],[297,326],[298,326], $
  [296,327],[297,327],[298,327], $
  [296,328],[297,328],[298,328]]
roi3.AddPixels, pixelAddr3, SPATIALREF=Subset.SPATIALREF
 
; Retrieve the spectra from the ROIs and use their mean as 
; endmembers for the Matched Filter task
spectra1 = Subset.GetData(ROI=roi1)
mean1 = Total(spectra1,1) / nSpectra
 
spectra2 = Subset.Getdata(ROI=roi2)
mean2 = Total(spectra2,1) / nSpectra
 
spectra3 = Subset.GetData(ROI=roi3)
mean3 = Total(spectra3,1) / nSpectra
 
endmembers = [[mean1],[mean2],[mean3]]
 
; Get the task from the catalog of ENVITasks
Task = ENVITask('MatchedFilter')
Task.INPUT_RASTER = Subset
Task.ENDMEMBERS = endmembers
Task.NAMES = ['Green Field', 'Soil', 'Ground']
 
; Run the task
Task.Execute
 
; Get the data collection
dataColl = e.Data
 
; Add the output to the data collection
dataColl.Add, Task.OUTPUT_RASTER
 
; Display the result
View = e.GetView()
Layer = View.CreateLayer(Task.OUTPUT_RASTER)

Syntax


Result = ENVITask('MatchedFilter')

Input parameters (Set, Get): COVARIANCE, BACKGROUND_THRESHOLD, ENDMEMBERS, INPUT_RASTER, MEAN, NAMES, OUTPUT_RASTER_URI, REGULARIZATION_METHOD, REGULARIZATION_TOLERANCE, USE_SUBSPACE_BACKGROUND

Output parameters (Get only): OUTPUT_RASTER

Parameters marked as "Set" are those that you can set to specific values. You can also retrieve their current values any time. Parameters marked as "Get" are those whose values you can retrieve but not set.

Input Parameters


BACKGROUND_THRESHOLD (optional)

Specify the background threshold to use when calculating statistics using the subspace background. The default value is 0.9.

COVARIANCE (optional)

Specify an array that is the covariance matrix of the input bands. The array size is [number of bands, number of bands].

ENDMEMBERS (required)

Specify an array that is [number of bands, number of classes].

INPUT_RASTER (required)

Specify a raster on which to perform the matched filter classification.

MEAN (optional)

Specify an array that is the mean of the input bands. The number of elements in the array must match the number of bands.

NAMES (optional)

This is an array of endmember names.

OUTPUT_RASTER_URI (optional)

Specify a string with the fully qualified filename and path of the associated OUTPUT_RASTER.

  • If you do not specify this parameter, or set it to an exclamation symbol (!), ENVI creates a temporary file.
  • If you set it to the hash symbol (#), ENVI creates a file in the temporary directory, but this file will not be deleted when ENVI closes.

REGULARIZATION_METHOD (optional)

Specify a method for regularizing the covariance matrix:

  • Diagonal: Diagonal loading, increasing all singular values by the tolerance value.
  • Dominant: Dominant mode rejection, setting singular values less than the tolerance value to their mean.
  • None: No regularization is used.
  • Shrink: Shrinkage of singular values based on the tolerance value.
  • Threshold: Singular values less than the tolerance value are set to the tolerance value.
  • Truncate (default): Singular values less than the tolerance value are set to zero.

REGULARIZATION_TOLERANCE (optional)

Specify the tolerance value to use for matrix regularization. If not set, the following values will be used based on the regularization method

  • Diagonal: Ten times the smallest nonzero singular value.
  • Dominant: The value prescribed by Gavish & Donoho.
  • None: N/A
  • Shrink: The Oracle Approximating Shrinkage (OAS) estimator.
  • Threshold: The largest singular value times the machine precision.
  • Truncate (default): The largest singular value times the machine precision.

USE_SUBSPACE_BACKGROUND (optional)

Specify whether to use the subspace background in statistics calculation.

Output Parameters


OUTPUT_RASTER

This is a reference to the output raster of filetype ENVI.

Methods


Execute

Parameter

ParameterNames

Properties


DESCRIPTION

DISPLAY_NAME

NAME

REVISION

TAGS

Version History


ENVI 5.5

Introduced

ENVI 6.2

Added the COVARIANCE, MEAN, REGULARIZATION_METHOD and REGULARIZATION_TOLERANCE parameters.

See Also


ENVITask, MixtureTunedMatchedFilter Task, ForwardMNFTransform Task, Masking Support in ENVITasks