This task performs the Spectral Information Divergence (SID) classification.
Example
This example performs the following steps:
-
Opens an AVIRIS hyperspectral image subset.
-
Runs a forward minimum noise transform (MNF) to reduce noise in the data.
-
Defines three regions of interest (ROIs), each containing nine pixels of a common material.
-
Retrieves the spectra from the ROIs and uses their means as targets for Spectral Information Divergence classification.
-
Runs the SID task, which performs spectral information divergence classification.
-
Displays the result. To see all of the bands, open the Data Manager.
e = ENVI()
File = Filepath('AVIRISReflectanceSubset.dat', $
SUBDIR=['data', 'hyperspectral'], $
ROOT_DIR=e.Root_Dir)
Raster = e.OpenRaster(File)
Task = ENVITask('ForwardMNFTransform')
Task.INPUT_RASTER = Raster
Task.Execute
Subset = ENVISubsetRaster(Task.OUTPUT_RASTER, BANDS=LINDGEN(15))
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
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
means = [[mean1],[mean2],[mean3]]
Task = ENVITask('SpectralInformationDivergenceClassification')
Task.INPUT_RASTER = Subset
Task.MEAN = means
Task.Execute
dataColl = e.Data
dataColl.Add, Task.OUTPUT_RASTER
View = e.GetView()
Layer = View.CreateLayer(Task.OUTPUT_RASTER)
Syntax
Result = ENVITask('SpectralInformationDivergenceClassification')
Input properties (Set, Get): CLASS_COLORS, CLASS_NAMES, INPUT_RASTER, MEAN, OUTPUT_RASTER_URI, OUTPUT_RULE_RASTER_URI, THRESHOLD
Output properties (Get only):OUTPUT_RASTER, OUTPUT_RULE_RASTER
Properties marked as "Set" are those that you can set to specific values. You can also retrieve their current values any time. Properties marked as "Get" are those whose values you can retrieve but not set.
Methods
This task inherits the following methods from ENVITask:
AddParameter
Execute
Parameter
ParameterNames
RemoveParameter
Properties
This task inherits the following properties from ENVITask:
COMMUTE_ON_DOWNSAMPLE
COMMUTE_ON_SUBSET
DESCRIPTION
DISPLAY_NAME
NAME
REVISION
TAGS
This task also contains the following properties:
CLASS_COLORS (optional)
This is an array of [3, number of classes] for RGB triplets representing the class colors.
CLASS_NAMES (optional)
This is an array of [number of classes] for unclassified and class names.
INPUT_RASTER (required)
Specify an input raster to process.
MEAN (required)
Specify an array that is [number of bands, number of classes].
OUTPUT_RASTER
This is a reference to the output raster of filetype ENVI.
OUTPUT_RASTER_URI (optional)
Specify a string with the fully qualified filename and path to export the associated OUTPUT_RASTER.
- If you set this property to an asterisk symbol (*), the output raster will be virtual and not written to disk.
- If you do not specify this property, the associated output raster will not be created. To force the creation of a temporary file, set this parameter to an exclamation symbol (!).
OUTPUT_RULE_RASTER (optional)
This is a reference to the output rule image of filetype ENVI.
OUTPUT_RULE_RASTER_URI (optional)
Specify a string with the fully qualified filename and path of the associated OUTPUT_RULE_RASTER. If you do not specify this property, the associated OUTPUT_RULE_RASTER will not be created. To force the creation of a temporary file set the property to an exclamation symbol (!).
THRESHOLD (required)
Specify a maximum value or array of maximum values (one for each class) for each class is tested against its corresponding maximum spectral divergence. The default value is 0.05.
Version History
API Version
4.3
See Also
ENVITask