SAGA-GIS Module Library Documentation (v2.1.3)

Module Supervised Classification

Supervised Classification

Parameters

 NameTypeIdentifierDescriptionConstraints
InputGridsGrid list (input)GRIDS--
Training AreasShapes (input)ROI--
Class StatisticsTable (input)STATS--
OutputSummaryTable (output)CLASS_INFO--
ClassificationGrid (output)CLASSES--
Quality (*)Grid (optional output)QUALITYDependent on chosen method, these are distances or probabilities.-
OptionsClass IdentifierTable fieldROI_ID--
Get Class Statistics from...ChoiceSTATS_SRC-Available Choices:
[0] training areas
[1] table
Default: 0
MethodChoiceMETHOD-Available Choices:
[0] Binary Encoding
[1] Parallelepiped
[2] Minimum Distance
[3] Mahalanobis Distance
[4] Maximum Likelihood
[5] Spectral Angle Mapping
[6] Winner Takes All
Default: 2
NormaliseBooleanNORMALISE-Default: 0
Distance ThresholdFloating pointTHRESHOLD_DISTLet pixel stay unclassified, if minimum or mahalanobis distance is greater than threshold.Minimum: 0.000000
Default: 0.000000
Probability Threshold (Percent)Floating pointTHRESHOLD_PROBLet pixel stay unclassified, if maximum likelihood probability is less than threshold.Minimum: 0.000000
Maximum: 100.000000
Default: 0.000000
Probability ReferenceChoiceRELATIVE_PROB-Available Choices:
[0] absolute
[1] relative
Default: 1
Spectral Angle Threshold (Degree)Floating pointTHRESHOLD_ANGLELet pixel stay unclassified, if spectral angle distance is greater than threshold.Minimum: 0.000000
Maximum: 90.000000
Default: 0.000000
Binary EncodingBooleanWTA_0-Default: 0
ParallelepipedBooleanWTA_1-Default: 0
Minimum DistanceBooleanWTA_2-Default: 0
Mahalanobis DistanceBooleanWTA_3-Default: 0
Maximum LikelihoodBooleanWTA_4-Default: 0
Spectral Angle MappingBooleanWTA_5-Default: 0
(*) optional

Command-line

Usage: saga_cmd imagery_classification 0 -GRIDS <str> -ROI <str> [-ROI_ID <str>] -STATS <str> [-CLASS_INFO <str>] [-CLASSES <str>] [-QUALITY <str>] [-STATS_SRC <str>] [-METHOD <str>] [-NORMALISE <str>] [-THRESHOLD_DIST <str>] [-THRESHOLD_PROB <str>] [-RELATIVE_PROB <str>] [-THRESHOLD_ANGLE <str>] [-WTA_0 <str>] [-WTA_1 <str>] [-WTA_2 <str>] [-WTA_3 <str>] [-WTA_4 <str>] [-WTA_5 <str>]
  -GRIDS:<str>          	Grids
	Grid list (input)
  -ROI:<str>            	Training Areas
	Shapes (input)
  -ROI_ID:<str>         	Class Identifier
	Table field
  -STATS:<str>          	Class Statistics
	Table (input)
  -CLASS_INFO:<str>     	Summary
	Table (output)
  -CLASSES:<str>        	Classification
	Grid (output)
  -QUALITY:<str>        	Quality
	Grid (optional output)
  -STATS_SRC:<str>      	Get Class Statistics from...
	Choice
	Available Choices:
	[0] training areas
	[1] table
	Default: 0
  -METHOD:<str>         	Method
	Choice
	Available Choices:
	[0] Binary Encoding
	[1] Parallelepiped
	[2] Minimum Distance
	[3] Mahalanobis Distance
	[4] Maximum Likelihood
	[5] Spectral Angle Mapping
	[6] Winner Takes All
	Default: 2
  -NORMALISE:<str>      	Normalise
	Boolean
	Default: 0
  -THRESHOLD_DIST:<str> 	Distance Threshold
	Floating point
	Minimum: 0.000000
	Default: 0.000000
  -THRESHOLD_PROB:<str> 	Probability Threshold (Percent)
	Floating point
	Minimum: 0.000000
	Maximum: 100.000000
	Default: 0.000000
  -RELATIVE_PROB:<str>  	Probability Reference
	Choice
	Available Choices:
	[0] absolute
	[1] relative
	Default: 1
  -THRESHOLD_ANGLE:<str>	Spectral Angle Threshold (Degree)
	Floating point
	Minimum: 0.000000
	Maximum: 90.000000
	Default: 0.000000
  -WTA_0:<str>          	Binary Encoding
	Boolean
	Default: 0
  -WTA_1:<str>          	Parallelepiped
	Boolean
	Default: 0
  -WTA_2:<str>          	Minimum Distance
	Boolean
	Default: 0
  -WTA_3:<str>          	Mahalanobis Distance
	Boolean
	Default: 0
  -WTA_4:<str>          	Maximum Likelihood
	Boolean
	Default: 0
  -WTA_5:<str>          	Spectral Angle Mapping
	Boolean
	Default: 0