TerraLib 4.1
TePDISAMClassifier Class Reference

Spectral Angle Mapper classification algorithm. More...

#include <TePDISAMClassifier.hpp>

Inheritance diagram for TePDISAMClassifier:
TePDIAlgorithm

List of all members.

Classes

class  ClassReferenceData
 Class classification reference data. More...
class  ClassSpectralSamples
 Class spectral samples. More...
class  SegThread
 Segmentation thread class. More...

Public Types

typedef std::vector
< ClassSpectralSamples
SpectralSamplesVectorT
 Samples vector.
typedef TeSharedPtr
< SpectralSamplesVectorT
SpectralSamplesVecPtrT
 Samples vector pointer.

Public Member Functions

 TePDISAMClassifier ()
 ~TePDISAMClassifier ()
bool CheckParameters (const TePDIParameters &parameters) const
 Checks if the supplied parameters fits the requirements of each PDI algorithm implementation.

Protected Member Functions

void ResetState (const TePDIParameters &)
 Reset the internal state to the initial state.
bool RunImplementation ()
 Runs the current algorithm implementation.
bool calcClassRefData (const SpectralSamplesVectorT &spectralSamples, std::vector< ClassReferenceData > &refDataVector) const
 Calc the classes reference data required by the classification process.

Detailed Description

Spectral Angle Mapper classification algorithm.

This algorithm maps the spectral similarity of input raster to the given reference spectra wich can be either laboratory of field spectra. This method assumes that the data have been reduced to apparent reflectance with all dark current and path radiance biases removed. Reference: The spectral image processing system (SIPS)- interactive visualization and analysis of imaging spectrometer data. Kruse, F. A.; Lefkoff, A. B.; Boardman, J. W.; Heidebrecht, K. B.; Shapiro, A. T.; Barloon, P. J.; Goetz, A. F. H. The earth and space science information system (ESSIS). AIP Conference Proceedings, Volume 283, pp. 192-201 (1993).

Author:
Emiliano F. Castejon <castejon@dpi.inpe.br>
Note:
The required parameters are:
Parameters:
input_raster(TePDITypes::TePDIRasterPtrType) - Input raster.
bands( std::vector< unsigned int > ) - Bands to process from the input raster.
spectral_samples( TePDISAMClassifier::SpectralSamplesVecPtrT ) - Reference spectral samples of all required classes.
output_raster(TePDITypes::TePDIRasterPtrType) - Output raster.
Note:
The optional parameters are:
Parameters:
enable_multi_thread(int) - If present (any value) multi-threaded processing will be used (default:multi-threaded processing disabled).
Examples:

TePDIClassification_test.cpp.


Member Typedef Documentation

Samples vector.


Constructor & Destructor Documentation

TePDISAMClassifier::TePDISAMClassifier ( )
TePDISAMClassifier::~TePDISAMClassifier ( )

Member Function Documentation

bool TePDISAMClassifier::calcClassRefData ( const SpectralSamplesVectorT spectralSamples,
std::vector< ClassReferenceData > &  refDataVector 
) const [protected]

Calc the classes reference data required by the classification process.

Parameters:
spectralSamples- Input spectral samples.
refDataVector- The generated output reference data vector.
bool TePDISAMClassifier::CheckParameters ( const TePDIParameters parameters) const [virtual]

Checks if the supplied parameters fits the requirements of each PDI algorithm implementation.

Note:
Error log messages must be generated. No exceptions generated.
Parameters:
parametersThe parameters to be checked.
Returns:
true if the parameters are OK. false if not.

Implements TePDIAlgorithm.

void TePDISAMClassifier::ResetState ( const TePDIParameters params) [protected, virtual]

Reset the internal state to the initial state.

Parameters:
paramsThe new parameters referente at initial state.

Implements TePDIAlgorithm.

bool TePDISAMClassifier::RunImplementation ( ) [protected, virtual]

Runs the current algorithm implementation.

Returns:
true if OK. false on error.

Implements TePDIAlgorithm.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines