ISOSeg strategy for OBIA classification. The algorithm orders regions by area (larger first), and classify the largest region as Cluster 1. All regions similar to this cluster are inserted in Cluster 1, otherwise new Clusters are created. After all regions belong to a cluster, the algorithm merges similar clusters. The acceptance threshold is the only parameter given by the user, and it indicates the maximum distance between two regions to be clustered togheter. More...

#include <ClassifierISOSegStrategy.h>

Inheritance diagram for te::rp::ClassifierISOSegStrategy:

Classes
class	Parameters
	Classifier Parameters. More...

class	Pattern
	Describes a region or a cluster (group of regions with similar properties) to be used by ISOSeg method. More...

Public Member Functions
	ClassifierISOSegStrategy ()

bool	execute (const te::rst::Raster &inputRaster, const std::vector< unsigned int > &inputRasterBands, const std::vector< te::gm::Polygon * > &inputPolygons, te::rst::Raster &outputRaster, const unsigned int outputRasterBand, const bool enableProgressInterface) throw (te::rp::Exception)
	Executes the classification strategy. More...

bool	initialize (StrategyParameters const *const strategyParams) throw (te::rp::Exception)
	Initialize the classification strategy. More...

	~ClassifierISOSegStrategy ()

Protected Attributes
bool	m_isInitialized
	True if this instance is initialized. More...

ClassifierISOSegStrategy::Parameters	m_parameters
	Internal execution parameters. More...

std::multimap< double, Pattern *, std::greater< double > >	m_regions
	A descriptive set of regions (area, features). More...

Detailed Description

ISOSeg strategy for OBIA classification. The algorithm orders regions by area (larger first), and classify the largest region as Cluster 1. All regions similar to this cluster are inserted in Cluster 1, otherwise new Clusters are created. After all regions belong to a cluster, the algorithm merges similar clusters. The acceptance threshold is the only parameter given by the user, and it indicates the maximum distance between two regions to be clustered togheter.

Definition at line 54 of file ClassifierISOSegStrategy.h.

Constructor & Destructor Documentation

te::rp::ClassifierISOSegStrategy::ClassifierISOSegStrategy ( )

Definition at line 194 of file ClassifierISOSegStrategy.cpp.

References m_isInitialized.

te::rp::ClassifierISOSegStrategy::~ClassifierISOSegStrategy ( )

Definition at line 199 of file ClassifierISOSegStrategy.cpp.

Member Function Documentation

bool te::rp::ClassifierISOSegStrategy::execute	(	const te::rst::Raster &	inputRaster,
		const std::vector< unsigned int > &	inputRasterBands,
		const std::vector< te::gm::Polygon * > &	inputPolygons,
		te::rst::Raster &	outputRaster,
		const unsigned int	outputRasterBand,
		const bool	enableProgressInterface
	)
throw	(	te::rp::Exception
	)

virtual

Executes the classification strategy.

Parameters

inputRaster	Input raster.
inputRasterBands	Input raster bands.
inputPolygons	The polygons to be classified when using object-based image analysis (OBIA).
outputRaster	Output raster.
outputRasterBand	Output raster band.
enableProgressInterface	Enable the internal strategy to update the progress interface.

Returns: true if OK, false on errors.

Implements te::rp::ClassifierStrategy.

Definition at line 259 of file ClassifierISOSegStrategy.cpp.

References te::rst::PolygonIterator< T >::begin(), te::rst::PolygonIterator< T >::end(), te::gm::CurvePolygon::getArea(), te::rst::PolygonIterator< T >::getColumn(), te::rst::PolygonIterator< T >::getRow(), getThreshold(), te::rp::ClassifierISOSegStrategy::Parameters::m_acceptanceThreshold, te::rp::ClassifierISOSegStrategy::Pattern::m_area, m_isInitialized, te::stat::NumericStatisticalSummary::m_mean, te::rp::ClassifierISOSegStrategy::Pattern::m_myCluster, m_parameters, m_regions, te::xsd::Pattern, te::common::TaskProgress::pulse(), TE_TR, TERP_TRUE_OR_RETURN_FALSE, and te::common::TaskProgress::UNDEFINED.

bool te::rp::ClassifierISOSegStrategy::initialize	(	StrategyParameters const *const	strategyParams	)
throw	(	te::rp::Exception
	)

virtual

Initialize the classification strategy.

Parameters

strategyParams A pointer to the user given specific classification strategy parameters ou NULL if no parameters are present.

Returns: true if OK, false on errors.

Implements te::rp::ClassifierStrategy.

Definition at line 203 of file ClassifierISOSegStrategy.cpp.

References te::rp::ClassifierISOSegStrategy::Parameters::m_acceptanceThreshold, m_isInitialized, m_parameters, and TERP_TRUE_OR_RETURN_FALSE.

Member Data Documentation

bool te::rp::ClassifierISOSegStrategy::m_isInitialized

protected

True if this instance is initialized.

Definition at line 150 of file ClassifierISOSegStrategy.h.

Referenced by ClassifierISOSegStrategy(), execute(), and initialize().

ClassifierISOSegStrategy::Parameters te::rp::ClassifierISOSegStrategy::m_parameters

protected

Internal execution parameters.

Definition at line 151 of file ClassifierISOSegStrategy.h.

Referenced by execute(), and initialize().

std::multimap<double, Pattern*, std::greater<double> > te::rp::ClassifierISOSegStrategy::m_regions

protected

A descriptive set of regions (area, features).

Definition at line 152 of file ClassifierISOSegStrategy.h.

Referenced by execute().

The documentation for this class was generated from the following files:

/home/castejon/castejon_files/develop/terralib5/git_master/terralib5/src/terralib/rp/ClassifierISOSegStrategy.h
/home/castejon/castejon_files/develop/terralib5/git_master/terralib5/src/terralib/rp/ClassifierISOSegStrategy.cpp

Classes

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation