#include <otbGeodesicMorphologyDecompositionImageFilter.h>

Inheritance diagram for otb::GeodesicMorphologyDecompositionImageFilter< TInputImage, TOutputImage, TStructuringElement >:

Collaboration diagram for otb::GeodesicMorphologyDecompositionImageFilter< TInputImage, TOutputImage, TStructuringElement >:

Public Types
typedef ClosingFilterType::Pointer	ClosingFilterPointerType

typedef itk::ClosingByReconstructionImageFilter< InputImageType, InputImageType, StructuringElementType >	ClosingFilterType

typedef ConcaveFilterType::Pointer	ConcaveFilterPointerType

typedef itk::SubtractImageFilter< OutputImageType, InputImageType, OutputImageType >	ConcaveFilterType

typedef itk::SmartPointer< const Self >	ConstPointer

typedef ConvexFilterType::Pointer	ConvexFilterPointerType

typedef itk::SubtractImageFilter< InputImageType, InputImageType, OutputImageType >	ConvexFilterType

typedef TInputImage	InputImageType

typedef LevelingFilterType::Pointer	LevelingFilterPointerType

typedef otb::GeodesicMorphologyLevelingFilter< InputImageType, OutputImageType, OutputImageType >	LevelingFilterType

typedef OpeningFilterType::Pointer	OpeningFilterPointerType

typedef itk::OpeningByReconstructionImageFilter< InputImageType, InputImageType, StructuringElementType >	OpeningFilterType

typedef TOutputImage	OutputImageType

typedef itk::SmartPointer< Self >	Pointer

typedef StructuringElementType::RadiusType	RadiusType

typedef GeodesicMorphologyDecompositionImageFilter	Self

typedef TStructuringElement	StructuringElementType

typedef itk::ImageToImageFilter< TInputImage, TOutputImage >	Superclass

Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const

virtual const char *	GetNameOfClass () const

Static Public Member Functions
static Pointer	New ()

RadiusType	m_Radius

OpeningFilterPointerType	m_OpeningFilter

ClosingFilterPointerType	m_ClosingFilter

ConvexFilterPointerType	m_ConvexFilter

ConcaveFilterPointerType	m_ConcaveFilter

LevelingFilterPointerType	m_LevelingFilter

bool	m_PreserveIntensities

bool	m_FullyConnected

itk::ProgressAccumulator::Pointer	m_Progress

virtual void	SetRadius (RadiusType _arg)

virtual const RadiusType &	GetRadius () const

OutputImageType *	GetConvexMap (void)

OutputImageType *	GetConcaveMap (void)

virtual void	SetFullyConnected (bool _arg)

virtual bool	GetFullyConnected ()

virtual void	SetPreserveIntensities (bool _arg)

virtual bool	GetPreserveIntensities ()

void	GenerateData (void) override

	GeodesicMorphologyDecompositionImageFilter ()

	~GeodesicMorphologyDecompositionImageFilter () override

void	PrintSelf (std::ostream &os, itk::Indent indent) const override

	GeodesicMorphologyDecompositionImageFilter (const Self &)=delete

void	operator= (const Self &)=delete

Detailed Description

template<class TInputImage, class TOutputImage, class TStructuringElement>
class otb::GeodesicMorphologyDecompositionImageFilter< TInputImage, TOutputImage, TStructuringElement >

This class implements a geodesic morphology based image analysis algorithm.

: This algorithm is based on the following publication:

: Martino Pesaresi and Jon Alti Benediktsson, Member, IEEE: A new approach for the morphological segmentation of high resolution satellite imagery. IEEE Transactions on geoscience and remote sensing, vol. 39, NO. 2, February 2001, p. 309-320.

Given $\gamma^{\star}_{N}$ the geodesic opening by reconstruction morphological operator and $\varphi^{\star}_{N}$ the geodesic closing by reconstruction morphological operator for a structuring element of size $N$ , one can define the two following membership functions for the input image $f$ :

$\stackrel{\smile}{\mu} = f-\gamma^{\star}_{N}(f)$

$\stackrel{\frown}{\mu} = \phi^{\star}_{N}(f)-f$

Where $\stackrel{\smile}{\mu}$ denotes the likelihood of the current pixel to belong to a convex structure of the input image $f$ (i.e. brighter than the surrounding background) with respect to the size of the structuring element $N$ , and $\stackrel{\frown}{\mu}$ denotes the likelihood of the current pixel to belong to a concave structure.

This two membership functions can be used to define a simplification operator $\psi_{N}$ called leveling, which removes from the input image $f$ the structures located by $\stackrel{\smile}{\mu}$ and $\stackrel{\frown}{\mu}$ :

$\psi_{N}(f)= \left\{\begin{array}{lcl} \gamma^{\star}_{N}(f)&:& \stackrel{\smile}{\mu}>\stackrel{\frown}{\mu}\\ \varphi^{\star}_{N}(f)&:& \stackrel{\frown}{\mu}>\stackrel{\smile}{\mu}\\ f&:&\stackrel{\frown}{\mu}=\stackrel{\smile}{\mu} \end{array}\right.$

This filter performs this image decomposition at a given structuring element size. The GetOutput() method returns $\psi_{N}(f)$ , the GetConvexMap() method returns $\stackrel{\smile}{\mu}$ and the GetConcaveMap() method returns $\stackrel{\frown}{\mu}$ .

The PreserveIntensities and the FullyConnected flags reflects the option of the geodesic morphology filters from ITK.

See also: GeodesicMorphologyLevelingFilter; itk::OpeningByReconstructionImageFilter; itk::ClosingByReconstructionImageFilter

Definition at line 85 of file otbGeodesicMorphologyDecompositionImageFilter.h.