#include <otbKMeansImageClassificationFilter.h>

Inheritance diagram for otb::KMeansImageClassificationFilter< TInputImage, TOutputImage, VMaxSampleDimension, TMaskImage >:

Collaboration diagram for otb::KMeansImageClassificationFilter< TInputImage, TOutputImage, VMaxSampleDimension, TMaskImage >:

Public Types
typedef std::map< LabelType, SampleType >	CentroidsMapType

typedef itk::SmartPointer< const Self >	ConstPointer

typedef itk::Statistics::EuclideanDistanceMetric< SampleType >	DistanceType

typedef InputImageType::ConstPointer	InputImageConstPointerType

typedef TInputImage	InputImageType

typedef itk::Array< double >	KMeansParametersType

typedef OutputImageType::PixelType	LabelType

typedef MaskImageType::ConstPointer	MaskImageConstPointerType

typedef MaskImageType::Pointer	MaskImagePointerType

typedef TMaskImage	MaskImageType

typedef OutputImageType::Pointer	OutputImagePointerType

typedef OutputImageType::RegionType	OutputImageRegionType

typedef TOutputImage	OutputImageType

typedef itk::SmartPointer< Self >	Pointer

typedef itk::FixedArray< ValueType, MaxSampleDimension >	SampleType

typedef KMeansImageClassificationFilter	Self

typedef itk::InPlaceImageFilter< TInputImage, TOutputImage >	Superclass

typedef InputImageType::InternalPixelType	ValueType

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

virtual const char *	GetNameOfClass () const

Static Public Member Functions
static Pointer	New ()

Static Public Attributes
static const unsigned int	MaxSampleDimension = VMaxSampleDimension

KMeansParametersType	m_Centroids

LabelType	m_DefaultLabel

CentroidsMapType	m_CentroidsMap

virtual void	SetCentroids (KMeansParametersType _arg)

virtual const KMeansParametersType &	GetCentroids () const

virtual void	SetDefaultLabel (LabelType _arg)

virtual LabelType	GetDefaultLabel ()

void	SetInputMask (const MaskImageType *mask)

const MaskImageType *	GetInputMask (void)

	KMeansImageClassificationFilter ()

	~KMeansImageClassificationFilter () override=default

void	ThreadedGenerateData (const OutputImageRegionType &outputRegionForThread, itk::ThreadIdType threadId) override

void	BeforeThreadedGenerateData () override

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

	KMeansImageClassificationFilter (const Self &)=delete

void	operator= (const Self &)=delete

Detailed Description

template<class TInputImage, class TOutputImage, unsigned int VMaxSampleDimension = 10, class TMaskImage = TOutputImage>
class otb::KMeansImageClassificationFilter< TInputImage, TOutputImage, VMaxSampleDimension, TMaskImage >

This filter performs the classification of a VectorImage using a KMeans estimation result.

This filter is streamed and threaded, allowing to classify huge images. Because the internal sample type has to be an itk::FixedArray, one must specify at compilation time the maximum sample dimension. It is up to the user to specify a MaxSampleDimension sufficiently high to integrate all its features. This filter internally use one SVMClassifier per thread.

See also: SVMClassifier

Definition at line 45 of file otbKMeansImageClassificationFilter.h.