mitk::CovarianceMatrixCalculator Class Reference

Computes covariance matrices for every vertex of a Surface, for use in the anisotropic ICP (A-ICP) algorithm. More...

#include <mitkCovarianceMatrixCalculator.h>

Inheritance diagram for mitk::CovarianceMatrixCalculator:

Collaboration diagram for mitk::CovarianceMatrixCalculator:

Public Member Functions
	mitkClassMacroItkParent (CovarianceMatrixCalculator, itk::Object)
Pointer	Clone () const
void	SetVoronoiScalingFator (const double factor)
void	EnableNormalization (bool state)
double	GetMeanVariance () const
const CovarianceMatrixList &	GetCovarianceMatrices () const
void	SetInputSurface (Surface *input)
void	ComputeCovarianceMatrices ()

Static Public Member Functions
static Pointer	New ()

Protected Types
typedef itk::Matrix< double, 3, 3 >	CovarianceMatrix
typedef std::vector< CovarianceMatrix >	CovarianceMatrixList
typedef double	Vertex[3]

Protected Member Functions
void	ComputeOrthonormalCoordinateSystem (const int index, Vertex normal, CovarianceMatrix &principalComponents, Vertex variances, Vertex curVertex)
	CovarianceMatrixCalculator ()
	~CovarianceMatrixCalculator () override

Protected Attributes
CovarianceMatrixList	m_CovarianceMatrixList

Detailed Description

Computes covariance matrices for every vertex of a Surface, for use in the anisotropic ICP (A-ICP) algorithm.

This class computes a 3x3 covariance matrix for each vertex in a given Surface based on its direct neighbours and stores them in a CovarianceMatrixList. The implementation follows the CM_PCA method presented by L. Maier-Hein et al. in "Convergent Iterative Closest-Point Algorithm to Accommodate Anisotropic and Inhomogenous Localization Error.", IEEE T Pattern Anal 34 (8), 1520-1532, 2012. The algorithm requires a clean Surface without non-manifold edges and without duplicated vertices. Use vtkCleanPolyData to ensure a correct Surface representation.

See also

AnisotropicIterativeClosestPointRegistration

AnisotropicRegistrationCommon

WeightedPointTransform

Definition at line 48 of file mitkCovarianceMatrixCalculator.h.

Member Typedef Documentation

CovarianceMatrix

typedef itk::Matrix<double, 3, 3> mitk::CovarianceMatrixCalculator::CovarianceMatrix

protected

Definition of the covariance matrix.

Definition at line 58 of file mitkCovarianceMatrixCalculator.h.

CovarianceMatrixList

typedef std::vector<CovarianceMatrix> mitk::CovarianceMatrixCalculator::CovarianceMatrixList

protected

Definition of a list of covariance matrices

Definition at line 60 of file mitkCovarianceMatrixCalculator.h.

Vertex

typedef double mitk::CovarianceMatrixCalculator::Vertex[3]

protected

Definition at line 61 of file mitkCovarianceMatrixCalculator.h.

Constructor & Destructor Documentation

CovarianceMatrixCalculator()

mitk::CovarianceMatrixCalculator::CovarianceMatrixCalculator ( )

protected

~CovarianceMatrixCalculator()

mitk::CovarianceMatrixCalculator::~CovarianceMatrixCalculator ( )

overrideprotected

Member Function Documentation

Clone()

Pointer mitk::CovarianceMatrixCalculator::Clone

(

)

const

ComputeCovarianceMatrices()

void mitk::CovarianceMatrixCalculator::ComputeCovarianceMatrices

(

)

Method that computes the covariance matrices for the input surface.

Exceptions

std::exception

If the input surface is not set.

ComputeOrthonormalCoordinateSystem()

void mitk::CovarianceMatrixCalculator::ComputeOrthonormalCoordinateSystem ( const int  index, Vertex  normal, CovarianceMatrix &  principalComponents, Vertex  variances, Vertex  curVertex  )

protected

This method projects all surrounding vertices of given vertex in a Surface in the normal direction onto a plane and computes a primary component analysis on the projected vertices. In the next step a orthonormal system is created.

Parameters

index	The index of the input Vertex in the Surface.
normal	The normal of the input Vertex.
principalComponents	CovarianceMatrix of the principal component analysis.
variances	Variances along the axes of the createt Orthonormal system.
curVertex	The current Vertex in the surface

EnableNormalization()

void mitk::CovarianceMatrixCalculator::EnableNormalization

(

bool

state

)

Enables/disables the covariance matrix normalization.

Parameters

state

Enables the covariance matrix normalization.

GetCovarianceMatrices()

const CovarianceMatrixList& mitk::CovarianceMatrixCalculator::GetCovarianceMatrices

(

)

const

Returns a reference to the CovarianceMatrixList with the computed covariance matrices.

Returns

A CovarianceMatrixList.

GetMeanVariance()

double mitk::CovarianceMatrixCalculator::GetMeanVariance

(

)

const

Returns the mean of variance of all computed covariance matrices.

Returns

The mean variance.

mitkClassMacroItkParent()

mitk::CovarianceMatrixCalculator::mitkClassMacroItkParent	(	CovarianceMatrixCalculator	,
		itk::Object
	)

New()

static Pointer mitk::CovarianceMatrixCalculator::New ( )

static

SetInputSurface()

void mitk::CovarianceMatrixCalculator::SetInputSurface

(

Surface *

input

)

Sets the input Surface for which the covariance matrices will be calculated.

Parameters

input

A Surface.

SetVoronoiScalingFator()

void mitk::CovarianceMatrixCalculator::SetVoronoiScalingFator

(

const double

factor

)

Sets the scaling factor for the voronoi area.

Parameters

factor

The scaling factor.

Member Data Documentation

m_CovarianceMatrixList

CovarianceMatrixList mitk::CovarianceMatrixCalculator::m_CovarianceMatrixList

protected

List that stores the computed covariance matrices.

Definition at line 64 of file mitkCovarianceMatrixCalculator.h.

---

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

• mitkCovarianceMatrixCalculator.h