FeatureMapsRegistrationAlgorithm Class Reference

#include <ImFusion/Reg/FeatureMapsRegistrationAlgorithm.h>

Algorithm for registering feature maps volumes. More...

Inheritance diagram for FeatureMapsRegistrationAlgorithm:

Detailed Description

Algorithm for registering feature maps volumes.

Classes
struct	OptimizationParameter
	Encapsulates the name and range (min, max) of a parameter. More...

Public Types
enum class	Similarity { Dot = 0 , SSD = 1 }
enum class	Transformation { Rigid = 0 , Affine = 1 }
Public Types inherited from Algorithm
enum	Status {   Unknown = -1 , Success = 0 , Error = 1 , InvalidInput ,   IncompleteInput , OutOfMemoryHost , OutOfMemoryGPU , UnsupportedGPU ,   UnknownAction , AbortedByUser , User = 1000 }
	Status codes. More...

Public Member Functions
	FeatureMapsRegistrationAlgorithm (SharedImageSet &fixed, SharedImageSet &moving, SharedImageSet *weightMoving=nullptr)
void	compute () override
	Execute the algorithm.
double	evaluate (int n, const double *x, double *dx) override
	Evaluates the objective function using parameters x. This algorithm supports gradients.
Eigen::VectorXd	eval (const Eigen::VectorXd &params)
	Evaluates the objective function, returns a vector containing [value, gradient...].
std::vector< Eigen::VectorXd >	batchEval (const std::vector< Eigen::VectorXd > &params)
	Batched implementation of eval. Thanks to GPU parallelism it is much faster than calling eval multiple times.
std::optional< std::pair< Eigen::VectorXd, double > >	localSearch (Eigen::VectorXd startingParams)
	Executes local search of the optimal parameters starting from startingParams. Returns a pair (parameters, score)
std::optional< std::pair< Eigen::VectorXd, double > >	localSearch ()
	Executes local search of the optimal parameters starting from the current parameters. Returns a pair (parameters, score)
std::vector< std::pair< Eigen::VectorXd, double > >	globalSearch (const Eigen::VectorXd &lowerBound, const Eigen::VectorXd &upperBound, int populationSize)
	Executes global search of the optimal parameters within the given bounds.
std::vector< std::pair< Eigen::VectorXd, double > >	globalSearch ()
	Runs global search using the parameters specified in p_rotationRange, p_translationRange, p_searchTrials.
mat4	registrationMatrix (const Eigen::VectorXd &params) const
	Converts parameters to a matrix.
void	applyRegistration (const Eigen::VectorXd &params)
	Applies the registration to the moving image.
void	resetPose ()
	Reset the pose of the moving image.
void	acceptCurrentParameters ()
	Set the initial pose of the moving image as the one specified by the current parameters, retest the current parameters to zero.
void	setDeformation (std::unique_ptr< ClDeformation > deformation)
	Adds a deformation to the registration problem.
std::vector< OptimizationParameter >	parameters () const
	List of parameters of the objective function.
void	configuration (Properties *p) const override
	Serialize the current object configuration into the given Properties object.
int	numEvals () const
	Total number of evaluations of the objective function.
double	bestVal () const
	Best value obtained by the optimizer.
void	setMovingFeatures (SharedImageSet &moving, SharedImageSet *weight=nullptr)
	Replaces the moving features and their weight.
void	setMovingWeight (SharedImageSet *weight=nullptr)
const SharedImageSet *	moving () const
const SharedImageSet *	fixed () const
const SharedImageSet *	weight () const
void	setRotationCenter (const vec3 &centerWorld)
	Sets the rotation center. By default it is the center of the moving image.
void	setPointCorrespondencesPenalty (const PointCorrespondences *pointCorr, double radius=10.0, double weight=1.0)
	Sets the PointCorrespondences used as a penalty In the point correspondences the first point set is assumed to be on the moving volume, and the second on the fixed volume.
Public Member Functions inherited from OptimizingAlgorithm
void	setOptimizer (std::shared_ptr< Optimizer > opt)
	Set an optimizer from outside.
std::shared_ptr< Optimizer >	optimizer ()
	Returns the current optimizer.
void	configure (const Properties *p) override
	Configures the optimizer from a sub-property if available.
void	configuration (Properties *p) const override
	Stores the optimizer configuration into a sub-property.
Public Member Functions inherited from Algorithm
	Algorithm ()
	Default constructor will registers a single "compute" action that calls compute() and returns status().
virtual OwningDataList	takeOutput ()
	Return any new Data that was created by the Algorithm during the last call to compute().
virtual void	setProgress (Progress *progress)
	Sets a Progress interface the algorithm can use to notify observers about its computing progress.
Progress *	progress () const
	Returns the progress interface if set.
virtual int	status () const
	Indicates the status of the last call to compute().
virtual bool	survivesDataDeletion (const Data *) const
	Indicates whether the algorithm can handle (partial) deletion of the specified data, by default this checks whether the data is in the input list.
const FactoryInfo &	factoryInfo () const
	Returns the record describing how this Algorithm was instantiated by the AlgorithmFactory.
void	setFactoryInfo (const FactoryInfo &value)
	Sets the record describing how this Algorithm was instantiated by the AlgorithmFactory.
Status	runAction (const std::string &id)
	Run the action with name id if it exists.
const std::vector< Action > &	actions ()
	Get a mapping from Action id to Action as registered in this algorithm.
Public Member Functions inherited from Configurable
virtual void	configureDefaults ()
	Retrieve the properties of this object, replaces values with their defaults and sets it again.
void	registerParameter (ParameterBase *param)
	Register the given Parameter or SubProperty, so that it will be configured during configure()/configuration().
void	unregisterParameter (const ParameterBase *param)
	Remove the given Parameter or SubProperty from the list of registered parameters.
	Configurable (const Configurable &rhs)
	Configurable (Configurable &&rhs) noexcept
Configurable &	operator= (const Configurable &)
Configurable &	operator= (Configurable &&) noexcept
Public Member Functions inherited from SignalReceiver
	SignalReceiver ()=default
	Default constructor.
	SignalReceiver (const SignalReceiver &other)
	Copy constructor, does not copy any existing signal connections from other.
SignalReceiver &	operator= (SignalReceiver rhs)
	Assignment operator, disconnects all existing connections, does not copy any existing signal connections from rhs.
virtual	~SignalReceiver ()
	Virtual destructor disconnects from all connected signals.

Static Public Member Functions
static bool	createCompatible (const DataList &data, Algorithm **a=nullptr)
Static Public Member Functions inherited from Algorithm
static bool	createCompatible (const DataList &data, Algorithm **a=nullptr)
	Factory function to check algorithm compatibility with input data and optionally instantiate it.

Public Attributes
Parameter< Similarity >	p_similarity = {"similarity", Similarity::Dot, this}
Parameter< Transformation >	p_transformation = {"transformation", Transformation::Rigid, this}
Parameter< bool >	p_quantize = {"quantize", false, this}
Parameter< bool >	p_relativeWeight = {"relativeWeight", false, this}
Parameter< double >	p_rotationRange = {"rotationRange", 40.0, this}
Parameter< double >	p_translationRange = {"translationRange", 80.0, this}
Parameter< int >	p_searchTrials = {"searchTrials", 256, this}
Parameter< int >	p_blockSize = {"blockSize", 128, this}
Parameter< double >	p_weightThreshold = {"weightThreshold", 1e-3, this}
Public Attributes inherited from Algorithm
Signal	signalOutputChanged
	Signal should be emitted by Algorithms when their output/result has changed.
Signal	signalParametersChanged
	Signal should be emitted by Algorithms when their parameter configuration has changed.
Public Attributes inherited from Configurable
Signal	signalParametersChanged
	Emitted whenever one of the registered Parameters' or SubPropertys' signalValueChanged signal was emitted.

Additional Inherited Members
Protected Member Functions inherited from Algorithm
void	loadDefaults ()
void	registerAction (const std::string &id, const std::string &guiName, const std::function< Algorithm::Status(void)> &action)
	Register an action to be run via runAction.
template<typename D>
void	registerAction (const std::string &id, const std::string &guiName, Algorithm::Status(D::*action)(void))
	Template version of runAction that can be used with a pointer to a member function.
void	registerAction (const Action &action)
	Register an action.
Protected Member Functions inherited from SignalReceiver
void	disconnectAll ()
	Disconnects all existing connections.
Protected Attributes inherited from OptimizingAlgorithm
std::shared_ptr< Optimizer >	m_opt
	The optimizer instance.
Protected Attributes inherited from Algorithm
std::string	m_name
	Algorithm name.
Progress *	m_progress = nullptr
	Non-owing pointer to a progress interface. May be a nullptr.
FactoryInfo	m_factoryInfo = {}
	Record describing how this algorithm was instantiated by the AlgorithmFactory.
int	m_status = Status::Unknown
	Algorithm status after last call to compute()
std::vector< Action >	m_actions
	Map of key given by the id of the action, of the available actions of this algorithm.
Protected Attributes inherited from Configurable
std::vector< Param >	m_params
	List of all registered Parameter and SubProperty instances.

Member Enumeration Documentation

Similarity

enum class Similarity

strong

Enumerator
Dot	Dot product similarity.
SSD	Sum of squared differences.

Member Function Documentation

compute()

void compute ( )

overridevirtual

Execute the algorithm.

Implements Algorithm.

evaluate()

double evaluate ( int n, const double * x, double * dx )

overridevirtual

Evaluates the objective function using parameters x. This algorithm supports gradients.

Implements CostFunction.

globalSearch() [1/2]

std::vector< std::pair< Eigen::VectorXd, double > > globalSearch	(	const Eigen::VectorXd &	lowerBound,
		const Eigen::VectorXd &	upperBound,
		int	populationSize )

Executes global search of the optimal parameters within the given bounds.

Returns a vector of pairs {(parameters, score), ...} sorted from best to worst

globalSearch() [2/2]

std::vector< std::pair< Eigen::VectorXd, double > > globalSearch

(

)

Runs global search using the parameters specified in p_rotationRange, p_translationRange, p_searchTrials.

Returns a vector of pairs {(parameters, score), ...} sorted from best to worst

configuration()

void configuration ( Properties * p ) const

overridevirtual

Serialize the current object configuration into the given Properties object.

The default implementation will do so automatically for all registered Parameter and SubProperty instances.

See also

configure() for the inverse functionality

Reimplemented from Configurable.

---

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

• ImFusion/Reg/FeatureMapsRegistrationAlgorithm.h