Point Cloud Library (PCL)  1.8.1-dev
List of all members | Public Types | Public Member Functions | Protected Member Functions | Protected Attributes
pcl::registration::DefaultConvergenceCriteria< Scalar > Class Template Reference

DefaultConvergenceCriteria represents an instantiation of ConvergenceCriteria, and implements the following criteria for registration loop evaluation: More...

#include <pcl/registration/default_convergence_criteria.h>

+ Inheritance diagram for pcl::registration::DefaultConvergenceCriteria< Scalar >:

Public Types

enum  ConvergenceState {
  CONVERGENCE_CRITERIA_NOT_CONVERGED, CONVERGENCE_CRITERIA_ITERATIONS, CONVERGENCE_CRITERIA_TRANSFORM, CONVERGENCE_CRITERIA_ABS_MSE,
  CONVERGENCE_CRITERIA_REL_MSE, CONVERGENCE_CRITERIA_NO_CORRESPONDENCES
}
 
typedef boost::shared_ptr
< DefaultConvergenceCriteria
< Scalar > > 
Ptr
 
typedef boost::shared_ptr
< const
DefaultConvergenceCriteria
< Scalar > > 
ConstPtr
 
typedef Eigen::Matrix< Scalar, 4, 4 > Matrix4
 
- Public Types inherited from pcl::registration::ConvergenceCriteria
typedef boost::shared_ptr
< ConvergenceCriteria
Ptr
 
typedef boost::shared_ptr
< const ConvergenceCriteria
ConstPtr
 

Public Member Functions

 DefaultConvergenceCriteria (const int &iterations, const Matrix4 &transform, const pcl::Correspondences &correspondences)
 Empty constructor. More...
 
virtual ~DefaultConvergenceCriteria ()
 Empty destructor. More...
 
void setMaximumIterationsSimilarTransforms (const int nr_iterations)
 Set the maximum number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar. More...
 
int getMaximumIterationsSimilarTransforms () const
 Get the maximum number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar, as set by the user. More...
 
void setMaximumIterations (const int nr_iterations)
 Set the maximum number of iterations the internal optimization should run for. More...
 
int getMaximumIterations () const
 Get the maximum number of iterations the internal optimization should run for, as set by the user. More...
 
void setFailureAfterMaximumIterations (const bool failure_after_max_iter)
 Specifies if the registration fails or converges when the maximum number of iterations is reached. More...
 
bool getFailureAfterMaximumIterations () const
 Get whether the registration will fail or converge when the maximum number of iterations is reached. More...
 
void setRotationThreshold (const double threshold)
 Set the rotation threshold cosine angle (maximum allowable difference between two consecutive transformations) in order for an optimization to be considered as having converged to the final solution. More...
 
double getRotationThreshold () const
 Get the rotation threshold cosine angle (maximum allowable difference between two consecutive transformations) as set by the user. More...
 
void setTranslationThreshold (const double threshold)
 Set the translation threshold (maximum allowable difference between two consecutive transformations) in order for an optimization to be considered as having converged to the final solution. More...
 
double getTranslationThreshold () const
 Get the rotation threshold cosine angle (maximum allowable difference between two consecutive transformations) as set by the user. More...
 
void setRelativeMSE (const double mse_relative)
 Set the relative MSE between two consecutive sets of correspondences. More...
 
double getRelativeMSE () const
 Get the relative MSE between two consecutive sets of correspondences. More...
 
void setAbsoluteMSE (const double mse_absolute)
 Set the absolute MSE between two consecutive sets of correspondences. More...
 
double getAbsoluteMSE () const
 Get the absolute MSE between two consecutive sets of correspondences. More...
 
virtual bool hasConverged ()
 Check if convergence has been reached. More...
 
ConvergenceState getConvergenceState ()
 Return the convergence state after hasConverged () More...
 
void setConvergenceState (ConvergenceState c)
 Sets the convergence state externally (for example, when ICP does not find enough correspondences to estimate a transformation, the function is called setting the convergence state to ConvergenceState::CONVERGENCE_CRITERIA_NO_CORRESPONDENCES) More...
 
- Public Member Functions inherited from pcl::registration::ConvergenceCriteria
 ConvergenceCriteria ()
 Empty constructor. More...
 
virtual ~ConvergenceCriteria ()
 Empty destructor. More...
 
 operator bool ()
 Bool operator. More...
 

Protected Member Functions

double calculateMSE (const pcl::Correspondences &correspondences) const
 Calculate the mean squared error (MSE) of the distance for a given set of correspondences. More...
 

Protected Attributes

const int & iterations_
 The number of iterations done by the registration loop so far. More...
 
const Matrix4transformation_
 The current transformation obtained by the transformation estimation method. More...
 
const pcl::Correspondencescorrespondences_
 The current set of point correspondences between the source and the target. More...
 
double correspondences_prev_mse_
 The MSE for the previous set of correspondences. More...
 
double correspondences_cur_mse_
 The MSE for the current set of correspondences. More...
 
int max_iterations_
 The maximum nuyyGmber of iterations that the registration loop is to be executed. More...
 
bool failure_after_max_iter_
 Specifys if the registration fails or converges when the maximum number of iterations is reached. More...
 
double rotation_threshold_
 The rotation threshold is the relative rotation between two iterations (as angle cosine). More...
 
double translation_threshold_
 The translation threshold is the relative translation between two iterations (0 if no translation). More...
 
double mse_threshold_relative_
 The relative change from the previous MSE for the current set of correspondences, e.g. More...
 
double mse_threshold_absolute_
 The absolute change from the previous MSE for the current set of correspondences. More...
 
int iterations_similar_transforms_
 Internal counter for the number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar. More...
 
int max_iterations_similar_transforms_
 The maximum number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar. More...
 
ConvergenceState convergence_state_
 The state of the convergence (e.g., why did the registration converge). More...
 

Detailed Description

template<typename Scalar = float>
class pcl::registration::DefaultConvergenceCriteria< Scalar >

DefaultConvergenceCriteria represents an instantiation of ConvergenceCriteria, and implements the following criteria for registration loop evaluation:

Note
Convergence is considered reached if ANY of the above criteria are met.
Author
Radu B. Rusu

Definition at line 65 of file default_convergence_criteria.h.

Member Typedef Documentation

template<typename Scalar = float>
typedef boost::shared_ptr<const DefaultConvergenceCriteria<Scalar> > pcl::registration::DefaultConvergenceCriteria< Scalar >::ConstPtr

Definition at line 69 of file default_convergence_criteria.h.

template<typename Scalar = float>
typedef Eigen::Matrix<Scalar, 4, 4> pcl::registration::DefaultConvergenceCriteria< Scalar >::Matrix4

Definition at line 71 of file default_convergence_criteria.h.

template<typename Scalar = float>
typedef boost::shared_ptr<DefaultConvergenceCriteria<Scalar> > pcl::registration::DefaultConvergenceCriteria< Scalar >::Ptr

Definition at line 68 of file default_convergence_criteria.h.

Member Enumeration Documentation

Enumerator
CONVERGENCE_CRITERIA_NOT_CONVERGED 
CONVERGENCE_CRITERIA_ITERATIONS 
CONVERGENCE_CRITERIA_TRANSFORM 
CONVERGENCE_CRITERIA_ABS_MSE 
CONVERGENCE_CRITERIA_REL_MSE 
CONVERGENCE_CRITERIA_NO_CORRESPONDENCES 

Definition at line 73 of file default_convergence_criteria.h.

Constructor & Destructor Documentation

template<typename Scalar = float>
pcl::registration::DefaultConvergenceCriteria< Scalar >::DefaultConvergenceCriteria ( const int &  iterations,
const Matrix4 transform,
const pcl::Correspondences correspondences 
)
inline

Empty constructor.

Sets:

  • the maximum number of iterations to 1000
  • the rotation threshold to 0.256 degrees (0.99999)
  • the translation threshold to 0.0003 meters (3e-4^2)
  • the MSE relative / absolute thresholds to 0.001% and 1e-12
Parameters
[in]iterationsa reference to the number of iterations the loop has ran so far
[in]transforma reference to the current transformation obtained by the transformation evaluation
[in]correspondencesa reference to the current set of point correspondences between source and target

Definition at line 94 of file default_convergence_criteria.h.

template<typename Scalar = float>
virtual pcl::registration::DefaultConvergenceCriteria< Scalar >::~DefaultConvergenceCriteria ( )
inlinevirtual

Empty destructor.

Definition at line 113 of file default_convergence_criteria.h.

Member Function Documentation

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::calculateMSE ( const pcl::Correspondences correspondences) const
inlineprotected

Calculate the mean squared error (MSE) of the distance for a given set of correspondences.

Parameters
[in]correspondencesthe given set of correspondences

Definition at line 219 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::getAbsoluteMSE ( ) const
inline

Get the absolute MSE between two consecutive sets of correspondences.

Definition at line 188 of file default_convergence_criteria.h.

template<typename Scalar = float>
ConvergenceState pcl::registration::DefaultConvergenceCriteria< Scalar >::getConvergenceState ( )
inline

Return the convergence state after hasConverged ()

Definition at line 197 of file default_convergence_criteria.h.

template<typename Scalar = float>
bool pcl::registration::DefaultConvergenceCriteria< Scalar >::getFailureAfterMaximumIterations ( ) const
inline

Get whether the registration will fail or converge when the maximum number of iterations is reached.

Definition at line 146 of file default_convergence_criteria.h.

template<typename Scalar = float>
int pcl::registration::DefaultConvergenceCriteria< Scalar >::getMaximumIterations ( ) const
inline

Get the maximum number of iterations the internal optimization should run for, as set by the user.

Definition at line 136 of file default_convergence_criteria.h.

template<typename Scalar = float>
int pcl::registration::DefaultConvergenceCriteria< Scalar >::getMaximumIterationsSimilarTransforms ( ) const
inline

Get the maximum number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar, as set by the user.

Definition at line 126 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::getRelativeMSE ( ) const
inline

Get the relative MSE between two consecutive sets of correspondences.

Definition at line 178 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::getRotationThreshold ( ) const
inline

Get the rotation threshold cosine angle (maximum allowable difference between two consecutive transformations) as set by the user.

Definition at line 157 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::getTranslationThreshold ( ) const
inline

Get the rotation threshold cosine angle (maximum allowable difference between two consecutive transformations) as set by the user.

Definition at line 168 of file default_convergence_criteria.h.

template<typename Scalar >
bool pcl::registration::DefaultConvergenceCriteria< Scalar >::hasConverged ( )
virtual

Check if convergence has been reached.

Implements pcl::registration::ConvergenceCriteria.

Definition at line 47 of file default_convergence_criteria.hpp.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setAbsoluteMSE ( const double  mse_absolute)
inline

Set the absolute MSE between two consecutive sets of correspondences.

Parameters
[in]mse_absolutethe relative MSE threshold

Definition at line 184 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setConvergenceState ( ConvergenceState  c)
inline

Sets the convergence state externally (for example, when ICP does not find enough correspondences to estimate a transformation, the function is called setting the convergence state to ConvergenceState::CONVERGENCE_CRITERIA_NO_CORRESPONDENCES)

Parameters
[in]cthe convergence state

Definition at line 208 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setFailureAfterMaximumIterations ( const bool  failure_after_max_iter)
inline

Specifies if the registration fails or converges when the maximum number of iterations is reached.

Parameters
[in]failure_after_max_iterIf true, the registration fails. If false, the registration is assumed to have converged.

Definition at line 142 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setMaximumIterations ( const int  nr_iterations)
inline

Set the maximum number of iterations the internal optimization should run for.

Parameters
[in]nr_iterationsthe maximum number of iterations the internal optimization should run for

Definition at line 132 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setMaximumIterationsSimilarTransforms ( const int  nr_iterations)
inline

Set the maximum number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar.

Parameters
[in]nr_iterationsthe maximum number of iterations

Definition at line 120 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setRelativeMSE ( const double  mse_relative)
inline

Set the relative MSE between two consecutive sets of correspondences.

Parameters
[in]mse_relativethe relative MSE threshold

Definition at line 174 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setRotationThreshold ( const double  threshold)
inline

Set the rotation threshold cosine angle (maximum allowable difference between two consecutive transformations) in order for an optimization to be considered as having converged to the final solution.

Parameters
[in]thresholdthe rotation threshold in order for an optimization to be considered as having converged to the final solution.

Definition at line 152 of file default_convergence_criteria.h.

template<typename Scalar = float>
void pcl::registration::DefaultConvergenceCriteria< Scalar >::setTranslationThreshold ( const double  threshold)
inline

Set the translation threshold (maximum allowable difference between two consecutive transformations) in order for an optimization to be considered as having converged to the final solution.

Parameters
[in]thresholdthe translation threshold in order for an optimization to be considered as having converged to the final solution.

Definition at line 163 of file default_convergence_criteria.h.

Member Data Documentation

template<typename Scalar = float>
ConvergenceState pcl::registration::DefaultConvergenceCriteria< Scalar >::convergence_state_
protected

The state of the convergence (e.g., why did the registration converge).

Definition at line 270 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getConvergenceState(), and pcl::registration::DefaultConvergenceCriteria< float >::setConvergenceState().

template<typename Scalar = float>
const pcl::Correspondences& pcl::registration::DefaultConvergenceCriteria< Scalar >::correspondences_
protected

The current set of point correspondences between the source and the target.

Definition at line 235 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::correspondences_cur_mse_
protected

The MSE for the current set of correspondences.

Definition at line 241 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::correspondences_prev_mse_
protected

The MSE for the previous set of correspondences.

Definition at line 238 of file default_convergence_criteria.h.

template<typename Scalar = float>
bool pcl::registration::DefaultConvergenceCriteria< Scalar >::failure_after_max_iter_
protected

Specifys if the registration fails or converges when the maximum number of iterations is reached.

Definition at line 247 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getFailureAfterMaximumIterations(), and pcl::registration::DefaultConvergenceCriteria< float >::setFailureAfterMaximumIterations().

template<typename Scalar = float>
const int& pcl::registration::DefaultConvergenceCriteria< Scalar >::iterations_
protected

The number of iterations done by the registration loop so far.

Definition at line 229 of file default_convergence_criteria.h.

template<typename Scalar = float>
int pcl::registration::DefaultConvergenceCriteria< Scalar >::iterations_similar_transforms_
protected

Internal counter for the number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar.

Definition at line 263 of file default_convergence_criteria.h.

template<typename Scalar = float>
int pcl::registration::DefaultConvergenceCriteria< Scalar >::max_iterations_
protected

The maximum nuyyGmber of iterations that the registration loop is to be executed.

Definition at line 244 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getMaximumIterations(), and pcl::registration::DefaultConvergenceCriteria< float >::setMaximumIterations().

template<typename Scalar = float>
int pcl::registration::DefaultConvergenceCriteria< Scalar >::max_iterations_similar_transforms_
protected

The maximum number of iterations that the internal rotation, translation, and MSE differences are allowed to be similar.

Definition at line 267 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getMaximumIterationsSimilarTransforms(), and pcl::registration::DefaultConvergenceCriteria< float >::setMaximumIterationsSimilarTransforms().

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::mse_threshold_absolute_
protected

The absolute change from the previous MSE for the current set of correspondences.

Definition at line 259 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getAbsoluteMSE(), and pcl::registration::DefaultConvergenceCriteria< float >::setAbsoluteMSE().

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::mse_threshold_relative_
protected

The relative change from the previous MSE for the current set of correspondences, e.g.

.1 means 10% change.

Definition at line 256 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getRelativeMSE(), and pcl::registration::DefaultConvergenceCriteria< float >::setRelativeMSE().

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::rotation_threshold_
protected

The rotation threshold is the relative rotation between two iterations (as angle cosine).

Definition at line 250 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getRotationThreshold(), and pcl::registration::DefaultConvergenceCriteria< float >::setRotationThreshold().

template<typename Scalar = float>
const Matrix4& pcl::registration::DefaultConvergenceCriteria< Scalar >::transformation_
protected

The current transformation obtained by the transformation estimation method.

Definition at line 232 of file default_convergence_criteria.h.

template<typename Scalar = float>
double pcl::registration::DefaultConvergenceCriteria< Scalar >::translation_threshold_
protected

The translation threshold is the relative translation between two iterations (0 if no translation).

Definition at line 253 of file default_convergence_criteria.h.

Referenced by pcl::registration::DefaultConvergenceCriteria< float >::getTranslationThreshold(), and pcl::registration::DefaultConvergenceCriteria< float >::setTranslationThreshold().


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