W3cubDocs

/PointCloudLibrary

FPCSInitialAlignment computes corresponding four point congruent sets as described in: "4-points congruent sets for robust pairwise surface registration", Dror Aiger, Niloy Mitra, Daniel Cohen-Or. More...

#include <pcl/registration/ia_fpcs.h>

Public Member Functions

FPCSInitialAlignment ()
Constructor. More...
~FPCSInitialAlignment ()
Destructor. More...
void setTargetIndices (const IndicesPtr &target_indices)
Provide a pointer to the vector of target indices. More...
IndicesPtr getTargetIndices () const
void setSourceNormals (const NormalsConstPtr &source_normals)
Provide a pointer to the normals of the source point cloud. More...
NormalsConstPtr getSourceNormals () const
void setTargetNormals (const NormalsConstPtr &target_normals)
Provide a pointer to the normals of the target point cloud. More...
NormalsConstPtr getTargetNormals () const
void setNumberOfThreads (int nr_threads)
Set the number of used threads if OpenMP is activated. More...
int getNumberOfThreads () const
void setDelta (float delta, bool normalize=false)
Set the constant factor delta which weights the internally calculated parameters. More...
float getDelta () const
void setApproxOverlap (float approx_overlap)
Set the approximate overlap between source and target. More...
float getApproxOverlap () const
void setScoreThreshold (float score_threshold)
Set the scoring threshold used for early finishing the method. More...
float getScoreThreshold () const
void setNumberOfSamples (int nr_samples)
Set the number of source samples to use during alignment. More...
int getNumberOfSamples () const
void setMaxNormalDifference (float max_norm_diff)
Set the maximum normal difference between valid point correspondences in degree. More...
float getMaxNormalDifference () const
void setMaxComputationTime (int max_runtime)
Set the maximum computation time in seconds. More...
int getMaxComputationTime () const
float getFitnessScore () const
- Public Member Functions inherited from pcl::Registration< PointSource, PointTarget, float >
Registration ()
Empty constructor. More...
~Registration ()
destructor. More...
void setTransformationEstimation (const TransformationEstimationPtr &te)
Provide a pointer to the transformation estimation object. More...
void setCorrespondenceEstimation (const CorrespondenceEstimationPtr &ce)
Provide a pointer to the correspondence estimation object. More...
virtual void setInputSource (const PointCloudSourceConstPtr &cloud)
Provide a pointer to the input source (e.g., the point cloud that we want to align to the target) More...
const PointCloudSourceConstPtr getInputSource ()
Get a pointer to the input point cloud dataset target. More...
virtual void setInputTarget (const PointCloudTargetConstPtr &cloud)
Provide a pointer to the input target (e.g., the point cloud that we want to align the input source to) More...
const PointCloudTargetConstPtr getInputTarget ()
Get a pointer to the input point cloud dataset target. More...
void setSearchMethodTarget (const KdTreePtr &tree, bool force_no_recompute=false)
Provide a pointer to the search object used to find correspondences in the target cloud. More...
KdTreePtr getSearchMethodTarget () const
Get a pointer to the search method used to find correspondences in the target cloud. More...
void setSearchMethodSource (const KdTreeReciprocalPtr &tree, bool force_no_recompute=false)
Provide a pointer to the search object used to find correspondences in the source cloud (usually used by reciprocal correspondence finding). More...
KdTreeReciprocalPtr getSearchMethodSource () const
Get a pointer to the search method used to find correspondences in the source cloud. More...
Matrix4 getFinalTransformation ()
Get the final transformation matrix estimated by the registration method. More...
Matrix4 getLastIncrementalTransformation ()
Get the last incremental transformation matrix estimated by the registration method. More...
void setMaximumIterations (int nr_iterations)
Set the maximum number of iterations the internal optimization should run for. More...
int getMaximumIterations ()
Get the maximum number of iterations the internal optimization should run for, as set by the user. More...
void setRANSACIterations (int ransac_iterations)
Set the number of iterations RANSAC should run for. More...
double getRANSACIterations ()
Get the number of iterations RANSAC should run for, as set by the user. More...
void setRANSACOutlierRejectionThreshold (double inlier_threshold)
Set the inlier distance threshold for the internal RANSAC outlier rejection loop. More...
double getRANSACOutlierRejectionThreshold ()
Get the inlier distance threshold for the internal outlier rejection loop as set by the user. More...
void setMaxCorrespondenceDistance (double distance_threshold)
Set the maximum distance threshold between two correspondent points in source <-> target. More...
double getMaxCorrespondenceDistance ()
Get the maximum distance threshold between two correspondent points in source <-> target. More...
void setTransformationEpsilon (double epsilon)
Set the transformation epsilon (maximum allowable translation squared difference between two consecutive transformations) in order for an optimization to be considered as having converged to the final solution. More...
double getTransformationEpsilon ()
Get the transformation epsilon (maximum allowable translation squared difference between two consecutive transformations) as set by the user. More...
void setTransformationRotationEpsilon (double epsilon)
Set the transformation rotation epsilon (maximum allowable rotation difference between two consecutive transformations) in order for an optimization to be considered as having converged to the final solution. More...
double getTransformationRotationEpsilon ()
Get the transformation rotation epsilon (maximum allowable difference between two consecutive transformations) as set by the user (epsilon is the cos(angle) in a axis-angle representation). More...
void setEuclideanFitnessEpsilon (double epsilon)
Set the maximum allowed Euclidean error between two consecutive steps in the ICP loop, before the algorithm is considered to have converged. More...
double getEuclideanFitnessEpsilon ()
Get the maximum allowed distance error before the algorithm will be considered to have converged, as set by the user. More...
void setPointRepresentation (const PointRepresentationConstPtr &point_representation)
Provide a boost shared pointer to the PointRepresentation to be used when comparing points. More...
bool registerVisualizationCallback (std::function< UpdateVisualizerCallbackSignature > &visualizerCallback)
Register the user callback function which will be called from registration thread in order to update point cloud obtained after each iteration. More...
double getFitnessScore (double max_range=std::numeric_limits< double >::max())
Obtain the Euclidean fitness score (e.g., mean of squared distances from the source to the target) More...
double getFitnessScore (const std::vector< float > &distances_a, const std::vector< float > &distances_b)
Obtain the Euclidean fitness score (e.g., mean of squared distances from the source to the target) from two sets of correspondence distances (distances between source and target points) More...
bool hasConverged () const
Return the state of convergence after the last align run. More...
void align (PointCloudSource &output)
Call the registration algorithm which estimates the transformation and returns the transformed source (input) as output. More...
void align (PointCloudSource &output, const Matrix4 &guess)
Call the registration algorithm which estimates the transformation and returns the transformed source (input) as output. More...
const std::string & getClassName () const
Abstract class get name method. More...
bool initCompute ()
Internal computation initialization. More...
bool initComputeReciprocal ()
Internal computation when reciprocal lookup is needed. More...
void addCorrespondenceRejector (const CorrespondenceRejectorPtr &rejector)
Add a new correspondence rejector to the list. More...
std::vector< CorrespondenceRejectorPtr > getCorrespondenceRejectors ()
Get the list of correspondence rejectors. More...
bool removeCorrespondenceRejector (unsigned int i)
Remove the i-th correspondence rejector in the list. More...
void clearCorrespondenceRejectors ()
Clear the list of correspondence rejectors. More...
- Public Member Functions inherited from pcl::PCLBase< PointSource >
PCLBase ()
Empty constructor. More...
PCLBase (const PCLBase &base)
Copy constructor. More...
virtual ~PCLBase ()=default
Destructor. More...
virtual void setInputCloud (const PointCloudConstPtr &cloud)
Provide a pointer to the input dataset. More...
const PointCloudConstPtr getInputCloud () const
Get a pointer to the input point cloud dataset. More...
virtual void setIndices (const IndicesPtr &indices)
Provide a pointer to the vector of indices that represents the input data. More...
virtual void setIndices (const IndicesConstPtr &indices)
Provide a pointer to the vector of indices that represents the input data. More...
virtual void setIndices (const PointIndicesConstPtr &indices)
Provide a pointer to the vector of indices that represents the input data. More...
virtual void setIndices (std::size_t row_start, std::size_t col_start, std::size_t nb_rows, std::size_t nb_cols)
Set the indices for the points laying within an interest region of the point cloud. More...
IndicesPtr getIndices ()
Get a pointer to the vector of indices used. More...
const IndicesConstPtr getIndices () const
Get a pointer to the vector of indices used. More...
const PointSource & operator[] (std::size_t pos) const
Override PointCloud operator[] to shorten code. More...

Protected Member Functions

void computeTransformation (PointCloudSource &output, const Eigen::Matrix4f &guess) override
Rigid transformation computation method. More...
virtual bool initCompute ()
Internal computation initialization. More...
int selectBase (pcl::Indices &base_indices, float(&ratio)[2])
Select an approximately coplanar set of four points from the source cloud. More...
int selectBaseTriangle (pcl::Indices &base_indices)
Select randomly a triplet of points with large point-to-point distances. More...
void setupBase (pcl::Indices &base_indices, float(&ratio)[2])
Setup the base (four coplanar points) by ordering the points and computing intersection ratios and segment to segment distances of base diagonal. More...
float segmentToSegmentDist (const pcl::Indices &base_indices, float(&ratio)[2])
Calculate intersection ratios and segment to segment distances of base diagonals. More...
virtual int bruteForceCorrespondences (int idx1, int idx2, pcl::Correspondences &pairs)
Search for corresponding point pairs given the distance between two base points. More...
virtual int determineBaseMatches (const pcl::Indices &base_indices, std::vector< pcl::Indices > &matches, const pcl::Correspondences &pairs_a, const pcl::Correspondences &pairs_b, const float(&ratio)[2])
Determine base matches by combining the point pair candidate and search for coinciding intersection points using the diagonal segment ratios of base B. More...
int checkBaseMatch (const pcl::Indices &match_indices, const float(&ds)[4])
Check if outer rectangle distance of matched points fit with the base rectangle. More...
virtual void handleMatches (const pcl::Indices &base_indices, std::vector< pcl::Indices > &matches, MatchingCandidates &candidates)
Method to handle current candidate matches. More...
virtual void linkMatchWithBase (const pcl::Indices &base_indices, pcl::Indices &match_indices, pcl::Correspondences &correspondences)
Sets the correspondences between the base B and the match M by using the distance of each point to the centroid of the rectangle. More...
virtual int validateMatch (const pcl::Indices &base_indices, const pcl::Indices &match_indices, const pcl::Correspondences &correspondences, Eigen::Matrix4f &transformation)
Validate the matching by computing the transformation between the source and target based on the four matched points and by comparing the mean square error (MSE) to a threshold. More...
virtual int validateTransformation (Eigen::Matrix4f &transformation, float &fitness_score)
Validate the transformation by calculating the number of inliers after transforming the source cloud. More...
virtual void finalCompute (const std::vector< MatchingCandidates > &candidates)
Final computation of best match out of vector of best matches. More...
- Protected Member Functions inherited from pcl::Registration< PointSource, PointTarget, float >
bool searchForNeighbors (const PointCloudSource &cloud, int index, pcl::Indices &indices, std::vector< float > &distances)
Search for the closest nearest neighbor of a given point. More...
virtual void computeTransformation (PointCloudSource &output, const Matrix4 &guess)=0
Abstract transformation computation method with initial guess. More...
- Protected Member Functions inherited from pcl::PCLBase< PointSource >
bool initCompute ()
This method should get called before starting the actual computation. More...
bool deinitCompute ()
This method should get called after finishing the actual computation. More...

Protected Attributes

NormalsConstPtr source_normals_
Normals of source point cloud. More...
NormalsConstPtr target_normals_
Normals of target point cloud. More...
int nr_threads_
Number of threads for parallelization (standard = 1). More...
float approx_overlap_
Estimated overlap between source and target (standard = 0.5). More...
float delta_
Delta value of 4pcs algorithm (standard = 1.0). More...
float score_threshold_
Score threshold to stop calculation with success. More...
int nr_samples_
The number of points to uniformly sample the source point cloud. More...
float max_norm_diff_
Maximum normal difference of corresponding point pairs in degrees (standard = 90). More...
int max_runtime_
Maximum allowed computation time in seconds (standard = 0 => ~unlimited). More...
float fitness_score_
Resulting fitness score of the best match. More...
float diameter_
Estimated diamter of the target point cloud. More...
float max_base_diameter_sqr_
Estimated squared metric overlap between source and target. More...
bool use_normals_
Use normals flag. More...
bool normalize_delta_
Normalize delta flag. More...
pcl::IndicesPtr source_indices_
A pointer to the vector of source point indices to use after sampling. More...
pcl::IndicesPtr target_indices_
A pointer to the vector of target point indices to use after sampling. More...
float max_pair_diff_
Maximal difference between corresponding point pairs in source and target. More...
float max_edge_diff_
Maximal difference between the length of the base edges and valid match edges. More...
float coincidation_limit_
Maximal distance between coinciding intersection points to find valid matches. More...
float max_mse_
Maximal mean squared errors of a transformation calculated from a candidate match. More...
float max_inlier_dist_sqr_
Maximal squared point distance between source and target points to count as inlier. More...
const float small_error_
Definition of a small error. More...
- Protected Attributes inherited from pcl::Registration< PointSource, PointTarget, float >
std::string reg_name_
The registration method name. More...
KdTreePtr tree_
A pointer to the spatial search object. More...
KdTreeReciprocalPtr tree_reciprocal_
A pointer to the spatial search object of the source. More...
int nr_iterations_
The number of iterations the internal optimization ran for (used internally). More...
int max_iterations_
The maximum number of iterations the internal optimization should run for. More...
int ransac_iterations_
The number of iterations RANSAC should run for. More...
PointCloudTargetConstPtr target_
The input point cloud dataset target. More...
Matrix4 final_transformation_
The final transformation matrix estimated by the registration method after N iterations. More...
Matrix4 transformation_
The transformation matrix estimated by the registration method. More...
Matrix4 previous_transformation_
The previous transformation matrix estimated by the registration method (used internally). More...
double transformation_epsilon_
The maximum difference between two consecutive transformations in order to consider convergence (user defined). More...
double transformation_rotation_epsilon_
The maximum rotation difference between two consecutive transformations in order to consider convergence (user defined). More...
double euclidean_fitness_epsilon_
The maximum allowed Euclidean error between two consecutive steps in the ICP loop, before the algorithm is considered to have converged. More...
double corr_dist_threshold_
The maximum distance threshold between two correspondent points in source <-> target. More...
double inlier_threshold_
The inlier distance threshold for the internal RANSAC outlier rejection loop. More...
bool converged_
Holds internal convergence state, given user parameters. More...
int min_number_correspondences_
The minimum number of correspondences that the algorithm needs before attempting to estimate the transformation. More...
CorrespondencesPtr correspondences_
The set of correspondences determined at this ICP step. More...
TransformationEstimationPtr transformation_estimation_
A TransformationEstimation object, used to calculate the 4x4 rigid transformation. More...
CorrespondenceEstimationPtr correspondence_estimation_
A CorrespondenceEstimation object, used to estimate correspondences between the source and the target cloud. More...
std::vector< CorrespondenceRejectorPtr > correspondence_rejectors_
The list of correspondence rejectors to use. More...
bool target_cloud_updated_
Variable that stores whether we have a new target cloud, meaning we need to pre-process it again. More...
bool source_cloud_updated_
Variable that stores whether we have a new source cloud, meaning we need to pre-process it again. More...
bool force_no_recompute_
A flag which, if set, means the tree operating on the target cloud will never be recomputed. More...
bool force_no_recompute_reciprocal_
A flag which, if set, means the tree operating on the source cloud will never be recomputed. More...
std::function< UpdateVisualizerCallbackSignature > update_visualizer_
Callback function to update intermediate source point cloud position during it's registration to the target point cloud. More...
- Protected Attributes inherited from pcl::PCLBase< PointSource >
PointCloudConstPtr input_
The input point cloud dataset. More...
IndicesPtr indices_
A pointer to the vector of point indices to use. More...
bool use_indices_
Set to true if point indices are used. More...
bool fake_indices_
If no set of indices are given, we construct a set of fake indices that mimic the input PointCloud. More...

Additional Inherited Members

- Public Types inherited from pcl::Registration< PointSource, PointTarget, float >
using Matrix4 = Eigen::Matrix< float, 4, 4 >
using Ptr = shared_ptr< Registration< PointSource, PointTarget, float > >
using ConstPtr = shared_ptr< const Registration< PointSource, PointTarget, float > >
using CorrespondenceRejectorPtr = pcl::registration::CorrespondenceRejector::Ptr
using KdTree = pcl::search::KdTree< PointTarget >
using KdTreePtr = typename KdTree::Ptr
using KdTreeReciprocal = pcl::search::KdTree< PointSource >
using KdTreeReciprocalPtr = typename KdTreeReciprocal::Ptr
using PointCloudSource = pcl::PointCloud< PointSource >
using PointCloudSourcePtr = typename PointCloudSource::Ptr
using PointCloudSourceConstPtr = typename PointCloudSource::ConstPtr
using PointCloudTarget = pcl::PointCloud< PointTarget >
using PointCloudTargetPtr = typename PointCloudTarget::Ptr
using PointCloudTargetConstPtr = typename PointCloudTarget::ConstPtr
using PointRepresentationConstPtr = typename KdTree::PointRepresentationConstPtr
using TransformationEstimation = typename pcl::registration::TransformationEstimation< PointSource, PointTarget, float >
using TransformationEstimationPtr = typename TransformationEstimation::Ptr
using TransformationEstimationConstPtr = typename TransformationEstimation::ConstPtr
using CorrespondenceEstimation = pcl::registration::CorrespondenceEstimationBase< PointSource, PointTarget, float >
using CorrespondenceEstimationPtr = typename CorrespondenceEstimation::Ptr
using CorrespondenceEstimationConstPtr = typename CorrespondenceEstimation::ConstPtr
using UpdateVisualizerCallbackSignature = void(const pcl::PointCloud< PointSource > &, const pcl::Indices &, const pcl::PointCloud< PointTarget > &, const pcl::Indices &)
The callback signature to the function updating intermediate source point cloud position during it's registration to the target point cloud. More...
- Public Types inherited from pcl::PCLBase< PointSource >
using PointCloud = pcl::PointCloud< PointSource >
using PointCloudPtr = typename PointCloud::Ptr
using PointCloudConstPtr = typename PointCloud::ConstPtr
using PointIndicesPtr = PointIndices::Ptr
using PointIndicesConstPtr = PointIndices::ConstPtr

Detailed Description

template<typename PointSource, typename PointTarget, typename NormalT = pcl::Normal, typename Scalar = float>
class pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >

FPCSInitialAlignment computes corresponding four point congruent sets as described in: "4-points congruent sets for robust pairwise surface registration", Dror Aiger, Niloy Mitra, Daniel Cohen-Or.

ACM Transactions on Graphics, vol. 27(3), 2008

Author
P.W.Theiler

Definition at line 81 of file ia_fpcs.h.

Constructor & Destructor Documentation

FPCSInitialAlignment()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::FPCSInitialAlignment

Constructor.

Resets the maximum number of iterations to 0 thus forcing an internal computation if not set by the user. Sets the number of RANSAC iterations to 1000 and the standard transformation estimation to TransformationEstimation3Point.

Definition at line 134 of file ia_fpcs.hpp.

~FPCSInitialAlignment()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::~FPCSInitialAlignment ( )
inline

Destructor.

Definition at line 112 of file ia_fpcs.h.

Member Function Documentation

bruteForceCorrespondences()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::bruteForceCorrespondences ( int idx1,
int idx2,
pcl::Correspondences & pairs
)
protectedvirtual

Search for corresponding point pairs given the distance between two base points.

Parameters
[in] idx1 first index of current base segment (in source cloud)
[in] idx2 second index of current base segment (in source cloud)
[out] pairs resulting point pairs with point-to-point distance close to ref_dist
Returns
  • < 0 no corresponding point pair was found
  • = 0 at least one point pair candidate was found

Definition at line 579 of file ia_fpcs.hpp.

checkBaseMatch()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::checkBaseMatch ( const pcl::Indices & match_indices,
const float(&) ds[4]
)
protected

Check if outer rectangle distance of matched points fit with the base rectangle.

Parameters
[in] match_indices indices of match M
[in] ds edge lengths of base B
Returns
  • < 0 at least one edge of the match M has no corresponding one in the base B
  • = 0 edges of match M fits to the ones of base B

Definition at line 715 of file ia_fpcs.hpp.

computeTransformation()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::computeTransformation ( PointCloudSource & output,
const Eigen::Matrix4f & guess
)
overrideprotected

Rigid transformation computation method.

Parameters
output the transformed input point cloud dataset using the rigid transformation found
guess The computed transforamtion

Definition at line 167 of file ia_fpcs.hpp.

determineBaseMatches()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::determineBaseMatches ( const pcl::Indices & base_indices,
std::vector< pcl::Indices > & matches,
const pcl::Correspondences & pairs_a,
const pcl::Correspondences & pairs_b,
const float(&) ratio[2]
)
protectedvirtual

Determine base matches by combining the point pair candidate and search for coinciding intersection points using the diagonal segment ratios of base B.

The coincidation threshold is calculated during initialization (coincidation_limit_).

Parameters
[in] base_indices indices of base B
[out] matches vector of candidate matches w.r.t the base B
[in] pairs_a point pairs corresponding to points of 1st diagonal of base B
[in] pairs_b point pairs corresponding to points of 2nd diagonal of base B
[in] ratio diagonal intersection ratios of base points
Returns
  • < 0 no base match could be found
  • = 0 at least one base match was found

Definition at line 633 of file ia_fpcs.hpp.

finalCompute()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::finalCompute ( const std::vector< MatchingCandidates > & candidates )
protectedvirtual

Final computation of best match out of vector of best matches.

To avoid cross thread dependencies during parallel running, a best match for each try was calculated.

Note
For forwards compatibility the candidates are stored in vectors of 'vectors of size 1'.
Parameters
[in] candidates vector of candidate matches

Reimplemented in pcl::registration::KFPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >.

Definition at line 904 of file ia_fpcs.hpp.

getApproxOverlap()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getApproxOverlap ( ) const
inline
Returns
the approximated overlap between source and target.

Definition at line 208 of file ia_fpcs.h.

getDelta()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getDelta ( ) const
inline
Returns
the constant factor delta which weights the internally calculated parameters.

Definition at line 192 of file ia_fpcs.h.

getFitnessScore()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getFitnessScore ( ) const
inline
Returns
the fitness score of the best scored four-point match.

Definition at line 280 of file ia_fpcs.h.

getMaxComputationTime()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getMaxComputationTime ( ) const
inline
Returns
the maximum computation time in seconds.

Definition at line 273 of file ia_fpcs.h.

getMaxNormalDifference()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getMaxNormalDifference ( ) const
inline
Returns
the maximum normal difference between valid point correspondences in degree.

Definition at line 257 of file ia_fpcs.h.

getNumberOfSamples()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getNumberOfSamples ( ) const
inline
Returns
the number of source samples to use during alignment.

Definition at line 240 of file ia_fpcs.h.

getNumberOfThreads()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getNumberOfThreads ( ) const
inline
Returns
the number of threads used if OpenMP is activated.

Definition at line 173 of file ia_fpcs.h.

getScoreThreshold()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getScoreThreshold ( ) const
inline
Returns
the scoring threshold used for early finishing the method.

Definition at line 224 of file ia_fpcs.h.

getSourceNormals()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
NormalsConstPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getSourceNormals ( ) const
inline
Returns
the normals of the source point cloud.

Definition at line 141 of file ia_fpcs.h.

getTargetIndices()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
IndicesPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getTargetIndices ( ) const
inline
Returns
a pointer to the vector of target indices.

Definition at line 125 of file ia_fpcs.h.

getTargetNormals()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
NormalsConstPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::getTargetNormals ( ) const
inline
Returns
the normals of the target point cloud.

Definition at line 157 of file ia_fpcs.h.

handleMatches()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::handleMatches ( const pcl::Indices & base_indices,
std::vector< pcl::Indices > & matches,
MatchingCandidates & candidates
)
protectedvirtual

Method to handle current candidate matches.

Here we validate and evaluate the matches w.r.t the base and store the best fitting match (together with its score and estimated transformation).

Note
For forwards compatibility the results are stored in 'vectors of size 1'.
Parameters
[in] base_indices indices of base B
[in,out] matches vector of candidate matches w.r.t the base B. The candidate matches are reordered during this step.
[out] candidates vector which contains the candidates matches M

Reimplemented in pcl::registration::KFPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >.

Definition at line 739 of file ia_fpcs.hpp.

initCompute()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
bool pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::initCompute
protectedvirtual

linkMatchWithBase()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::linkMatchWithBase ( const pcl::Indices & base_indices,
pcl::Indices & match_indices,
pcl::Correspondences & correspondences
)
protectedvirtual

Sets the correspondences between the base B and the match M by using the distance of each point to the centroid of the rectangle.

Parameters
[in] base_indices indices of base B
[in] match_indices indices of match M
[out] correspondences resulting correspondences

Definition at line 777 of file ia_fpcs.hpp.

segmentToSegmentDist()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::segmentToSegmentDist ( const pcl::Indices & base_indices,
float(&) ratio[2]
)
protected

Calculate intersection ratios and segment to segment distances of base diagonals.

Parameters
[in] base_indices indices of base B
[out] ratio diagonal intersection ratios of base points
Returns
quality value of diagonal intersection

Definition at line 494 of file ia_fpcs.hpp.

selectBase()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::selectBase ( pcl::Indices & base_indices,
float(&) ratio[2]
)
protected

Select an approximately coplanar set of four points from the source cloud.

Parameters
[out] base_indices selected source cloud indices, further used as base (B)
[out] ratio the two diagonal intersection ratios (r1,r2) of the base points
Returns
  • < 0 no coplanar four point sets with large enough sampling distance was found
  • = 0 a set of four congruent points was selected

Definition at line 347 of file ia_fpcs.hpp.

selectBaseTriangle()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::selectBaseTriangle ( pcl::Indices & base_indices )
protected

Select randomly a triplet of points with large point-to-point distances.

The minimum point sampling distance is calculated based on the estimated point cloud overlap during initialization.

Parameters
[out] base_indices indices of base B
Returns
  • < 0 no triangle with large enough base lines could be selected
  • = 0 base triangle succesully selected

Definition at line 413 of file ia_fpcs.hpp.

setApproxOverlap()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setApproxOverlap ( float approx_overlap )
inline

Set the approximate overlap between source and target.

Parameters
[in] approx_overlap the estimated overlap

Definition at line 201 of file ia_fpcs.h.

setDelta()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setDelta ( float delta,
bool normalize = false
)
inline

Set the constant factor delta which weights the internally calculated parameters.

Parameters
[in] delta the weight factor delta
[in] normalize flag if delta should be normalized according to point cloud density

Definition at line 183 of file ia_fpcs.h.

setMaxComputationTime()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setMaxComputationTime ( int max_runtime )
inline

Set the maximum computation time in seconds.

Parameters
[in] max_runtime the maximum runtime of the method in seconds

Definition at line 266 of file ia_fpcs.h.

setMaxNormalDifference()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setMaxNormalDifference ( float max_norm_diff )
inline

Set the maximum normal difference between valid point correspondences in degree.

Parameters
[in] max_norm_diff the maximum difference in degree

Definition at line 249 of file ia_fpcs.h.

setNumberOfSamples()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setNumberOfSamples ( int nr_samples )
inline

Set the number of source samples to use during alignment.

Parameters
[in] nr_samples the number of source samples

Definition at line 233 of file ia_fpcs.h.

setNumberOfThreads()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setNumberOfThreads ( int nr_threads )
inline

Set the number of used threads if OpenMP is activated.

Parameters
[in] nr_threads the number of used threads

Definition at line 166 of file ia_fpcs.h.

setScoreThreshold()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setScoreThreshold ( float score_threshold )
inline

Set the scoring threshold used for early finishing the method.

Parameters
[in] score_threshold early terminating score criteria

Definition at line 217 of file ia_fpcs.h.

setSourceNormals()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setSourceNormals ( const NormalsConstPtr & source_normals )
inline

Provide a pointer to the normals of the source point cloud.

Parameters
[in] source_normals pointer to the normals of the source pointer cloud.

Definition at line 134 of file ia_fpcs.h.

setTargetIndices()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setTargetIndices ( const IndicesPtr & target_indices )
inline

Provide a pointer to the vector of target indices.

Parameters
[in] target_indices a pointer to the target indices

Definition at line 118 of file ia_fpcs.h.

setTargetNormals()

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setTargetNormals ( const NormalsConstPtr & target_normals )
inline

Provide a pointer to the normals of the target point cloud.

Parameters
[in] target_normals point to the normals of the target point cloud.

Definition at line 150 of file ia_fpcs.h.

setupBase()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
void pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::setupBase ( pcl::Indices & base_indices,
float(&) ratio[2]
)
protected

Setup the base (four coplanar points) by ordering the points and computing intersection ratios and segment to segment distances of base diagonal.

Parameters
[in,out] base_indices indices of base B (will be reordered)
[out] ratio diagonal intersection ratios of base points

Definition at line 451 of file ia_fpcs.hpp.

validateMatch()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::validateMatch ( const pcl::Indices & base_indices,
const pcl::Indices & match_indices,
const pcl::Correspondences & correspondences,
Eigen::Matrix4f & transformation
)
protectedvirtual

Validate the matching by computing the transformation between the source and target based on the four matched points and by comparing the mean square error (MSE) to a threshold.

The MSE limit was calculated during initialization (max_mse_).

Parameters
[in] base_indices indices of base B
[in] match_indices indices of match M
[in] correspondences corresondences between source and target
[out] transformation resulting transformation matrix
Returns
  • < 0 MSE bigger than max_mse_
  • = 0 MSE smaller than max_mse_

Definition at line 830 of file ia_fpcs.hpp.

validateTransformation()

template<typename PointSource , typename PointTarget , typename NormalT , typename Scalar >
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::validateTransformation ( Eigen::Matrix4f & transformation,
float & fitness_score
)
protectedvirtual

Validate the transformation by calculating the number of inliers after transforming the source cloud.

The resulting fitness score is later used as the decision criteria of the best fitting match.

Parameters
[out] transformation updated orientation matrix using all inliers
[out] fitness_score current best fitness_score
Note
fitness score is only updated if the score of the current transformation exceeds the input one.
Returns
  • < 0 if previous result is better than the current one (score remains)
  • = 0 current result is better than the previous one (score updated)

Reimplemented in pcl::registration::KFPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >.

Definition at line 862 of file ia_fpcs.hpp.

Member Data Documentation

approx_overlap_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::approx_overlap_
protected

coincidation_limit_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::coincidation_limit_
protected

Maximal distance between coinciding intersection points to find valid matches.

Note
Internally calculated using an estimation of the point density.

Definition at line 542 of file ia_fpcs.h.

delta_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::delta_
protected

Delta value of 4pcs algorithm (standard = 1.0).

It can be used as:

  • absolute value (normalization = false), value should represent the point accuracy to ensure finding neighbors between source <-> target
  • relative value (normalization = true), to adjust the internally calculated point accuracy (= point density)

Definition at line 485 of file ia_fpcs.h.

Referenced by pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, pcl::Normal, float >::getDelta(), and pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, pcl::Normal, float >::setDelta().

diameter_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::diameter_
protected

Estimated diamter of the target point cloud.

Definition at line 508 of file ia_fpcs.h.

fitness_score_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::fitness_score_
protected

Resulting fitness score of the best match.

Definition at line 505 of file ia_fpcs.h.

Referenced by pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, pcl::Normal, float >::getFitnessScore().

max_base_diameter_sqr_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_base_diameter_sqr_
protected

Estimated squared metric overlap between source and target.

Note
Internally calculated using the estimated overlap and the extent of the source cloud. It is used to derive the minimum sampling distance of the base points as well as to calculated the number of tries to reliably find a correct match.

Definition at line 515 of file ia_fpcs.h.

max_edge_diff_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_edge_diff_
protected

Maximal difference between the length of the base edges and valid match edges.

Note
Internally calculated using an estimation of the point density.

Definition at line 537 of file ia_fpcs.h.

max_inlier_dist_sqr_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_inlier_dist_sqr_
protected

Maximal squared point distance between source and target points to count as inlier.

Note
Internally calculated using an estimation of the point density.

Definition at line 552 of file ia_fpcs.h.

max_mse_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_mse_
protected

Maximal mean squared errors of a transformation calculated from a candidate match.

Note
Internally calculated using an estimation of the point density.

Definition at line 547 of file ia_fpcs.h.

max_norm_diff_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_norm_diff_
protected

max_pair_diff_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_pair_diff_
protected

Maximal difference between corresponding point pairs in source and target.

Note
Internally calculated using an estimation of the point density.

Definition at line 532 of file ia_fpcs.h.

max_runtime_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::max_runtime_
protected

normalize_delta_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
bool pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::normalize_delta_
protected

nr_samples_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::nr_samples_
protected

nr_threads_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
int pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::nr_threads_
protected

score_threshold_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::score_threshold_
protected

Score threshold to stop calculation with success.

If not set by the user it depends on the size of the approximated overlap

Definition at line 490 of file ia_fpcs.h.

Referenced by pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, pcl::Normal, float >::getScoreThreshold(), and pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, pcl::Normal, float >::setScoreThreshold().

small_error_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
const float pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::small_error_
protected

Definition of a small error.

Definition at line 555 of file ia_fpcs.h.

source_indices_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
pcl::IndicesPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::source_indices_
protected

A pointer to the vector of source point indices to use after sampling.

Definition at line 524 of file ia_fpcs.h.

source_normals_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
NormalsConstPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::source_normals_
protected

target_indices_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
pcl::IndicesPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::target_indices_
protected

target_normals_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
NormalsConstPtr pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::target_normals_
protected

use_normals_

template<typename PointSource , typename PointTarget , typename NormalT = pcl::Normal, typename Scalar = float>
bool pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >::use_normals_
protected

Use normals flag.

Definition at line 518 of file ia_fpcs.h.


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

© 2009–2012, Willow Garage, Inc.
© 2012–, Open Perception, Inc.
Licensed under the BSD License.
https://pointclouds.org/documentation/classpcl_1_1registration_1_1_f_p_c_s_initial_alignment.html