Point Cloud Library (PCL)
1.7.0
|
SampleConsensusInitialAlignment is an implementation of the initial alignment algorithm described in section IV of "Fast Point Feature Histograms (FPFH) for 3D Registration," Rusu et al. More...
#include <pcl/registration/ia_ransac.h>
Classes | |
class | ErrorFunctor |
class | HuberPenalty |
class | TruncatedError |
Public Member Functions | |
SampleConsensusInitialAlignment () | |
Constructor. More... | |
void | setSourceFeatures (const FeatureCloudConstPtr &features) |
Provide a boost shared pointer to the source point cloud's feature descriptors. More... | |
FeatureCloudConstPtr const | getSourceFeatures () |
Get a pointer to the source point cloud's features. More... | |
void | setTargetFeatures (const FeatureCloudConstPtr &features) |
Provide a boost shared pointer to the target point cloud's feature descriptors. More... | |
FeatureCloudConstPtr const | getTargetFeatures () |
Get a pointer to the target point cloud's features. More... | |
void | setMinSampleDistance (float min_sample_distance) |
Set the minimum distances between samples. More... | |
float | getMinSampleDistance () |
Get the minimum distances between samples, as set by the user. More... | |
void | setNumberOfSamples (int nr_samples) |
Set the number of samples to use during each iteration. More... | |
int | getNumberOfSamples () |
Get the number of samples to use during each iteration, as set by the user. More... | |
void | setCorrespondenceRandomness (int k) |
Set the number of neighbors to use when selecting a random feature correspondence. More... | |
int | getCorrespondenceRandomness () |
Get the number of neighbors used when selecting a random feature correspondence, as set by the user. More... | |
void | setErrorFunction (const boost::shared_ptr< ErrorFunctor > &error_functor) |
Specify the error function to minimize. More... | |
boost::shared_ptr< ErrorFunctor > | getErrorFunction () |
Get a shared pointer to the ErrorFunctor that is to be minimized. More... | |
![]() | |
Registration () | |
Empty constructor. More... | |
virtual | ~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... | |
PCL_DEPRECATED (void setInputCloud(const PointCloudSourceConstPtr &cloud),"[pcl::registration::Registration::setInputCloud] setInputCloud is deprecated. Please use setInputSource instead.") | |
Provide a pointer to the input source (e.g., the point cloud that we want to align to the target) More... | |
PCL_DEPRECATED (PointCloudSourceConstPtr const getInputCloud(),"[pcl::registration::Registration::getInputCloud] getInputCloud is deprecated. Please use getInputSource instead.") | |
Get a pointer to the input point cloud dataset target. 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... | |
PointCloudSourceConstPtr const | 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... | |
PointCloudTargetConstPtr const | 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 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 difference between two consecutive transformations) as set by the user. 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 (boost::function< FunctionSignature > &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., sum 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., sum of squared distances from the source to the target) from two sets of correspondence distances (distances between source and target points) More... | |
bool | hasConverged () |
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 initalization. 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... | |
![]() | |
PCLBase () | |
Empty constructor. More... | |
PCLBase (const PCLBase &base) | |
Copy constructor. More... | |
virtual | ~PCLBase () |
Destructor. More... | |
virtual void | setInputCloud (const PointCloudConstPtr &cloud) |
Provide a pointer to the input dataset. More... | |
PointCloudConstPtr const | getInputCloud () |
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 (size_t row_start, size_t col_start, size_t nb_rows, size_t nb_cols) |
Set the indices for the points laying within an interest region of the point cloud. More... | |
IndicesPtr const | getIndices () |
Get a pointer to the vector of indices used. More... | |
const PointSource & | operator[] (size_t pos) |
Override PointCloud operator[] to shorten code. More... | |
Protected Member Functions | |
int | getRandomIndex (int n) |
Choose a random index between 0 and n-1. More... | |
void | selectSamples (const PointCloudSource &cloud, int nr_samples, float min_sample_distance, std::vector< int > &sample_indices) |
Select nr_samples sample points from cloud while making sure that their pairwise distances are greater than a user-defined minimum distance, min_sample_distance. More... | |
void | findSimilarFeatures (const FeatureCloud &input_features, const std::vector< int > &sample_indices, std::vector< int > &corresponding_indices) |
For each of the sample points, find a list of points in the target cloud whose features are similar to the sample points' features. More... | |
float | computeErrorMetric (const PointCloudSource &cloud, float threshold) |
An error metric for that computes the quality of the alignment between the given cloud and the target. More... | |
virtual void | computeTransformation (PointCloudSource &output, const Eigen::Matrix4f &guess) |
Rigid transformation computation method. More... | |
![]() | |
bool | searchForNeighbors (const PointCloudSource &cloud, int index, std::vector< int > &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... | |
![]() | |
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 | |
FeatureCloudConstPtr | input_features_ |
The source point cloud's feature descriptors. More... | |
FeatureCloudConstPtr | target_features_ |
The target point cloud's feature descriptors. More... | |
int | nr_samples_ |
The number of samples to use during each iteration. More... | |
float | min_sample_distance_ |
The minimum distances between samples. More... | |
int | k_correspondences_ |
The number of neighbors to use when selecting a random feature correspondence. More... | |
FeatureKdTreePtr | feature_tree_ |
The KdTree used to compare feature descriptors. More... | |
boost::shared_ptr< ErrorFunctor > | error_functor_ |
![]() | |
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 | 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... | |
boost::function< void(const pcl::PointCloud< PointSource > &cloud_src, const std::vector < int > &indices_src, const pcl::PointCloud< PointTarget > &cloud_tgt, const std::vector < int > &indices_tgt)> | update_visualizer_ |
Callback function to update intermediate source point cloud position during it's registration to the target point cloud. More... | |
![]() | |
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... | |
SampleConsensusInitialAlignment is an implementation of the initial alignment algorithm described in section IV of "Fast Point Feature Histograms (FPFH) for 3D Registration," Rusu et al.
Definition at line 54 of file ia_ransac.h.
typedef boost::shared_ptr<const SampleConsensusInitialAlignment<PointSource, PointTarget, FeatureT> > pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::ConstPtr |
Definition at line 84 of file ia_ransac.h.
typedef pcl::PointCloud<FeatureT> pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::FeatureCloud |
Definition at line 79 of file ia_ransac.h.
typedef FeatureCloud::ConstPtr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::FeatureCloudConstPtr |
Definition at line 81 of file ia_ransac.h.
typedef FeatureCloud::Ptr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::FeatureCloudPtr |
Definition at line 80 of file ia_ransac.h.
typedef KdTreeFLANN<FeatureT>::Ptr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::FeatureKdTreePtr |
Definition at line 130 of file ia_ransac.h.
typedef Registration<PointSource, PointTarget>::PointCloudSource pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::PointCloudSource |
Definition at line 70 of file ia_ransac.h.
typedef PointCloudSource::ConstPtr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::PointCloudSourceConstPtr |
Definition at line 72 of file ia_ransac.h.
typedef PointCloudSource::Ptr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::PointCloudSourcePtr |
Definition at line 71 of file ia_ransac.h.
typedef Registration<PointSource, PointTarget>::PointCloudTarget pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::PointCloudTarget |
Definition at line 74 of file ia_ransac.h.
typedef PointIndices::ConstPtr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::PointIndicesConstPtr |
Definition at line 77 of file ia_ransac.h.
typedef PointIndices::Ptr pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::PointIndicesPtr |
Definition at line 76 of file ia_ransac.h.
typedef boost::shared_ptr<SampleConsensusInitialAlignment<PointSource, PointTarget, FeatureT> > pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::Ptr |
Definition at line 83 of file ia_ransac.h.
|
inline |
Constructor.
Definition at line 132 of file ia_ransac.h.
References pcl::Registration< PointSource, PointTarget >::corr_dist_threshold_, pcl::Registration< PointSource, PointTarget >::max_iterations_, pcl::Registration< PointSource, PointTarget >::reg_name_, and pcl::Registration< PointSource, PointTarget >::transformation_estimation_.
|
protected |
An error metric for that computes the quality of the alignment between the given cloud and the target.
cloud | the input cloud |
threshold | distances greater than this value are capped |
Definition at line 153 of file ia_ransac.hpp.
|
protectedvirtual |
Rigid transformation computation method.
output | the transformed input point cloud dataset using the rigid transformation found |
Definition at line 175 of file ia_ransac.hpp.
References pcl::transformPointCloud().
|
protected |
For each of the sample points, find a list of points in the target cloud whose features are similar to the sample points' features.
From these, select one randomly which will be considered that sample point's correspondence.
input_features | a cloud of feature descriptors |
sample_indices | the indices of each sample point |
corresponding_indices | the resulting indices of each sample's corresponding point in the target cloud |
Definition at line 132 of file ia_ransac.hpp.
|
inline |
Get the number of neighbors used when selecting a random feature correspondence, as set by the user.
Definition at line 195 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::k_correspondences_.
|
inline |
Get a shared pointer to the ErrorFunctor that is to be minimized.
Definition at line 208 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::error_functor_.
|
inline |
Get the minimum distances between samples, as set by the user.
Definition at line 174 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::min_sample_distance_.
|
inline |
Get the number of samples to use during each iteration, as set by the user.
Definition at line 184 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::nr_samples_.
|
inlineprotected |
Choose a random index between 0 and n-1.
n | the number of possible indices to choose from |
Definition at line 215 of file ia_ransac.h.
|
inline |
Get a pointer to the source point cloud's features.
Definition at line 154 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::input_features_.
|
inline |
Get a pointer to the target point cloud's features.
Definition at line 164 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::target_features_.
|
protected |
Select nr_samples sample points from cloud while making sure that their pairwise distances are greater than a user-defined minimum distance, min_sample_distance.
cloud | the input point cloud |
nr_samples | the number of samples to select |
min_sample_distance | the minimum distance between any two samples |
sample_indices | the resulting sample indices |
Definition at line 73 of file ia_ransac.hpp.
References pcl::euclideanDistance().
|
inline |
Set the number of neighbors to use when selecting a random feature correspondence.
A higher value will add more randomness to the feature matching.
k | the number of neighbors to use when selecting a random feature correspondence. |
Definition at line 191 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::k_correspondences_.
|
inline |
Specify the error function to minimize.
[in] | error_functor | a shared pointer to a subclass of SampleConsensusInitialAlignment::ErrorFunctor |
Definition at line 202 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::error_functor_.
|
inline |
Set the minimum distances between samples.
min_sample_distance | the minimum distances between samples |
Definition at line 170 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::min_sample_distance_.
|
inline |
Set the number of samples to use during each iteration.
nr_samples | the number of samples to use during each iteration |
Definition at line 180 of file ia_ransac.h.
References pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::nr_samples_.
void pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::setSourceFeatures | ( | const FeatureCloudConstPtr & | features | ) |
Provide a boost shared pointer to the source point cloud's feature descriptors.
features | the source point cloud's features |
Definition at line 48 of file ia_ransac.hpp.
void pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::setTargetFeatures | ( | const FeatureCloudConstPtr & | features | ) |
Provide a boost shared pointer to the target point cloud's feature descriptors.
features | the target point cloud's features |
Definition at line 60 of file ia_ransac.hpp.
|
protected |
Definition at line 271 of file ia_ransac.h.
Referenced by pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::getErrorFunction(), and pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::setErrorFunction().
|
protected |
The KdTree used to compare feature descriptors.
Definition at line 268 of file ia_ransac.h.
|
protected |
The source point cloud's feature descriptors.
Definition at line 253 of file ia_ransac.h.
Referenced by pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::getSourceFeatures().
|
protected |
The number of neighbors to use when selecting a random feature correspondence.
Definition at line 265 of file ia_ransac.h.
Referenced by pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::getCorrespondenceRandomness(), and pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::setCorrespondenceRandomness().
|
protected |
The minimum distances between samples.
Definition at line 262 of file ia_ransac.h.
Referenced by pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::getMinSampleDistance(), and pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::setMinSampleDistance().
|
protected |
The number of samples to use during each iteration.
Definition at line 259 of file ia_ransac.h.
Referenced by pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::getNumberOfSamples(), and pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::setNumberOfSamples().
|
protected |
The target point cloud's feature descriptors.
Definition at line 256 of file ia_ransac.h.
Referenced by pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >::getTargetFeatures().