MovingLeastSquares represent an implementation of the MLS (Moving Least Squares) algorithm for data smoothing and improved normal estimation. It also contains methods for upsampling the resulting cloud based on the parametric fit. Reference paper: "Computing and Rendering Point Set Surfaces" by Marc Alexa, Johannes Behr, Daniel Cohen-Or, Shachar Fleishman, David Levin and Claudio T. Silva www.sci.utah.edu/~shachar/Publications/crpss.pdf. More...

#include <mls.h>

Inheritance diagram for pcl::MovingLeastSquares< PointInT, PointOutT >:

[legend]

List of all members.

Classes
struct	MLSResult
	Data structure used to store the results of the MLS fitting. More...
class	MLSVoxelGrid
	A minimalistic implementation of a voxel grid, necessary for the point cloud upsampling. More...
Public Types
typedef boost::shared_ptr < const MovingLeastSquares < PointInT, PointOutT > >	ConstPtr
typedef pcl::search::Search < PointInT >	KdTree
typedef pcl::search::Search < PointInT >::Ptr	KdTreePtr
typedef pcl::PointCloud < pcl::Normal >	NormalCloud
typedef pcl::PointCloud < pcl::Normal >::Ptr	NormalCloudPtr
typedef pcl::PointCloud< PointInT >	PointCloudIn
typedef PointCloudIn::ConstPtr	PointCloudInConstPtr
typedef PointCloudIn::Ptr	PointCloudInPtr
typedef pcl::PointCloud < PointOutT >	PointCloudOut
typedef PointCloudOut::ConstPtr	PointCloudOutConstPtr
typedef PointCloudOut::Ptr	PointCloudOutPtr
typedef boost::shared_ptr < MovingLeastSquares< PointInT, PointOutT > >	Ptr
typedef boost::function< int(int, double, std::vector< int > &, std::vector< float > &)>	SearchMethod
enum	UpsamplingMethod { NONE, DISTINCT_CLOUD, SAMPLE_LOCAL_PLANE, RANDOM_UNIFORM_DENSITY, VOXEL_GRID_DILATION }
Public Member Functions
PointIndicesPtr	getCorrespondingIndices ()
	Get the set of indices with each point in output having the corresponding point in input.
int	getDilationIterations ()
	Get the number of dilation steps of the voxel grid.
float	getDilationVoxelSize ()
	Get the voxel size for the voxel grid.
PointCloudInConstPtr	getDistinctCloud ()
	Get the distinct cloud used for the DISTINCT_CLOUD upsampling method.
int	getPointDensity ()
	Get the parameter that specifies the desired number of points within the search radius.
bool	getPolynomialFit ()
	Get the polynomial_fit value (true if the surface and normal are approximated using a polynomial).
int	getPolynomialOrder ()
	Get the order of the polynomial to be fit.
KdTreePtr	getSearchMethod ()
	Get a pointer to the search method used.
double	getSearchRadius ()
	Get the sphere radius used for determining the k-nearest neighbors.
double	getSqrGaussParam () const
	Get the parameter for distance based weighting of neighbors.
double	getUpsamplingRadius ()
	Get the radius of the circle in the local point plane that will be sampled.
double	getUpsamplingStepSize ()
	Get the step size for the local plane sampling.
	MovingLeastSquares ()
	Empty constructor.
void	process (PointCloudOut &output)
	Base method for surface reconstruction for all points given in <setInputCloud (), setIndices ()>
void	setComputeNormals (bool compute_normals)
	Set whether the algorithm should also store the normals computed.
void	setDilationIterations (int iterations)
	Set the number of dilation steps of the voxel grid.
void	setDilationVoxelSize (float voxel_size)
	Set the voxel size for the voxel grid.
void	setDistinctCloud (PointCloudInConstPtr distinct_cloud)
	Set the distinct cloud used for the DISTINCT_CLOUD upsampling method.
void	setPointDensity (int desired_num_points_in_radius)
	Set the parameter that specifies the desired number of points within the search radius.
void	setPolynomialFit (bool polynomial_fit)
	Sets whether the surface and normal are approximated using a polynomial, or only via tangent estimation.
void	setPolynomialOrder (int order)
	Set the order of the polynomial to be fit.
void	setSearchMethod (const KdTreePtr &tree)
	Provide a pointer to the search object.
void	setSearchRadius (double radius)
	Set the sphere radius that is to be used for determining the k-nearest neighbors used for fitting.
void	setSqrGaussParam (double sqr_gauss_param)
	Set the parameter used for distance based weighting of neighbors (the square of the search radius works best in general).
void	setUpsamplingMethod (UpsamplingMethod method)
	Set the upsampling method to be used.
void	setUpsamplingRadius (double radius)
	Set the radius of the circle in the local point plane that will be sampled.
void	setUpsamplingStepSize (double step_size)
	Set the step size for the local plane sampling.
virtual	~MovingLeastSquares ()
	Empty destructor.
Protected Member Functions
void	computeMLSPointNormal (int index, const std::vector< int > &nn_indices, std::vector< float > &nn_sqr_dists, PointCloudOut &projected_points, NormalCloud &projected_points_normals, PointIndices &corresponding_input_indices, MLSResult &mls_result) const
	Smooth a given point and its neighborghood using Moving Least Squares.
void	copyMissingFields (const PointInT &point_in, PointOutT &point_out) const
virtual void	performProcessing (PointCloudOut &output)
	Abstract surface reconstruction method.
void	performUpsampling (PointCloudOut &output)
	Perform upsampling for the distinct-cloud and voxel-grid methods.
void	projectPointToMLSSurface (float &u_disp, float &v_disp, Eigen::Vector3d &u_axis, Eigen::Vector3d &v_axis, Eigen::Vector3d &n_axis, Eigen::Vector3d &mean, float &curvature, Eigen::VectorXd &c_vec, int num_neighbors, PointOutT &result_point, pcl::Normal &result_normal) const
	Fits a point (sample point) given in the local plane coordinates of an input point (query point) to the MLS surface of the input point.
int	searchForNeighbors (int index, std::vector< int > &indices, std::vector< float > &sqr_distances) const
	Search for the closest nearest neighbors of a given point using a radius search.
Protected Attributes
bool	compute_normals_
	Parameter that specifies whether the normals should be computed for the input cloud or not.
PointIndicesPtr	corresponding_input_indices_
	Collects for each point in output the corrseponding point in the input.
int	desired_num_points_in_radius_
	Parameter that specifies the desired number of points within the search radius.
int	dilation_iteration_num_
	Number of dilation steps for the VOXEL_GRID_DILATION upsampling method.
PointCloudInConstPtr	distinct_cloud_
	The distinct point cloud that will be projected to the MLS surface.
std::vector< MLSResult >	mls_results_
	Stores the MLS result for each point in the input cloud.
NormalCloudPtr	normals_
	The point cloud that will hold the estimated normals, if set.
int	nr_coeff_
	Number of coefficients, to be computed from the requested order.
int	order_
	The order of the polynomial to be fit.
bool	polynomial_fit_
SearchMethod	search_method_
	The search method template for indices.
double	search_radius_
	The nearest neighbors search radius for each point.
double	sqr_gauss_param_
	Parameter for distance based weighting of neighbors (search_radius_ * search_radius_ works fine)
KdTreePtr	tree_
	A pointer to the spatial search object.
UpsamplingMethod	upsample_method_
	Parameter that specifies the upsampling method to be used.
double	upsampling_radius_
	Radius of the circle in the local point plane that will be sampled.
double	upsampling_step_
	Step size for the local plane sampling.
float	voxel_size_
	Voxel size for the VOXEL_GRID_DILATION upsampling method.
Private Member Functions
std::string	getClassName () const
	Abstract class get name method.
Private Attributes
boost::mt19937	rng_alg_
	Boost-based random number generator algorithm.
boost::shared_ptr < boost::variate_generator < boost::mt19937 &, boost::uniform_real< float > > >	rng_uniform_distribution_
	Random number generator using an uniform distribution of floats.

Detailed Description

template<typename PointInT, typename PointOutT>
class pcl::MovingLeastSquares< PointInT, PointOutT >

MovingLeastSquares represent an implementation of the MLS (Moving Least Squares) algorithm for data smoothing and improved normal estimation. It also contains methods for upsampling the resulting cloud based on the parametric fit. Reference paper: "Computing and Rendering Point Set Surfaces" by Marc Alexa, Johannes Behr, Daniel Cohen-Or, Shachar Fleishman, David Levin and Claudio T. Silva www.sci.utah.edu/~shachar/Publications/crpss.pdf.

Author:: Zoltan Csaba Marton, Radu B. Rusu, Alexandru E. Ichim, Suat Gedikli

Definition at line 65 of file mls.h.

Member Typedef Documentation

template<typename PointInT, typename PointOutT>

typedef boost::shared_ptr<const MovingLeastSquares<PointInT, PointOutT> > pcl::MovingLeastSquares< PointInT, PointOutT >::ConstPtr

Reimplemented from pcl::CloudSurfaceProcessing< PointInT, PointOutT >.

Definition at line 69 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef pcl::search::Search<PointInT> pcl::MovingLeastSquares< PointInT, PointOutT >::KdTree

Definition at line 77 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef pcl::search::Search<PointInT>::Ptr pcl::MovingLeastSquares< PointInT, PointOutT >::KdTreePtr

Definition at line 78 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef pcl::PointCloud<pcl::Normal> pcl::MovingLeastSquares< PointInT, PointOutT >::NormalCloud

Definition at line 79 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef pcl::PointCloud<pcl::Normal>::Ptr pcl::MovingLeastSquares< PointInT, PointOutT >::NormalCloudPtr

Definition at line 80 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef pcl::PointCloud<PointInT> pcl::MovingLeastSquares< PointInT, PointOutT >::PointCloudIn

Definition at line 86 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef PointCloudIn::ConstPtr pcl::MovingLeastSquares< PointInT, PointOutT >::PointCloudInConstPtr

Definition at line 88 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef PointCloudIn::Ptr pcl::MovingLeastSquares< PointInT, PointOutT >::PointCloudInPtr

Definition at line 87 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef pcl::PointCloud<PointOutT> pcl::MovingLeastSquares< PointInT, PointOutT >::PointCloudOut

Definition at line 82 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef PointCloudOut::ConstPtr pcl::MovingLeastSquares< PointInT, PointOutT >::PointCloudOutConstPtr

Definition at line 84 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef PointCloudOut::Ptr pcl::MovingLeastSquares< PointInT, PointOutT >::PointCloudOutPtr

Definition at line 83 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef boost::shared_ptr<MovingLeastSquares<PointInT, PointOutT> > pcl::MovingLeastSquares< PointInT, PointOutT >::Ptr

Reimplemented from pcl::CloudSurfaceProcessing< PointInT, PointOutT >.

Definition at line 68 of file mls.h.

template<typename PointInT, typename PointOutT>

typedef boost::function<int (int, double, std::vector<int> &, std::vector<float> &)> pcl::MovingLeastSquares< PointInT, PointOutT >::SearchMethod

Definition at line 90 of file mls.h.

Member Enumeration Documentation

template<typename PointInT, typename PointOutT>

enum pcl::MovingLeastSquares::UpsamplingMethod

Enumerator:

NONE
DISTINCT_CLOUD
SAMPLE_LOCAL_PLANE
RANDOM_UNIFORM_DENSITY
VOXEL_GRID_DILATION

Definition at line 92 of file mls.h.

Constructor & Destructor Documentation

template<typename PointInT, typename PointOutT>

pcl::MovingLeastSquares< PointInT, PointOutT >::MovingLeastSquares ( ) [inline]

Empty constructor.

Definition at line 95 of file mls.h.

template<typename PointInT, typename PointOutT>

virtual pcl::MovingLeastSquares< PointInT, PointOutT >::~MovingLeastSquares ( ) [inline, virtual]

Empty destructor.

Definition at line 119 of file mls.h.

Member Function Documentation

template<typename PointInT , typename PointOutT >

void pcl::MovingLeastSquares< PointInT, PointOutT >::computeMLSPointNormal	(	int	index,
		const std::vector< int > &	nn_indices,
		std::vector< float > &	nn_sqr_dists,
		PointCloudOut &	projected_points,
		NormalCloud &	projected_points_normals,
		PointIndices &	corresponding_input_indices,
		MLSResult &	mls_result
	)		const `[protected]`

Smooth a given point and its neighborghood using Moving Least Squares.

Parameters:

[in]	index	the inex of the query point in the input cloud
[in]	nn_indices	the set of nearest neighbors indices for pt
[in]	nn_sqr_dists	the set of nearest neighbors squared distances for pt
[out]	projected_points	the set of points projected points around the query point (in the case of upsampling method NONE, only the query point projected to its own fitted surface will be returned, in the case of the other upsampling methods, multiple points will be returned)
[out]	projected_points_normals	the normals corresponding to the projected points
[out]	corresponding_input_indices	the set of indices with each point in output having the corresponding point in input
[out]	mls_result	stores the MLS result for each point in the input cloud (used only in the case of VOXEL_GRID_DILATION or DISTINCT_CLOUD upsampling)

Definition at line 159 of file mls.hpp.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::copyMissingFields	(	const PointInT &	point_in,
		PointOutT &	point_out
	)		const `[protected]`

Definition at line 752 of file mls.hpp.

template<typename PointInT, typename PointOutT>

std::string pcl::MovingLeastSquares< PointInT, PointOutT >::getClassName ( ) const [inline, private]

Abstract class get name method.

Definition at line 523 of file mls.h.

template<typename PointInT, typename PointOutT>

PointIndicesPtr pcl::MovingLeastSquares< PointInT, PointOutT >::getCorrespondingIndices ( ) [inline]

Get the set of indices with each point in output having the corresponding point in input.

Definition at line 295 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::getDilationIterations ( ) [inline]

Get the number of dilation steps of the voxel grid.

Note:: Used only in the VOXEL_GRID_DILATION upsampling method

Definition at line 283 of file mls.h.

template<typename PointInT, typename PointOutT>

float pcl::MovingLeastSquares< PointInT, PointOutT >::getDilationVoxelSize ( ) [inline]

Get the voxel size for the voxel grid.

Note:: Used only in the VOXEL_GRID_DILATION upsampling method

Definition at line 270 of file mls.h.

template<typename PointInT, typename PointOutT>

PointCloudInConstPtr pcl::MovingLeastSquares< PointInT, PointOutT >::getDistinctCloud ( ) [inline]

Get the distinct cloud used for the DISTINCT_CLOUD upsampling method.

Definition at line 213 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::getPointDensity ( ) [inline]

Get the parameter that specifies the desired number of points within the search radius.

Note:: Used only in the case of RANDOM_UNIFORM_DENSITY upsampling

Definition at line 256 of file mls.h.

template<typename PointInT, typename PointOutT>

bool pcl::MovingLeastSquares< PointInT, PointOutT >::getPolynomialFit ( ) [inline]

Get the polynomial_fit value (true if the surface and normal are approximated using a polynomial).

Definition at line 162 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::getPolynomialOrder ( ) [inline]

Get the order of the polynomial to be fit.

Definition at line 152 of file mls.h.

template<typename PointInT, typename PointOutT>

KdTreePtr pcl::MovingLeastSquares< PointInT, PointOutT >::getSearchMethod ( ) [inline]

Get a pointer to the search method used.

Definition at line 142 of file mls.h.

template<typename PointInT, typename PointOutT>

double pcl::MovingLeastSquares< PointInT, PointOutT >::getSearchRadius ( ) [inline]

Get the sphere radius used for determining the k-nearest neighbors.

Definition at line 173 of file mls.h.

template<typename PointInT, typename PointOutT>

double pcl::MovingLeastSquares< PointInT, PointOutT >::getSqrGaussParam ( ) const [inline]

Get the parameter for distance based weighting of neighbors.

Definition at line 184 of file mls.h.

template<typename PointInT, typename PointOutT>

double pcl::MovingLeastSquares< PointInT, PointOutT >::getUpsamplingRadius ( ) [inline]

Get the radius of the circle in the local point plane that will be sampled.

Note:: Used only in the case of SAMPLE_LOCAL_PLANE upsampling

Definition at line 227 of file mls.h.

template<typename PointInT, typename PointOutT>

double pcl::MovingLeastSquares< PointInT, PointOutT >::getUpsamplingStepSize ( ) [inline]

Get the step size for the local plane sampling.

Note:: Used only in the case of SAMPLE_LOCAL_PLANE upsampling

Definition at line 241 of file mls.h.

template<typename PointInT , typename PointOutT >

void pcl::MovingLeastSquares< PointInT, PointOutT >::performProcessing ( PointCloudOut & output ) [protected, virtual]

Abstract surface reconstruction method.

Parameters:

[out] output the result of the reconstruction

Definition at line 460 of file mls.hpp.

template<typename PointInT , typename PointOutT >

void pcl::MovingLeastSquares< PointInT, PointOutT >::performUpsampling ( PointCloudOut & output ) [protected]

Perform upsampling for the distinct-cloud and voxel-grid methods.

Parameters:

[out] output the result of the reconstruction

Definition at line 573 of file mls.hpp.

template<typename PointInT , typename PointOutT >

void pcl::MovingLeastSquares< PointInT, PointOutT >::process ( PointCloudOut & output )

Base method for surface reconstruction for all points given in <setInputCloud (), setIndices ()>

Parameters:

[out] output the resultant reconstructed surface model

Definition at line 56 of file mls.hpp.

template<typename PointInT , typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::projectPointToMLSSurface	(	float &	u_disp,
		float &	v_disp,
		Eigen::Vector3d &	u_axis,
		Eigen::Vector3d &	v_axis,
		Eigen::Vector3d &	n_axis,
		Eigen::Vector3d &	mean,
		float &	curvature,
		Eigen::VectorXd &	c_vec,
		int	num_neighbors,
		PointOutT &	result_point,
		pcl::Normal &	result_normal
	)		const `[protected]`

Fits a point (sample point) given in the local plane coordinates of an input point (query point) to the MLS surface of the input point.

Parameters:

[in]	u_disp	the u coordinate of the sample point in the local plane of the query point
[in]	v_disp	the v coordinate of the sample point in the local plane of the query point
[in]	u	the axis corresponding to the u-coordinates of the local plane of the query point
[in]	v	the axis corresponding to the v-coordinates of the local plane of the query point
[in]	plane_normal	the normal to the local plane of the query point
[in]	curvature	the curvature of the surface at the query point
[in]	query_point	the absolute 3D position of the query point
[in]	c_vec	the coefficients of the polynomial fit on the MLS surface of the query point
[in]	num_neighbors	the number of neighbors of the query point in the input cloud
[out]	result_point	the absolute 3D position of the resulting projected point
[out]	result_normal	the normal of the resulting projected point

Definition at line 403 of file mls.hpp.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::searchForNeighbors	(	int	index,
		std::vector< int > &	indices,
		std::vector< float > &	sqr_distances
	)		const `[inline, protected]`

Search for the closest nearest neighbors of a given point using a radius search.

Parameters:

[in]	index	the index of the query point
[out]	indices	the resultant vector of indices representing the k-nearest neighbors
[out]	sqr_distances	the resultant squared distances from the query point to the k-nearest neighbors

Definition at line 446 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setComputeNormals ( bool compute_normals ) [inline]

Set whether the algorithm should also store the normals computed.

Note:: This is optional, but need a proper output cloud type

Definition at line 126 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setDilationIterations ( int iterations ) [inline]

Set the number of dilation steps of the voxel grid.

Note:: Used only in the VOXEL_GRID_DILATION upsampling method

Parameters:

[in] iterations the number of dilation iterations

Definition at line 277 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setDilationVoxelSize ( float voxel_size ) [inline]

Set the voxel size for the voxel grid.

Note:: Used only in the VOXEL_GRID_DILATION upsampling method

Parameters:

[in] voxel_size the edge length of a cubic voxel in the voxel grid

Definition at line 263 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setDistinctCloud ( PointCloudInConstPtr distinct_cloud ) [inline]

Set the distinct cloud used for the DISTINCT_CLOUD upsampling method.

Definition at line 209 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setPointDensity ( int desired_num_points_in_radius ) [inline]

Set the parameter that specifies the desired number of points within the search radius.

Note:: Used only in the case of RANDOM_UNIFORM_DENSITY upsampling

Parameters:

[in] desired_num_points_in_radius the desired number of points in the output cloud in a sphere of radius search_radius_ around each point

Definition at line 249 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setPolynomialFit ( bool polynomial_fit ) [inline]

Sets whether the surface and normal are approximated using a polynomial, or only via tangent estimation.

Parameters:

[in] polynomial_fit set to true for polynomial fit

Definition at line 158 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setPolynomialOrder ( int order ) [inline]

Set the order of the polynomial to be fit.

Parameters:

[in] order the order of the polynomial

Definition at line 148 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setSearchMethod ( const KdTreePtr & tree ) [inline]

Provide a pointer to the search object.

Parameters:

[in] tree a pointer to the spatial search object.

Definition at line 132 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setSearchRadius ( double radius ) [inline]

Set the sphere radius that is to be used for determining the k-nearest neighbors used for fitting.

Parameters:

[in] radius the sphere radius that is to contain all k-nearest neighbors

Note:: Calling this method resets the squared Gaussian parameter to radius * radius !

Definition at line 169 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setSqrGaussParam ( double sqr_gauss_param ) [inline]

Set the parameter used for distance based weighting of neighbors (the square of the search radius works best in general).

Parameters:

[in] sqr_gauss_param the squared Gaussian parameter

Definition at line 180 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setUpsamplingMethod ( UpsamplingMethod method ) [inline]

Set the upsampling method to be used.

Note:: Options are: * NONE - no upsampling will be done, only the input points will be projected to their own MLS surfaces * DISTINCT_CLOUD - will project the points of the distinct cloud to the closest point on the MLS surface * SAMPLE_LOCAL_PLANE - the local plane of each input point will be sampled in a circular fashion using the upsampling_radius_ and the upsampling_step_ parameters * RANDOM_UNIFORM_DENSITY - the local plane of each input point will be sampled using an uniform random distribution such that the density of points is constant throughout the cloud - given by the desired_num_points_in_radius_ parameter * VOXEL_GRID_DILATION - the input cloud will be inserted into a voxel grid with voxels of size voxel_size_; this voxel grid will be dilated dilation_iteration_num_ times and the resulting points will be projected to the MLS surface of the closest point in the input cloud; the result is a point cloud with filled holes and a constant point density

Definition at line 205 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setUpsamplingRadius ( double radius ) [inline]

Set the radius of the circle in the local point plane that will be sampled.

Note:: Used only in the case of SAMPLE_LOCAL_PLANE upsampling

Parameters:

[in] radius the radius of the circle

Definition at line 221 of file mls.h.

template<typename PointInT, typename PointOutT>

void pcl::MovingLeastSquares< PointInT, PointOutT >::setUpsamplingStepSize ( double step_size ) [inline]

Set the step size for the local plane sampling.

Note:: Used only in the case of SAMPLE_LOCAL_PLANE upsampling

Parameters:

[in] step_size the step size

Definition at line 234 of file mls.h.

Member Data Documentation

template<typename PointInT, typename PointOutT>

bool pcl::MovingLeastSquares< PointInT, PointOutT >::compute_normals_ [protected]

Parameter that specifies whether the normals should be computed for the input cloud or not.

Definition at line 323 of file mls.h.

template<typename PointInT, typename PointOutT>

PointIndicesPtr pcl::MovingLeastSquares< PointInT, PointOutT >::corresponding_input_indices_ [protected]

Collects for each point in output the corrseponding point in the input.

Definition at line 438 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::desired_num_points_in_radius_ [protected]

Parameter that specifies the desired number of points within the search radius.

Note:: Used only in the case of RANDOM_UNIFORM_DENSITY upsampling

Definition at line 341 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::dilation_iteration_num_ [protected]

Number of dilation steps for the VOXEL_GRID_DILATION upsampling method.

Definition at line 432 of file mls.h.

template<typename PointInT, typename PointOutT>

PointCloudInConstPtr pcl::MovingLeastSquares< PointInT, PointOutT >::distinct_cloud_ [protected]

The distinct point cloud that will be projected to the MLS surface.

Definition at line 302 of file mls.h.

template<typename PointInT, typename PointOutT>

std::vector<MLSResult> pcl::MovingLeastSquares< PointInT, PointOutT >::mls_results_ [protected]

Stores the MLS result for each point in the input cloud.

Note:: Used only in the case of VOXEL_GRID_DILATION or DISTINCT_CLOUD upsampling

Definition at line 369 of file mls.h.

template<typename PointInT, typename PointOutT>

NormalCloudPtr pcl::MovingLeastSquares< PointInT, PointOutT >::normals_ [protected]

The point cloud that will hold the estimated normals, if set.

Definition at line 299 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::nr_coeff_ [protected]

Number of coefficients, to be computed from the requested order.

Definition at line 435 of file mls.h.

template<typename PointInT, typename PointOutT>

int pcl::MovingLeastSquares< PointInT, PointOutT >::order_ [protected]

The order of the polynomial to be fit.

Definition at line 311 of file mls.h.

template<typename PointInT, typename PointOutT>

bool pcl::MovingLeastSquares< PointInT, PointOutT >::polynomial_fit_ [protected]

True if the surface and normal be approximated using a polynomial, false if tangent estimation is sufficient.

Definition at line 314 of file mls.h.

template<typename PointInT, typename PointOutT>

boost::mt19937 pcl::MovingLeastSquares< PointInT, PointOutT >::rng_alg_ [private]

Boost-based random number generator algorithm.

Definition at line 513 of file mls.h.

template<typename PointInT, typename PointOutT>

boost::shared_ptr<boost::variate_generator<boost::mt19937&, boost::uniform_real<float> > > pcl::MovingLeastSquares< PointInT, PointOutT >::rng_uniform_distribution_ [private]

Random number generator using an uniform distribution of floats.