RSDEstimation estimates the Radius-based Surface Descriptor (minimal and maximal radius of the local surface's curves) for a given point cloud dataset containing points and normals. More...

#include <rsd.h>

Inheritance diagram for pcl::RSDEstimation< PointInT, PointNT, PointOutT >:

[legend]

List of all members.

Public Types
typedef boost::shared_ptr < const RSDEstimation < PointInT, PointNT, PointOutT > >	ConstPtr
typedef Feature< PointInT, PointOutT >::PointCloudIn	PointCloudIn
typedef Feature< PointInT, PointOutT >::PointCloudOut	PointCloudOut
typedef boost::shared_ptr < RSDEstimation< PointInT, PointNT, PointOutT > >	Ptr
Public Member Functions
boost::shared_ptr< std::vector < Eigen::MatrixXf, Eigen::aligned_allocator < Eigen::MatrixXf > > >	getHistograms () const
	Returns a pointer to the list of full distance-angle histograms for all points.
int	getNrSubdivisions () const
	Get the number of subdivisions for the considered distance interval.
double	getPlaneRadius () const
	Get the maximum radius, above which everything can be considered planar.
bool	getSaveHistograms () const
	Returns whether the full distance-angle histograms are being saved.
	RSDEstimation ()
	Empty constructor.
void	setKSearch (int)
	Disables the setting of the number of k nearest neighbors to use for the feature estimation.
void	setNrSubdivisions (int nr_subdiv)
	Set the number of subdivisions for the considered distance interval.
void	setPlaneRadius (double plane_radius)
	Set the maximum radius, above which everything can be considered planar.
void	setSaveHistograms (bool save)
	Set whether the full distance-angle histograms should be saved.
Protected Member Functions
void	computeFeature (PointCloudOut &output)
	Estimate the estimates the Radius-based Surface Descriptor (RSD) at a set of points given by <setInputCloud (), setIndices ()> using the surface in setSearchSurface () and the spatial locator in setSearchMethod ()
Protected Attributes
boost::shared_ptr< std::vector < Eigen::MatrixXf, Eigen::aligned_allocator < Eigen::MatrixXf > > >	histograms_
	The list of full distance-angle histograms for all points.
Private Attributes
int	nr_subdiv_
	The number of subdivisions for the considered distance interval.
double	plane_radius_
	The maximum radius, above which everything can be considered planar.
bool	save_histograms_
	Signals whether the full distance-angle histograms are being saved.

Detailed Description

template<typename PointInT, typename PointNT, typename PointOutT>
class pcl::RSDEstimation< PointInT, PointNT, PointOutT >

RSDEstimation estimates the Radius-based Surface Descriptor (minimal and maximal radius of the local surface's curves) for a given point cloud dataset containing points and normals.

Note:: If you use this code in any academic work, please cite:

Z.C. Marton , D. Pangercic , N. Blodow , J. Kleinehellefort, M. Beetz General 3D Modelling of Novel Objects from a Single View In Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Taipei, Taiwan, October 18-22, 2010
Z.C. Marton, D. Pangercic, N. Blodow, Michael Beetz. Combined 2D-3D Categorization and Classification for Multimodal Perception Systems. In The International Journal of Robotics Research, Sage Publications pages 1378--1402, Volume 30, Number 11, September 2011.

Note:: The code is stateful as we do not expect this class to be multicore parallelized.

Author:: Zoltan-Csaba Marton

Definition at line 130 of file rsd.h.

Member Typedef Documentation

template<typename PointInT , typename PointNT , typename PointOutT >

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

Reimplemented from pcl::FeatureFromNormals< PointInT, PointNT, PointOutT >.

Definition at line 145 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

typedef Feature<PointInT, PointOutT>::PointCloudIn pcl::RSDEstimation< PointInT, PointNT, PointOutT >::PointCloudIn

Reimplemented from pcl::FeatureFromNormals< PointInT, PointNT, PointOutT >.

Definition at line 142 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

typedef Feature<PointInT, PointOutT>::PointCloudOut pcl::RSDEstimation< PointInT, PointNT, PointOutT >::PointCloudOut

Reimplemented from pcl::FeatureFromNormals< PointInT, PointNT, PointOutT >.

Definition at line 141 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

typedef boost::shared_ptr<RSDEstimation<PointInT, PointNT, PointOutT> > pcl::RSDEstimation< PointInT, PointNT, PointOutT >::Ptr

Reimplemented from pcl::FeatureFromNormals< PointInT, PointNT, PointOutT >.

Definition at line 144 of file rsd.h.

Constructor & Destructor Documentation

template<typename PointInT , typename PointNT , typename PointOutT >

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

Empty constructor.

Definition at line 149 of file rsd.h.

Member Function Documentation

template<typename PointInT , typename PointNT , typename PointOutT >

void pcl::RSDEstimation< PointInT, PointNT, PointOutT >::computeFeature ( PointCloudOut & output ) [protected, virtual]

Estimate the estimates the Radius-based Surface Descriptor (RSD) at a set of points given by <setInputCloud (), setIndices ()> using the surface in setSearchSurface () and the spatial locator in setSearchMethod ()

Parameters:

output the resultant point cloud model dataset that contains the RSD feature estimates (r_min and r_max values)

Implements pcl::Feature< PointInT, PointOutT >.

Definition at line 249 of file rsd.hpp.

template<typename PointInT , typename PointNT , typename PointOutT >

boost::shared_ptr<std::vector<Eigen::MatrixXf, Eigen::aligned_allocator<Eigen::MatrixXf> > > pcl::RSDEstimation< PointInT, PointNT, PointOutT >::getHistograms ( ) const [inline]

Returns a pointer to the list of full distance-angle histograms for all points.

Definition at line 196 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

int pcl::RSDEstimation< PointInT, PointNT, PointOutT >::getNrSubdivisions ( ) const [inline]

Get the number of subdivisions for the considered distance interval.

Definition at line 162 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

double pcl::RSDEstimation< PointInT, PointNT, PointOutT >::getPlaneRadius ( ) const [inline]

Get the maximum radius, above which everything can be considered planar.

Definition at line 174 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

bool pcl::RSDEstimation< PointInT, PointNT, PointOutT >::getSaveHistograms ( ) const [inline]

Returns whether the full distance-angle histograms are being saved.

Definition at line 192 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

void pcl::RSDEstimation< PointInT, PointNT, PointOutT >::setKSearch ( int ) [inline]

Disables the setting of the number of k nearest neighbors to use for the feature estimation.

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

Definition at line 178 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

void pcl::RSDEstimation< PointInT, PointNT, PointOutT >::setNrSubdivisions ( int nr_subdiv ) [inline]

Set the number of subdivisions for the considered distance interval.

Parameters:

[in] nr_subdiv the number of subdivisions

Definition at line 158 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

void pcl::RSDEstimation< PointInT, PointNT, PointOutT >::setPlaneRadius ( double plane_radius ) [inline]

Set the maximum radius, above which everything can be considered planar.

Note:: the order of magnitude should be around 10-20 times the search radius (0.2 works well for typical datasets).; on accurate 3D data (e.g. openni sernsors) a search radius as low as 0.01 still gives good results.

Parameters:

[in] plane_radius the new plane radius

Definition at line 170 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

void pcl::RSDEstimation< PointInT, PointNT, PointOutT >::setSaveHistograms ( bool save ) [inline]

Set whether the full distance-angle histograms should be saved.

Note:: Obtain the list of histograms by getHistograms ()

Parameters:

[in] save set to true if histograms should be saved

Definition at line 188 of file rsd.h.

Member Data Documentation

template<typename PointInT , typename PointNT , typename PointOutT >

boost::shared_ptr<std::vector<Eigen::MatrixXf, Eigen::aligned_allocator<Eigen::MatrixXf> > > pcl::RSDEstimation< PointInT, PointNT, PointOutT >::histograms_ [protected]

The list of full distance-angle histograms for all points.

Definition at line 209 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

int pcl::RSDEstimation< PointInT, PointNT, PointOutT >::nr_subdiv_ [private]

The number of subdivisions for the considered distance interval.

Definition at line 213 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

double pcl::RSDEstimation< PointInT, PointNT, PointOutT >::plane_radius_ [private]

The maximum radius, above which everything can be considered planar.

Definition at line 216 of file rsd.h.

template<typename PointInT , typename PointNT , typename PointOutT >

bool pcl::RSDEstimation< PointInT, PointNT, PointOutT >::save_histograms_ [private]

Signals whether the full distance-angle histograms are being saved.

Definition at line 219 of file rsd.h.

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

Public Types

Public Member Functions

Protected Member Functions

Protected Attributes

Private Attributes

Detailed Description

template<typename PointInT, typename PointNT, typename PointOutT> class pcl::RSDEstimation< PointInT, PointNT, PointOutT >

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation

template<typename PointInT, typename PointNT, typename PointOutT>
class pcl::RSDEstimation< PointInT, PointNT, PointOutT >