Point Cloud Library (PCL)  1.9.1-dev
List of all members | Public Types | Public Member Functions | Protected Member Functions
pcl::IntegralImageNormalEstimation< PointInT, PointOutT > Class Template Reference

Surface normal estimation on organized data using integral images. More...

#include <pcl/features/integral_image_normal.h>

+ Inheritance diagram for pcl::IntegralImageNormalEstimation< PointInT, PointOutT >:

Public Types

enum  BorderPolicy { BORDER_POLICY_IGNORE, BORDER_POLICY_MIRROR }
 Different types of border handling. More...
 
enum  NormalEstimationMethod { COVARIANCE_MATRIX, AVERAGE_3D_GRADIENT, AVERAGE_DEPTH_CHANGE, SIMPLE_3D_GRADIENT }
 Different normal estimation methods. More...
 
typedef boost::shared_ptr< IntegralImageNormalEstimation< PointInT, PointOutT > > Ptr
 
typedef boost::shared_ptr< const IntegralImageNormalEstimation< PointInT, PointOutT > > ConstPtr
 
typedef Feature< PointInT, PointOutT >::PointCloudIn PointCloudIn
 
typedef Feature< PointInT, PointOutT >::PointCloudOut PointCloudOut
 
- Public Types inherited from pcl::Feature< PointInT, PointOutT >
typedef PCLBase< PointInT > BaseClass
 
typedef boost::shared_ptr< Feature< PointInT, PointOutT > > Ptr
 
typedef boost::shared_ptr< const Feature< PointInT, PointOutT > > ConstPtr
 
typedef pcl::search::Search< PointInT > KdTree
 
typedef pcl::search::Search< PointInT >::Ptr KdTreePtr
 
typedef pcl::PointCloud< PointInT > PointCloudIn
 
typedef PointCloudIn::Ptr PointCloudInPtr
 
typedef PointCloudIn::ConstPtr PointCloudInConstPtr
 
typedef pcl::PointCloud< PointOutT > PointCloudOut
 
typedef boost::function< int(size_t, double, std::vector< int > &, std::vector< float > &)> SearchMethod
 
typedef boost::function< int(const PointCloudIn &cloud, size_t index, double, std::vector< int > &, std::vector< float > &)> SearchMethodSurface
 
- Public Types inherited from pcl::PCLBase< PointInT >
typedef pcl::PointCloud< PointInT > PointCloud
 
typedef PointCloud::Ptr PointCloudPtr
 
typedef PointCloud::ConstPtr PointCloudConstPtr
 
typedef boost::shared_ptr< PointIndicesPointIndicesPtr
 
typedef boost::shared_ptr< PointIndices const > PointIndicesConstPtr
 

Public Member Functions

 IntegralImageNormalEstimation ()
 Constructor. More...
 
virtual ~IntegralImageNormalEstimation ()
 Destructor. More...
 
void setRectSize (const int width, const int height)
 Set the regions size which is considered for normal estimation. More...
 
void setBorderPolicy (const BorderPolicy border_policy)
 Sets the policy for handling borders. More...
 
void computePointNormal (const int pos_x, const int pos_y, const unsigned point_index, PointOutT &normal)
 Computes the normal at the specified position. More...
 
void computePointNormalMirror (const int pos_x, const int pos_y, const unsigned point_index, PointOutT &normal)
 Computes the normal at the specified position with mirroring for border handling. More...
 
void setMaxDepthChangeFactor (float max_depth_change_factor)
 The depth change threshold for computing object borders. More...
 
void setNormalSmoothingSize (float normal_smoothing_size)
 Set the normal smoothing size. More...
 
void setNormalEstimationMethod (NormalEstimationMethod normal_estimation_method)
 Set the normal estimation method. More...
 
void setDepthDependentSmoothing (bool use_depth_dependent_smoothing)
 Set whether to use depth depending smoothing or not. More...
 
virtual void setInputCloud (const typename PointCloudIn::ConstPtr &cloud)
 Provide a pointer to the input dataset (overwrites the PCLBase::setInputCloud method) More...
 
float * getDistanceMap ()
 Returns a pointer to the distance map which was computed internally. More...
 
void setViewPoint (float vpx, float vpy, float vpz)
 Set the viewpoint. More...
 
void getViewPoint (float &vpx, float &vpy, float &vpz)
 Get the viewpoint. More...
 
void useSensorOriginAsViewPoint ()
 sets whether the sensor origin or a user given viewpoint should be used. More...
 
- Public Member Functions inherited from pcl::Feature< PointInT, PointOutT >
 Feature ()
 Empty constructor. More...
 
virtual ~Feature ()
 Empty destructor. More...
 
void setSearchSurface (const PointCloudInConstPtr &cloud)
 Provide a pointer to a dataset to add additional information to estimate the features for every point in the input dataset. More...
 
PointCloudInConstPtr getSearchSurface () const
 Get a pointer to the surface point cloud dataset. More...
 
void setSearchMethod (const KdTreePtr &tree)
 Provide a pointer to the search object. More...
 
KdTreePtr getSearchMethod () const
 Get a pointer to the search method used. More...
 
double getSearchParameter () const
 Get the internal search parameter. More...
 
void setKSearch (int k)
 Set the number of k nearest neighbors to use for the feature estimation. More...
 
int getKSearch () const
 get the number of k nearest neighbors used for the feature estimation. More...
 
void setRadiusSearch (double radius)
 Set the sphere radius that is to be used for determining the nearest neighbors used for the feature estimation. More...
 
double getRadiusSearch () const
 Get the sphere radius used for determining the neighbors. More...
 
void compute (PointCloudOut &output)
 Base method for feature estimation for all points given in <setInputCloud (), setIndices ()> using the surface in setSearchSurface () and the spatial locator in setSearchMethod () More...
 
- Public Member Functions inherited from pcl::PCLBase< PointInT >
 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 () 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 (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...
 
IndicesConstPtr const getIndices () const
 Get a pointer to the vector of indices used. More...
 
const PointInT & operator[] (size_t pos) const
 Override PointCloud operator[] to shorten code. More...
 

Protected Member Functions

void computeFeature (PointCloudOut &output)
 Computes the normal for the complete cloud or only indices_ if provided. More...
 
void computeFeatureFull (const float *distance_map, const float &bad_point, PointCloudOut &output)
 Computes the normal for the complete cloud. More...
 
void computeFeaturePart (const float *distance_map, const float &bad_point, PointCloudOut &output)
 Computes the normal for part of the cloud specified by indices_. More...
 
void initData ()
 Initialize the data structures, based on the normal estimation method chosen. More...
 
- Protected Member Functions inherited from pcl::Feature< PointInT, PointOutT >
const std::string & getClassName () const
 Get a string representation of the name of this class. More...
 
virtual bool deinitCompute ()
 This method should get called after ending the actual computation. More...
 
int searchForNeighbors (size_t index, double parameter, std::vector< int > &indices, std::vector< float > &distances) const
 Search for k-nearest neighbors using the spatial locator from setSearchmethod, and the given surface from setSearchSurface. More...
 
int searchForNeighbors (const PointCloudIn &cloud, size_t index, double parameter, std::vector< int > &indices, std::vector< float > &distances) const
 Search for k-nearest neighbors using the spatial locator from setSearchmethod, and the given surface from setSearchSurface. More...
 
- Protected Member Functions inherited from pcl::PCLBase< PointInT >
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...
 

Additional Inherited Members

- Protected Attributes inherited from pcl::Feature< PointInT, PointOutT >
std::string feature_name_
 The feature name. More...
 
SearchMethodSurface search_method_surface_
 The search method template for points. More...
 
PointCloudInConstPtr surface_
 An input point cloud describing the surface that is to be used for nearest neighbors estimation. More...
 
KdTreePtr tree_
 A pointer to the spatial search object. More...
 
double search_parameter_
 The actual search parameter (from either search_radius_ or k_). More...
 
double search_radius_
 The nearest neighbors search radius for each point. More...
 
int k_
 The number of K nearest neighbors to use for each point. More...
 
bool fake_surface_
 If no surface is given, we use the input PointCloud as the surface. More...
 
- Protected Attributes inherited from pcl::PCLBase< PointInT >
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...
 

Detailed Description

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

Surface normal estimation on organized data using integral images.

For detailed information about this method see:

S. Holzer and R. B. Rusu and M. Dixon and S. Gedikli and N. Navab, Adaptive Neighborhood Selection for Real-Time Surface Normal Estimation from Organized Point Cloud Data Using Integral Images, IROS 2012.

D. Holz, S. Holzer, R. B. Rusu, and S. Behnke (2011, July). Real-Time Plane Segmentation using RGB-D Cameras. In Proceedings of the 15th RoboCup International Symposium, Istanbul, Turkey. http://www.ais.uni-bonn.de/~holz/papers/holz_2011_robocup.pdf

Author
Stefan Holzer

Definition at line 67 of file integral_image_normal.h.

Member Typedef Documentation

template<typename PointInT, typename PointOutT>
typedef boost::shared_ptr<const IntegralImageNormalEstimation<PointInT, PointOutT> > pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::ConstPtr

Definition at line 77 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
typedef Feature<PointInT, PointOutT>::PointCloudIn pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::PointCloudIn

Definition at line 105 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
typedef Feature<PointInT, PointOutT>::PointCloudOut pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::PointCloudOut

Definition at line 106 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
typedef boost::shared_ptr<IntegralImageNormalEstimation<PointInT, PointOutT> > pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::Ptr

Definition at line 76 of file integral_image_normal.h.

Member Enumeration Documentation

template<typename PointInT, typename PointOutT>
enum pcl::IntegralImageNormalEstimation::BorderPolicy

Different types of border handling.

Enumerator
BORDER_POLICY_IGNORE 
BORDER_POLICY_MIRROR 

Definition at line 80 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
enum pcl::IntegralImageNormalEstimation::NormalEstimationMethod

Different normal estimation methods.

  • COVARIANCE_MATRIX - creates 9 integral images to compute the normal for a specific point from the covariance matrix of its local neighborhood.
  • AVERAGE_3D_GRADIENT - creates 6 integral images to compute smoothed versions of horizontal and vertical 3D gradients and computes the normals using the cross-product between these two gradients.
  • AVERAGE_DEPTH_CHANGE - creates only a single integral image and computes the normals from the average depth changes.
Enumerator
COVARIANCE_MATRIX 
AVERAGE_3D_GRADIENT 
AVERAGE_DEPTH_CHANGE 
SIMPLE_3D_GRADIENT 

Definition at line 97 of file integral_image_normal.h.

Constructor & Destructor Documentation

template<typename PointInT, typename PointOutT>
pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::IntegralImageNormalEstimation ( )
inline

Constructor.

Definition at line 109 of file integral_image_normal.h.

template<typename PointInT , typename PointOutT >
pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::~IntegralImageNormalEstimation ( )
virtual

Member Function Documentation

template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::computeFeature ( PointCloudOut output)
protectedvirtual

Computes the normal for the complete cloud or only indices_ if provided.

Parameters
[out]outputthe resultant normals

Implements pcl::Feature< PointInT, PointOutT >.

Definition at line 722 of file integral_image_normal.hpp.

References pcl::PointCloud< PointT >::sensor_orientation_, and pcl::PointCloud< PointT >::sensor_origin_.

Referenced by pcl::IntegralImageNormalEstimation< pcl::PointXYZRGBA, pcl::pcl::Normal >::useSensorOriginAsViewPoint().

template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::computeFeatureFull ( const float *  distance_map,
const float &  bad_point,
PointCloudOut output 
)
protected

Computes the normal for the complete cloud.

Parameters
[in]distance_mapdistance map
[in]bad_pointconstant given to invalid normal components
[out]outputthe resultant normals

Definition at line 829 of file integral_image_normal.hpp.

References pcl::computePointNormal(), pcl::PointCloud< PointT >::is_dense, and pcl::PointCloud< PointT >::width.

Referenced by pcl::IntegralImageNormalEstimation< pcl::PointXYZRGBA, pcl::pcl::Normal >::useSensorOriginAsViewPoint().

template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::computeFeaturePart ( const float *  distance_map,
const float &  bad_point,
PointCloudOut output 
)
protected

Computes the normal for part of the cloud specified by indices_.

Parameters
[in]distance_mapdistance map
[in]bad_pointconstant given to invalid normal components
[out]outputthe resultant normals

Definition at line 1016 of file integral_image_normal.hpp.

References pcl::computePointNormal(), pcl::PointCloud< PointT >::is_dense, pcl::PointCloud< PointT >::points, and pcl::PointCloud< PointT >::width.

Referenced by pcl::IntegralImageNormalEstimation< pcl::PointXYZRGBA, pcl::pcl::Normal >::useSensorOriginAsViewPoint().

template<typename PointInT , typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::computePointNormal ( const int  pos_x,
const int  pos_y,
const unsigned  point_index,
PointOutT &  normal 
)

Computes the normal at the specified position.

Parameters
[in]pos_xx position (pixel)
[in]pos_yy position (pixel)
[in]point_indexthe position index of the point
[out]normalthe output estimated normal

Definition at line 207 of file integral_image_normal.hpp.

References pcl::eigen33(), pcl::EIGEN_ALIGN16, pcl::flipNormalTowardsViewpoint(), pcl::IntegralImage2D< DataType, Dimension >::getFirstOrderSum(), and pcl::IntegralImage2D< DataType, Dimension >::getSecondOrderSum().

Referenced by pcl::IntegralImageNormalEstimation< pcl::PointXYZRGBA, pcl::pcl::Normal >::setBorderPolicy().

template<typename PointInT , typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::computePointNormalMirror ( const int  pos_x,
const int  pos_y,
const unsigned  point_index,
PointOutT &  normal 
)

Computes the normal at the specified position with mirroring for border handling.

Parameters
[in]pos_xx position (pixel)
[in]pos_yy position (pixel)
[in]point_indexthe position index of the point
[out]normalthe output estimated normal

Definition at line 462 of file integral_image_normal.hpp.

References pcl::eigen33(), pcl::EIGEN_ALIGN16, and pcl::flipNormalTowardsViewpoint().

Referenced by pcl::IntegralImageNormalEstimation< pcl::PointXYZRGBA, pcl::pcl::Normal >::setBorderPolicy().

template<typename PointInT, typename PointOutT>
float* pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::getDistanceMap ( )
inline

Returns a pointer to the distance map which was computed internally.

Definition at line 259 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::getViewPoint ( float &  vpx,
float &  vpy,
float &  vpz 
)
inline

Get the viewpoint.

Parameters
[out]vpxx-coordinate of the view point
[out]vpyy-coordinate of the view point
[out]vpzz-coordinate of the view point
Note
this method returns the currently used viewpoint for normal flipping. If the viewpoint is set manually using the setViewPoint method, this method will return the set view point coordinates. If an input cloud is set, it will return the sensor origin otherwise it will return the origin (0, 0, 0)

Definition at line 287 of file integral_image_normal.h.

template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::initData ( )
protected
template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setBorderPolicy ( const BorderPolicy  border_policy)
inline

Sets the policy for handling borders.

Parameters
[in]border_policythe border policy.

Definition at line 154 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setDepthDependentSmoothing ( bool  use_depth_dependent_smoothing)
inline

Set whether to use depth depending smoothing or not.

Parameters
[in]use_depth_dependent_smoothingdecides whether the smoothing is depth dependent

Definition at line 225 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
virtual void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setInputCloud ( const typename PointCloudIn::ConstPtr cloud)
inlinevirtual
template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setMaxDepthChangeFactor ( float  max_depth_change_factor)
inline

The depth change threshold for computing object borders.

Parameters
[in]max_depth_change_factorthe depth change threshold for computing object borders based on depth changes

Definition at line 182 of file integral_image_normal.h.

Referenced by pcl::gpu::people::OrganizedPlaneDetector::setNeMaxDepthChangeFactor().

template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setNormalEstimationMethod ( NormalEstimationMethod  normal_estimation_method)
inline

Set the normal estimation method.

The current implemented algorithms are:

  • COVARIANCE_MATRIX - creates 9 integral images to compute the normal for a specific point from the covariance matrix of its local neighborhood.
  • AVERAGE_3D_GRADIENT - creates 6 integral images to compute smoothed versions of horizontal and vertical 3D gradients and computes the normals using the cross-product between these two gradients.
  • AVERAGE_DEPTH_CHANGE - creates only a single integral image and computes the normals from the average depth changes.
Parameters
[in]normal_estimation_methodthe method used for normal estimation

Definition at line 216 of file integral_image_normal.h.

Referenced by pcl::HarrisKeypoint6D< PointInT, PointOutT, NormalT >::detectKeypoints(), pcl::TrajkovicKeypoint3D< PointInT, PointOutT, NormalT >::initCompute(), pcl::HarrisKeypoint3D< PointInT, PointOutT, NormalT >::initCompute(), pcl::SUSANKeypoint< PointInT, PointOutT, NormalT, IntensityT >::initCompute(), and pcl::ISSKeypoint3D< PointInT, PointOutT, NormalT >::initCompute().

template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setNormalSmoothingSize ( float  normal_smoothing_size)
inline
template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setRectSize ( const int  width,
const int  height 
)

Set the regions size which is considered for normal estimation.

Parameters
[in]widththe width of the search rectangle
[in]heightthe height of the search rectangle

Definition at line 93 of file integral_image_normal.hpp.

Referenced by pcl::IntegralImageNormalEstimation< pcl::PointXYZRGBA, pcl::pcl::Normal >::IntegralImageNormalEstimation().

template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setViewPoint ( float  vpx,
float  vpy,
float  vpz 
)
inline

Set the viewpoint.

Parameters
vpxthe X coordinate of the viewpoint
vpythe Y coordinate of the viewpoint
vpzthe Z coordinate of the viewpoint

Definition at line 270 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::useSensorOriginAsViewPoint ( )
inline

sets whether the sensor origin or a user given viewpoint should be used.

After this method, the normal estimation method uses the sensor origin of the input cloud. to use a user defined view point, use the method setViewPoint

Definition at line 299 of file integral_image_normal.h.


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