Point Cloud Library (PCL)  1.7.0
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 >:

List of all members.

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 Member Functions

 IntegralImageNormalEstimation ()
 Constructor.
virtual ~IntegralImageNormalEstimation ()
 Destructor.
void setRectSize (const int width, const int height)
 Set the regions size which is considered for normal estimation.
void setBorderPolicy (const BorderPolicy border_policy)
 Sets the policy for handling borders.
void computePointNormal (const int pos_x, const int pos_y, const unsigned point_index, PointOutT &normal)
 Computes the normal at the specified position.
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.
void setMaxDepthChangeFactor (float max_depth_change_factor)
 The depth change threshold for computing object borders.
void setNormalSmoothingSize (float normal_smoothing_size)
 Set the normal smoothing size.
void setNormalEstimationMethod (NormalEstimationMethod normal_estimation_method)
 Set the normal estimation method.
void setDepthDependentSmoothing (bool use_depth_dependent_smoothing)
 Set whether to use depth depending smoothing or not.
virtual void setInputCloud (const typename PointCloudIn::ConstPtr &cloud)
 Provide a pointer to the input dataset (overwrites the PCLBase::setInputCloud method)
float * getDistanceMap ()
 Returns a pointer to the distance map which was computed internally.
void setViewPoint (float vpx, float vpy, float vpz)
 Set the viewpoint.
void getViewPoint (float &vpx, float &vpy, float &vpz)
 Get the viewpoint.
void useSensorOriginAsViewPoint ()
 sets whether the sensor origin or a user given viewpoint should be used.

Protected Member Functions

void computeFeature (PointCloudOut &output)
 Computes the normal for the complete cloud.
void initData ()
 Initialize the data structures, based on the normal estimation method chosen.

Detailed Description

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

Surface normal estimation on organized data using integral images.

Author:
Stefan Holzer

Definition at line 56 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

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

Definition at line 65 of file integral_image_normal.h.

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

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

Definition at line 93 of file integral_image_normal.h.

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

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

Definition at line 94 of file integral_image_normal.h.

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

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

Definition at line 64 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 68 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 85 of file integral_image_normal.h.


Constructor & Destructor Documentation

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

Destructor.

Definition at line 46 of file integral_image_normal.hpp.


Member Function Documentation

template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::computeFeature ( PointCloudOut output) [protected, virtual]
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().

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().

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 247 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 275 of file integral_image_normal.h.

template<typename PointInT , typename PointOutT >
void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::initData ( ) [protected]

Initialize the data structures, based on the normal estimation method chosen.

Definition at line 56 of file integral_image_normal.hpp.

Referenced by pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setInputCloud().

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 142 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 213 of file integral_image_normal.h.

template<typename PointInT, typename PointOutT>
virtual void pcl::IntegralImageNormalEstimation< PointInT, PointOutT >::setInputCloud ( const typename PointCloudIn::ConstPtr cloud) [inline, virtual]
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 170 of file integral_image_normal.h.

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 204 of file integral_image_normal.h.

Referenced by pcl::HarrisKeypoint6D< PointInT, PointOutT, NormalT >::detectKeypoints(), 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]

Set the normal smoothing size.

Parameters:
[in]normal_smoothing_sizefactor which influences the size of the area used to smooth normals (depth dependent if useDepthDependentSmoothing is true)

Definition at line 180 of file integral_image_normal.h.

References pcl::Feature< PointInT, PointOutT >::feature_name_.

Referenced by pcl::HarrisKeypoint6D< PointInT, PointOutT, NormalT >::detectKeypoints(), 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 >::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.

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 258 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 287 of file integral_image_normal.h.

References pcl::PCLBase< PointInT >::input_.


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