OrganizedEdgeBase, OrganizedEdgeFromRGB, OrganizedEdgeFromNormals, and OrganizedEdgeFromRGBNormals find 3D edges from an organized point cloud data. More...

#include <pcl/features/organized_edge_detection.h>

Inheritance diagram for pcl::OrganizedEdgeBase< PointT, PointLT >:

Collaboration diagram for pcl::OrganizedEdgeBase< PointT, PointLT >:

Classes
struct	Neighbor

Public Types
enum	{ EDGELABEL_NAN_BOUNDARY =1 , EDGELABEL_OCCLUDING =2 , EDGELABEL_OCCLUDED =4 , EDGELABEL_HIGH_CURVATURE =8 , EDGELABEL_RGB_CANNY =16 }

using	Ptr = shared_ptr< OrganizedEdgeBase< PointT, PointLT > >

using	ConstPtr = shared_ptr< const OrganizedEdgeBase< PointT, PointLT > >

Public Types inherited from pcl::PCLBase< PointT >
using	PointCloud = pcl::PointCloud< PointT >

using	PointCloudPtr = typename PointCloud::Ptr

using	PointCloudConstPtr = typename PointCloud::ConstPtr

using	PointIndicesPtr = PointIndices::Ptr

using	PointIndicesConstPtr = PointIndices::ConstPtr

Public Member Functions
	OrganizedEdgeBase ()
	Constructor for OrganizedEdgeBase. More...

	~OrganizedEdgeBase () override=default
	Destructor for OrganizedEdgeBase. More...

void	compute (pcl::PointCloud< PointLT > &labels, std::vector< pcl::PointIndices > &label_indices) const
	Perform the 3D edge detection (edges from depth discontinuities) More...

void	setDepthDisconThreshold (const float th)
	Set the tolerance in meters for the relative difference in depth values between neighboring points. More...

float	getDepthDisconThreshold () const
	Get the tolerance in meters for the relative difference in depth values between neighboring points. More...

void	setMaxSearchNeighbors (const int max_dist)
	Set the max search distance for deciding occluding and occluded edges. More...

int	getMaxSearchNeighbors () const
	Get the max search distance for deciding occluding and occluded edges. More...

void	setEdgeType (int edge_types)
	Set the detecting edge types. More...

int	getEdgeType () const
	Get the detecting edge types. More...

Public Member Functions inherited from pcl::PCLBase< PointT >
	PCLBase ()
	Empty constructor. More...

	PCLBase (const PCLBase &base)
	Copy constructor. More...

virtual	~PCLBase ()=default
	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 (std::size_t row_start, std::size_t col_start, std::size_t nb_rows, std::size_t nb_cols)
	Set the indices for the points laying within an interest region of the point cloud. More...

IndicesPtr	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 PointT &	operator[] (std::size_t pos) const
	Override PointCloud operator[] to shorten code. More...

Static Public Attributes
static const int	num_of_edgetype_ = 5

Protected Member Functions
void	extractEdges (pcl::PointCloud< PointLT > &labels) const
	Perform the 3D edge detection (edges from depth discontinuities) and assign point indices for each edge label. More...

void	assignLabelIndices (pcl::PointCloud< PointLT > &labels, std::vector< pcl::PointIndices > &label_indices) const
	Assign point indices for each edge label. More...

Protected Member Functions inherited from pcl::PCLBase< PointT >
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
float	th_depth_discon_ {0.02f}
	The tolerance in meters for the relative difference in depth values between neighboring points (The default value is set for .02 meters and is adapted with respect to depth value linearly. More...

int	max_search_neighbors_ {50}
	The max search distance for deciding occluding and occluded edges. More...

int	detecting_edge_types_
	The bit encoded value that represents edge types to detect. More...

Protected Attributes inherited from pcl::PCLBase< PointT >
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 PointT, typename PointLT>
class pcl::OrganizedEdgeBase< PointT, PointLT >

OrganizedEdgeBase, OrganizedEdgeFromRGB, OrganizedEdgeFromNormals, and OrganizedEdgeFromRGBNormals find 3D edges from an organized point cloud data.

Given an organized point cloud, they will output a PointCloud of edge labels and a vector of PointIndices. OrganizedEdgeBase accepts PCL_XYZ_POINT_TYPES and returns EDGELABEL_NAN_BOUNDARY, EDGELABEL_OCCLUDING, and EDGELABEL_OCCLUDED. OrganizedEdgeFromRGB accepts PCL_RGB_POINT_TYPES and returns EDGELABEL_NAN_BOUNDARY, EDGELABEL_OCCLUDING, EDGELABEL_OCCLUDED, and EDGELABEL_RGB_CANNY. OrganizedEdgeFromNormals accepts PCL_XYZ_POINT_TYPES with PCL_NORMAL_POINT_TYPES and returns EDGELABEL_NAN_BOUNDARY, EDGELABEL_OCCLUDING, EDGELABEL_OCCLUDED, and EDGELABEL_HIGH_CURVATURE. OrganizedEdgeFromRGBNormals accepts PCL_RGB_POINT_TYPES with PCL_NORMAL_POINT_TYPES and returns EDGELABEL_NAN_BOUNDARY, EDGELABEL_OCCLUDING, EDGELABEL_OCCLUDED, EDGELABEL_HIGH_CURVATURE, and EDGELABEL_RGB_CANNY.

Author: Changhyun Choi

Definition at line 57 of file organized_edge_detection.h.

Member Typedef Documentation

◆ ConstPtr

template<typename PointT , typename PointLT >

using pcl::OrganizedEdgeBase< PointT, PointLT >::ConstPtr = shared_ptr<const OrganizedEdgeBase<PointT, PointLT> >

Definition at line 69 of file organized_edge_detection.h.

◆ Ptr

template<typename PointT , typename PointLT >

using pcl::OrganizedEdgeBase< PointT, PointLT >::Ptr = shared_ptr<OrganizedEdgeBase<PointT, PointLT> >

Definition at line 68 of file organized_edge_detection.h.

Member Enumeration Documentation

◆ anonymous enum

template<typename PointT , typename PointLT >

anonymous enum

Enumerator
EDGELABEL_NAN_BOUNDARY
EDGELABEL_OCCLUDING
EDGELABEL_OCCLUDED
EDGELABEL_HIGH_CURVATURE
EDGELABEL_RGB_CANNY

Definition at line 137 of file organized_edge_detection.h.

Constructor & Destructor Documentation

◆ OrganizedEdgeBase()

template<typename PointT , typename PointLT >

pcl::OrganizedEdgeBase< PointT, PointLT >::OrganizedEdgeBase ( )

inline

Constructor for OrganizedEdgeBase.

Definition at line 76 of file organized_edge_detection.h.

◆ ~OrganizedEdgeBase()

template<typename PointT , typename PointLT >

pcl::OrganizedEdgeBase< PointT, PointLT >::~OrganizedEdgeBase ( )

overridedefault

Destructor for OrganizedEdgeBase.

Member Function Documentation

◆ assignLabelIndices()

template<typename PointT , typename PointLT >

void pcl::OrganizedEdgeBase< PointT, PointLT >::assignLabelIndices	(	pcl::PointCloud< PointLT > &	labels,
		std::vector< pcl::PointIndices > &	label_indices
	)		const

protected

Assign point indices for each edge label.

Parameters

[out]	labels	a PointCloud of edge labels
[out]	label_indices	a vector of PointIndices corresponding to each edge label

Definition at line 67 of file organized_edge_detection.hpp.

◆ compute()

template<typename PointT , typename PointLT >

void pcl::OrganizedEdgeBase< PointT, PointLT >::compute	(	pcl::PointCloud< PointLT > &	labels,
		std::vector< pcl::PointIndices > &	label_indices
	)		const

Perform the 3D edge detection (edges from depth discontinuities)

Directions: 1 2 3 0 x 4 7 6 5 e.g.

Parameters

[out]	labels	a PointCloud of edge labels
[out]	label_indices	a vector of PointIndices corresponding to each edge label

direction y means we came from pixel with label y to the center pixel x

Definition at line 52 of file organized_edge_detection.hpp.

References pcl::PointCloud< PointT >::height, pcl::Label::label, pcl::PointCloud< PointT >::resize(), and pcl::PointCloud< PointT >::width.

◆ extractEdges()

template<typename PointT , typename PointLT >

void pcl::OrganizedEdgeBase< PointT, PointLT >::extractEdges ( pcl::PointCloud< PointLT > & labels ) const

protected

Perform the 3D edge detection (edges from depth discontinuities) and assign point indices for each edge label.

Parameters

[out] labels a PointCloud of edge labels

Definition at line 86 of file organized_edge_detection.hpp.

References pcl::OrganizedEdgeBase< PointT, PointLT >::Neighbor::d_index, and pcl::PointCloud< PointT >::width.

◆ getDepthDisconThreshold()

template<typename PointT , typename PointLT >

float pcl::OrganizedEdgeBase< PointT, PointLT >::getDepthDisconThreshold ( ) const

inline

Get the tolerance in meters for the relative difference in depth values between neighboring points.

e.g. If a point has a depth (z) value of 2.0 meters, a neighboring point is discontinuous if its depth differs by > 2.0 * th.

Definition at line 104 of file organized_edge_detection.h.

References pcl::OrganizedEdgeBase< PointT, PointLT >::th_depth_discon_.

◆ getEdgeType()

template<typename PointT , typename PointLT >

int pcl::OrganizedEdgeBase< PointT, PointLT >::getEdgeType ( ) const

inline

Get the detecting edge types.

Definition at line 132 of file organized_edge_detection.h.

References pcl::OrganizedEdgeBase< PointT, PointLT >::detecting_edge_types_.

◆ getMaxSearchNeighbors()

template<typename PointT , typename PointLT >

int pcl::OrganizedEdgeBase< PointT, PointLT >::getMaxSearchNeighbors ( ) const

inline

Get the max search distance for deciding occluding and occluded edges.

Definition at line 118 of file organized_edge_detection.h.

References pcl::OrganizedEdgeBase< PointT, PointLT >::max_search_neighbors_.

◆ setDepthDisconThreshold()

template<typename PointT , typename PointLT >

void pcl::OrganizedEdgeBase< PointT, PointLT >::setDepthDisconThreshold ( const float th )

inline

Set the tolerance in meters for the relative difference in depth values between neighboring points.

e.g. If a point has a depth (z) value of 2.0 meters, a neighboring point is discontinuous if its depth differs by > 2.0 * th.

Definition at line 96 of file organized_edge_detection.h.

References pcl::OrganizedEdgeBase< PointT, PointLT >::th_depth_discon_.

◆ setEdgeType()

template<typename PointT , typename PointLT >

void pcl::OrganizedEdgeBase< PointT, PointLT >::setEdgeType ( int edge_types )

inline

Set the detecting edge types.

Definition at line 125 of file organized_edge_detection.h.

References pcl::OrganizedEdgeBase< PointT, PointLT >::detecting_edge_types_.

Referenced by pcl::OrganizedEdgeFromNormals< PointT, PointNT, PointLT >::OrganizedEdgeFromNormals(), pcl::OrganizedEdgeFromRGB< PointT, PointLT >::OrganizedEdgeFromRGB(), and pcl::OrganizedEdgeFromRGBNormals< PointT, PointNT, PointLT >::OrganizedEdgeFromRGBNormals().

◆ setMaxSearchNeighbors()

template<typename PointT , typename PointLT >

void pcl::OrganizedEdgeBase< PointT, PointLT >::setMaxSearchNeighbors ( const int max_dist )

inline

Set the max search distance for deciding occluding and occluded edges.

Definition at line 111 of file organized_edge_detection.h.

References pcl::OrganizedEdgeBase< PointT, PointLT >::max_search_neighbors_.

Member Data Documentation

◆ detecting_edge_types_

template<typename PointT , typename PointLT >

int pcl::OrganizedEdgeBase< PointT, PointLT >::detecting_edge_types_

protected

The bit encoded value that represents edge types to detect.

Definition at line 176 of file organized_edge_detection.h.

Referenced by pcl::OrganizedEdgeBase< PointT, PointLT >::getEdgeType(), and pcl::OrganizedEdgeBase< PointT, PointLT >::setEdgeType().

◆ max_search_neighbors_

template<typename PointT , typename PointLT >

int pcl::OrganizedEdgeBase< PointT, PointLT >::max_search_neighbors_ {50}

protected

The max search distance for deciding occluding and occluded edges.

Definition at line 173 of file organized_edge_detection.h.

Referenced by pcl::OrganizedEdgeBase< PointT, PointLT >::getMaxSearchNeighbors(), and pcl::OrganizedEdgeBase< PointT, PointLT >::setMaxSearchNeighbors().

◆ num_of_edgetype_

template<typename PointT , typename PointLT >

const int pcl::OrganizedEdgeBase< PointT, PointLT >::num_of_edgetype_ = 5

static

Definition at line 138 of file organized_edge_detection.h.

◆ th_depth_discon_

template<typename PointT , typename PointLT >

float pcl::OrganizedEdgeBase< PointT, PointLT >::th_depth_discon_ {0.02f}

protected

The tolerance in meters for the relative difference in depth values between neighboring points (The default value is set for .02 meters and is adapted with respect to depth value linearly.

e.g. If a point has a depth (z) value of 2.0 meters, a neighboring point is discontinuous if its depth differs by > 2.0 * th.

Definition at line 170 of file organized_edge_detection.h.

Referenced by pcl::OrganizedEdgeBase< PointT, PointLT >::getDepthDisconThreshold(), and pcl::OrganizedEdgeBase< PointT, PointLT >::setDepthDisconThreshold().

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

pcl/features/organized_edge_detection.h
pcl/features/impl/organized_edge_detection.hpp

Classes

Public Types

Public Member Functions

Static Public Attributes

Protected Member Functions

Protected Attributes

Detailed Description

template<typename PointT, typename PointLT> class pcl::OrganizedEdgeBase< PointT, PointLT >

Member Typedef Documentation

◆ ConstPtr

◆ Ptr

Member Enumeration Documentation

◆ anonymous enum

Constructor & Destructor Documentation

◆ OrganizedEdgeBase()

◆ ~OrganizedEdgeBase()

Member Function Documentation

◆ assignLabelIndices()

◆ compute()

◆ extractEdges()

◆ getDepthDisconThreshold()

◆ getEdgeType()

◆ getMaxSearchNeighbors()

◆ setDepthDisconThreshold()

◆ setEdgeType()

◆ setMaxSearchNeighbors()

Member Data Documentation

◆ detecting_edge_types_

◆ max_search_neighbors_

◆ num_of_edgetype_

◆ th_depth_discon_

template<typename PointT, typename PointLT>
class pcl::OrganizedEdgeBase< PointT, PointLT >