Module features

---

Detailed Description

Overview

The pcl_features library contains data structures and mechanisms for 3D feature estimation from point cloud data. 3D features are representations at a certain 3D point or position in space, which describe geometrical patterns based on the information available around the point. The data space selected around the query point is usually referred as the k-neighborhood.

The following figure shows a simple example of a selected query point, and its selected k-neighborhood.

An example of two of the most widely used geometric point features are the underlying surface's estimated curvature and normal at a query point p. Both of them are considered local features, as they characterize a point using the information provided by its k closest point neighbors. For determining these neighbors efficienctly, the input dataset is usually split into smaller chunks using spatial decomposition techniques such as octrees or kD-trees (see the figure below - left: kD-tree, right: octree), and then closest point searches are performed in that space. Depending on the application one can opt for either determining a fixed number of k points in the vecinity of p, or all points which are found inside of a sphere of radius r centered at p. Unarguably, one the easiest methods for estimating the surface normals and curvature changes at a point p is to perform an eigendecomposition (i.e. compute the eigenvectors and eigenvalues) of the k-neighborhood point surface patch. Thus, the eigenvector corresponding to the smallest eigenvalue will approximate the surface normal n at point p, while the surface curvature change will be estimated from the eigenvalues as:

, where .

Please visit http://www.pointclouds.org for more information.

Requirements

• common
• search
• kdtree
• octree
• range_image

Classes
class	pcl::ShapeContext3DEstimation< PointInT, PointNT, PointOutT >
	ShapeContext3DEstimation implements the 3D shape context descriptor as described in: More...
class	pcl::ShapeContext3DEstimation< PointInT, PointNT, Eigen::MatrixXf >
	ShapeContext3DEstimation implements the 3D shape context descriptor as described in: More...
class	pcl::BoundaryEstimation< PointInT, PointNT, PointOutT >
	BoundaryEstimation estimates whether a set of points is lying on surface boundaries using an angle criterion. More...
class	pcl::BoundaryEstimation< PointInT, PointNT, Eigen::MatrixXf >
	BoundaryEstimation estimates whether a set of points is lying on surface boundaries using an angle criterion. More...
class	pcl::CVFHEstimation< PointInT, PointNT, PointOutT >
	CVFHEstimation estimates the Clustered Viewpoint Feature Histogram (CVFH) descriptor for a given point cloud dataset containing XYZ data and normals, as presented in: More...
class	pcl::Feature< PointInT, PointOutT >
	Feature represents the base feature class. More...
class	pcl::FPFHEstimation< PointInT, PointNT, PointOutT >
	FPFHEstimation estimates the Fast Point Feature Histogram (FPFH) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::FPFHEstimation< PointInT, PointNT, Eigen::MatrixXf >
	FPFHEstimation estimates the Fast Point Feature Histogram (FPFH) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::FPFHEstimationOMP< PointInT, PointNT, PointOutT >
	FPFHEstimationOMP estimates the Fast Point Feature Histogram (FPFH) descriptor for a given point cloud dataset containing points and normals, in parallel, using the OpenMP standard. More...
class	pcl::IntegralImage2D< DataType, Dimension >
	Determines an integral image representation for a given organized data array. More...
class	pcl::IntensityGradientEstimation< PointInT, PointNT, PointOutT >
	IntensityGradientEstimation estimates the intensity gradient for a point cloud that contains position and intensity values. More...
class	pcl::IntensityGradientEstimation< PointInT, PointNT, Eigen::MatrixXf >
	IntensityGradientEstimation estimates the intensity gradient for a point cloud that contains position and intensity values. More...
class	pcl::IntensitySpinEstimation< PointInT, PointOutT >
	IntensitySpinEstimation estimates the intensity-domain spin image descriptors for a given point cloud dataset containing points and intensity. More...
class	pcl::IntensitySpinEstimation< PointInT, Eigen::MatrixXf >
	IntensitySpinEstimation estimates the intensity-domain spin image descriptors for a given point cloud dataset containing points and intensity. More...
class	pcl::MomentInvariantsEstimation< PointInT, PointOutT >
	MomentInvariantsEstimation estimates the 3 moment invariants (j1, j2, j3) at each 3D point. More...
class	pcl::MomentInvariantsEstimation< PointInT, Eigen::MatrixXf >
	MomentInvariantsEstimation estimates the 3 moment invariants (j1, j2, j3) at each 3D point. More...
class	pcl::Narf
	NARF (Normal Aligned Radial Features) is a point feature descriptor type for 3D data. More...
class	pcl::NarfDescriptor
	Computes NARF feature descriptors for points in a range image More...
class	pcl::NormalEstimation< PointInT, PointOutT >
	NormalEstimation estimates local surface properties at each 3D point, such as surface normals and curvatures. More...
class	pcl::NormalEstimation< PointInT, Eigen::MatrixXf >
	NormalEstimation estimates local surface properties at each 3D point, such as surface normals and curvatures. More...
class	pcl::NormalEstimationOMP< PointInT, PointOutT >
	NormalEstimationOMP estimates local surface properties at each 3D point, such as surface normals and curvatures, in parallel, using the OpenMP standard. More...
class	pcl::NormalEstimationOMP< PointInT, Eigen::MatrixXf >
	NormalEstimationOMP estimates local surface properties at each 3D point, such as surface normals and curvatures, in parallel, using the OpenMP standard. More...
class	pcl::PFHEstimation< PointInT, PointNT, PointOutT >
	PFHEstimation estimates the Point Feature Histogram (PFH) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::PFHEstimation< PointInT, PointNT, Eigen::MatrixXf >
	PFHEstimation estimates the Point Feature Histogram (PFH) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::PrincipalCurvaturesEstimation< PointInT, PointNT, PointOutT >
	PrincipalCurvaturesEstimation estimates the directions (eigenvectors) and magnitudes (eigenvalues) of principal surface curvatures for a given point cloud dataset containing points and normals. More...
class	pcl::PrincipalCurvaturesEstimation< PointInT, PointNT, Eigen::MatrixXf >
	PrincipalCurvaturesEstimation estimates the directions (eigenvectors) and magnitudes (eigenvalues) of principal surface curvatures for a given point cloud dataset containing points and normals. More...
class	pcl::RangeImageBorderExtractor
	Extract obstacle borders from range images, meaning positions where there is a transition from foreground to background. More...
class	pcl::RIFTEstimation< PointInT, GradientT, PointOutT >
	RIFTEstimation estimates the Rotation Invariant Feature Transform descriptors for a given point cloud dataset containing points and intensity. More...
class	pcl::RIFTEstimation< PointInT, GradientT, Eigen::MatrixXf >
	RIFTEstimation estimates the Rotation Invariant Feature Transform descriptors for a given point cloud dataset containing points and intensity. More...
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. More...
class	pcl::SHOTEstimationBase< PointInT, PointNT, PointOutT >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::SHOTEstimationBase< PointInT, PointNT, Eigen::MatrixXf >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::SHOTEstimation< PointInT, PointNT, PointOutT >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::SHOTEstimation< PointInT, PointNT, Eigen::MatrixXf >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::SHOTEstimation< pcl::PointXYZRGBA, PointNT, PointOutT >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::SHOTEstimation< pcl::PointXYZRGBA, PointNT, Eigen::MatrixXf >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals. More...
class	pcl::SHOTEstimationOMP< PointInT, PointNT, PointOutT >
	SHOTEstimation estimates the Signature of Histograms of OrienTations (SHOT) descriptor for a given point cloud dataset containing points and normals, in parallel, using the OpenMP standard. More...
class	pcl::SpinImageEstimation< PointInT, PointNT, PointOutT >
	Estimates spin-image descriptors in the given input points. More...
class	pcl::SpinImageEstimation< PointInT, PointNT, Eigen::MatrixXf >
	Estimates spin-image descriptors in the given input points. More...
class	pcl::UniqueShapeContext< PointInT, PointOutT >
	UniqueShapeContext implements the Unique Shape Descriptor described here: More...
class	pcl::UniqueShapeContext< PointInT, Eigen::MatrixXf >
	UniqueShapeContext implements the Unique Shape Descriptor described here: More...
class	pcl::VFHEstimation< PointInT, PointNT, PointOutT >
	VFHEstimation estimates the Viewpoint Feature Histogram (VFH) descriptor for a given point cloud dataset containing points and normals. More...
Functions
void	pcl::solvePlaneParameters (const Eigen::Matrix3f &covariance_matrix, const Eigen::Vector4f &point, Eigen::Vector4f &plane_parameters, float &curvature)
	Solve the eigenvalues and eigenvectors of a given 3x3 covariance matrix, and estimate the least-squares plane normal and surface curvature.
void	pcl::solvePlaneParameters (const Eigen::Matrix3f &covariance_matrix, float &nx, float &ny, float &nz, float &curvature)
	Solve the eigenvalues and eigenvectors of a given 3x3 covariance matrix, and estimate the least-squares plane normal and surface curvature.
template<typename PointT >
void	pcl::computePointNormal (const pcl::PointCloud< PointT > &cloud, Eigen::Vector4f &plane_parameters, float &curvature)
	Compute the Least-Squares plane fit for a given set of points, and return the estimated plane parameters together with the surface curvature.
template<typename PointT >
void	pcl::computePointNormal (const pcl::PointCloud< PointT > &cloud, const std::vector< int > &indices, Eigen::Vector4f &plane_parameters, float &curvature)
	Compute the Least-Squares plane fit for a given set of points, using their indices, and return the estimated plane parameters together with the surface curvature.
template<typename PointT >
void	pcl::flipNormalTowardsViewpoint (const PointT &point, float vp_x, float vp_y, float vp_z, Eigen::Vector4f &normal)
	Flip (in place) the estimated normal of a point towards a given viewpoint.
template<typename PointT >
void	pcl::flipNormalTowardsViewpoint (const PointT &point, float vp_x, float vp_y, float vp_z, float &nx, float &ny, float &nz)
	Flip (in place) the estimated normal of a point towards a given viewpoint.
PCL_EXPORTS bool	pcl::computePairFeatures (const Eigen::Vector4f &p1, const Eigen::Vector4f &n1, const Eigen::Vector4f &p2, const Eigen::Vector4f &n2, float &f1, float &f2, float &f3, float &f4)
	Compute the 4-tuple representation containing the three angles and one distance between two points represented by Cartesian coordinates and normals.
int	pcl::getSimpleType (float min_radius, float max_radius, double min_radius_plane=0.100, double max_radius_noise=0.015, double min_radius_cylinder=0.175, double max_min_radius_diff=0.050)
	Simple rule-based labeling of the local surface type based on the principle curvatures.
template<int N>
void	pcl::getFeaturePointCloud (const std::vector< Eigen::MatrixXf > &histograms2D, PointCloud< Histogram< N > > &histogramsPC)
	Transform a list of 2D matrices into a point cloud containing the values in a vector (Histogram<N>).
template<typename PointInT , typename PointNT , typename PointOutT >
void	pcl::computeRSD (const PointCloud< PointInT > &surface, const PointCloud< PointNT > &normals, const std::vector< int > &indices, double max_dist, int nr_subdiv, double plane_radius, PointOutT &radii, Eigen::MatrixXf *histogram=NULL)
	Estimate the Radius-based Surface Descriptor (RSD) for a given point based on its spatial neighborhood of 3D points with normals.

---

Function Documentation

PCL_EXPORTS bool pcl::computePairFeatures	(	const Eigen::Vector4f &	p1,
		const Eigen::Vector4f &	n1,
		const Eigen::Vector4f &	p2,
		const Eigen::Vector4f &	n2,
		float &	f1,
		float &	f2,
		float &	f3,
		float &	f4
	)

Compute the 4-tuple representation containing the three angles and one distance between two points represented by Cartesian coordinates and normals.

Note:

For explanations about the features, please see the literature mentioned above (the order of the features might be different).

Parameters:

[in]	p1	the first XYZ point
[in]	n1	the first surface normal
[in]	p2	the second XYZ point
[in]	n2	the second surface normal
[out]	f1	the first angular feature (angle between the projection of nq_idx and u)
[out]	f2	the second angular feature (angle between nq_idx and v)
[out]	f3	the third angular feature (angle between np_idx and |p_idx - q_idx|)
[out]	f4	the distance feature (p_idx - q_idx)

Note:

For efficiency reasons, we assume that the point data passed to the method is finite.

template<typename PointT >

void pcl::computePointNormal	(	const pcl::PointCloud< PointT > &	cloud,
		Eigen::Vector4f &	plane_parameters,
		float &	curvature
	)		[inline]

Compute the Least-Squares plane fit for a given set of points, and return the estimated plane parameters together with the surface curvature.

Parameters:

cloud	the input point cloud
plane_parameters	the plane parameters as: a, b, c, d (ax + by + cz + d = 0)
curvature	the estimated surface curvature as a measure of

Definition at line 58 of file normal_3d.h.

template<typename PointT >

void pcl::computePointNormal	(	const pcl::PointCloud< PointT > &	cloud,
		const std::vector< int > &	indices,
		Eigen::Vector4f &	plane_parameters,
		float &	curvature
	)		[inline]

Compute the Least-Squares plane fit for a given set of points, using their indices, and return the estimated plane parameters together with the surface curvature.

Parameters:

cloud	the input point cloud
indices	the point cloud indices that need to be used
plane_parameters	the plane parameters as: a, b, c, d (ax + by + cz + d = 0)
curvature	the estimated surface curvature as a measure of

Definition at line 94 of file normal_3d.h.

template<typename PointInT , typename PointNT , typename PointOutT >

void pcl::computeRSD	(	const PointCloud< PointInT > &	surface,
		const PointCloud< PointNT > &	normals,
		const std::vector< int > &	indices,
		double	max_dist,
		int	nr_subdiv,
		double	plane_radius,
		PointOutT &	radii,
		Eigen::MatrixXf *	histogram = NULL
	)		[inline]

Estimate the Radius-based Surface Descriptor (RSD) for a given point based on its spatial neighborhood of 3D points with normals.

Parameters:

[in]	surface	the dataset containing the XYZ points
[in]	normals	the dataset containing the surface normals at each point in the dataset
[in]	indices	the neighborhood point indices in the dataset
[in]	max_dist	the upper bound for the considered distance interval
[in]	nr_subdiv	the number of subdivisions for the considered distance interval
[in]	plane_radius	maximum radius, above which everything can be considered planar
[in]	radii	the output point of a type that should have r_min and r_max fields
[out]	histogram	if not NULL, the full neighborhood histogram is provided, usable as a point signature

Note:

: orientation is neglected!

: we neglect points that are outside the specified interval!

Definition at line 46 of file rsd.hpp.

template<typename PointT >

void pcl::flipNormalTowardsViewpoint	(	const PointT &	point,
		float	vp_x,
		float	vp_y,
		float	vp_z,
		Eigen::Vector4f &	normal
	)		[inline]

Flip (in place) the estimated normal of a point towards a given viewpoint.

Parameters:

point	a given point
vp_x	the X coordinate of the viewpoint
vp_y	the X coordinate of the viewpoint
vp_z	the X coordinate of the viewpoint
normal	the plane normal to be flipped

Definition at line 127 of file normal_3d.h.

template<typename PointT >

void pcl::flipNormalTowardsViewpoint	(	const PointT &	point,
		float	vp_x,
		float	vp_y,
		float	vp_z,
		float &	nx,
		float &	ny,
		float &	nz
	)		[inline]

Flip (in place) the estimated normal of a point towards a given viewpoint.

Parameters:

point	a given point
vp_x	the X coordinate of the viewpoint
vp_y	the X coordinate of the viewpoint
vp_z	the X coordinate of the viewpoint
nx	the resultant X component of the plane normal
ny	the resultant Y component of the plane normal
nz	the resultant Z component of the plane normal

Definition at line 159 of file normal_3d.h.

template<int N>

void pcl::getFeaturePointCloud	(	const std::vector< Eigen::MatrixXf > &	histograms2D,
		PointCloud< Histogram< N > > &	histogramsPC
	)

Transform a list of 2D matrices into a point cloud containing the values in a vector (Histogram<N>).

Can be used to transform the 2D histograms obtained in RSDEstimation into a point cloud.

Note:

The template paramter N should be (greater or) equal to the product of the number of rows and columns.

Parameters:

[in]	histograms2D	the list of neighborhood 2D histograms
[out]	histogramsPC	the dataset containing the linearized matrices

Definition at line 81 of file rsd.h.

int pcl::getSimpleType	(	float	min_radius,
		float	max_radius,
		double	min_radius_plane = 0.100,
		double	max_radius_noise = 0.015,
		double	min_radius_cylinder = 0.175,
		double	max_min_radius_diff = 0.050
	)		[inline]

Simple rule-based labeling of the local surface type based on the principle curvatures.

Parameters:

min_radius	smallest estimated surface radius
max_radius	largest estimated surface radius
min_radius_plane	radius above which a the labeled is "planar"==1
max_radius_noise	radius below which the label is "noise/corner"==0
min_radius_cylinder	radius above which the label is "cylinder/rim"==2
max_min_radius_diff	difference of the principal radii below which label is "sphere"==3 and above "edge"==4

Definition at line 55 of file rsd.h.

void pcl::solvePlaneParameters	(	const Eigen::Matrix3f &	covariance_matrix,
		const Eigen::Vector4f &	point,
		Eigen::Vector4f &	plane_parameters,
		float &	curvature
	)		[inline]

Solve the eigenvalues and eigenvectors of a given 3x3 covariance matrix, and estimate the least-squares plane normal and surface curvature.

Parameters:

covariance_matrix	the 3x3 covariance matrix
point	a point lying on the least-squares plane (SSE aligned)
plane_parameters	the resultant plane parameters as: a, b, c, d (ax + by + cz + d = 0)
curvature	the estimated surface curvature as a measure of

Definition at line 47 of file feature.hpp.

void pcl::solvePlaneParameters	(	const Eigen::Matrix3f &	covariance_matrix,
		float &	nx,
		float &	ny,
		float &	nz,
		float &	curvature
	)		[inline]

Solve the eigenvalues and eigenvectors of a given 3x3 covariance matrix, and estimate the least-squares plane normal and surface curvature.

Parameters:

covariance_matrix	the 3x3 covariance matrix
nx	the resultant X component of the plane normal
ny	the resultant Y component of the plane normal
nz	the resultant Z component of the plane normal
curvature	the estimated surface curvature as a measure of

Definition at line 97 of file feature.hpp.