Detailed Description

Overview

Combining several datasets into a global consistent model is usually performed using a technique called registration. The key idea is to identify corresponding points between the data sets and find a transformation that minimizes the distance (alignment error) between corresponding points. This process is repeated, since correspondence search is affected by the relative position and orientation of the data sets. Once the alignment errors fall below a given threshold, the registration is said to be complete.

The pcl_registration library implements a plethora of point cloud registration algorithms for both organized and unorganized (general purpose) datasets.

Requirements

• common
• kdtree
• sample_consensus
• features

Classes
class	pcl::registration::ConvergenceCriteria
	ConvergenceCriteria represents an abstract base class for different convergence criteria used in registration loops. More...
class	pcl::registration::CorrespondenceEstimationBase< PointSource, PointTarget, Scalar >
	Abstract CorrespondenceEstimationBase class. More...
class	pcl::registration::CorrespondenceEstimation< PointSource, PointTarget, Scalar >
	CorrespondenceEstimation represents the base class for determining correspondences between target and query point sets/features. More...
class	pcl::registration::CorrespondenceEstimationBackProjection< PointSource, PointTarget, NormalT, Scalar >
	CorrespondenceEstimationBackprojection computes correspondences as points in the target cloud which have minimum More...
class	pcl::registration::CorrespondenceEstimationNormalShooting< PointSource, PointTarget, NormalT, Scalar >
	CorrespondenceEstimationNormalShooting computes correspondences as points in the target cloud which have minimum distance to normals computed on the input cloud More...
class	pcl::registration::CorrespondenceEstimationOrganizedProjection< PointSource, PointTarget, Scalar >
	CorrespondenceEstimationOrganizedProjection computes correspondences by projecting the source point cloud onto the target point cloud using the camera intrinsic and extrinsic parameters. More...
class	pcl::registration::CorrespondenceRejector
	CorrespondenceRejector represents the base class for correspondence rejection methods More...
class	pcl::registration::DataContainerInterface
	DataContainerInterface provides a generic interface for computing correspondence scores between correspondent points in the input and target clouds More...
class	pcl::registration::DataContainer< PointT, NormalT >
	DataContainer is a container for the input and target point clouds and implements the interface to compute correspondence scores between correspondent points in the input and target clouds More...
class	pcl::registration::CorrespondenceRejectorDistance
	CorrespondenceRejectorDistance implements a simple correspondence rejection method based on thresholding the distances between the correspondences. More...
class	pcl::registration::CorrespondenceRejectorFeatures
	CorrespondenceRejectorFeatures implements a correspondence rejection method based on a set of feature descriptors. More...
class	pcl::registration::CorrespondenceRejectorMedianDistance
	CorrespondenceRejectorMedianDistance implements a simple correspondence rejection method based on thresholding based on the median distance between the correspondences. More...
class	pcl::registration::CorrespondenceRejectorOneToOne
	CorrespondenceRejectorOneToOne implements a correspondence rejection method based on eliminating duplicate match indices in the correspondences. More...
class	pcl::registration::CorrespondenceRejectionOrganizedBoundary
	The CorrespondenceRejectionOrganizedBoundary class implements a simple correspondence rejection measure. More...
class	pcl::registration::CorrespondenceRejectorPoly< SourceT, TargetT >
	CorrespondenceRejectorPoly implements a correspondence rejection method that exploits low-level and pose-invariant geometric constraints between two point sets by forming virtual polygons of a user-specifiable cardinality on each model using the input correspondences. More...
class	pcl::registration::CorrespondenceRejectorSampleConsensus< PointT >
	CorrespondenceRejectorSampleConsensus implements a correspondence rejection using Random Sample Consensus to identify inliers (and reject outliers) More...
class	pcl::registration::CorrespondenceRejectorSampleConsensus2D< PointT >
	CorrespondenceRejectorSampleConsensus2D implements a pixel-based correspondence rejection using Random Sample Consensus to identify inliers (and reject outliers) More...
class	pcl::registration::CorrespondenceRejectorSurfaceNormal
	CorrespondenceRejectorSurfaceNormal implements a simple correspondence rejection method based on the angle between the normals at correspondent points. More...
class	pcl::registration::CorrespondenceRejectorTrimmed
	CorrespondenceRejectorTrimmed implements a correspondence rejection for ICP-like registration algorithms that uses only the best 'k' correspondences where 'k' is some estimate of the overlap between the two point clouds being registered. More...
class	pcl::registration::CorrespondenceRejectorVarTrimmed
	CorrespondenceRejectoVarTrimmed implements a simple correspondence rejection method by considering as inliers a certain percentage of correspondences with the least distances. More...
struct	pcl::registration::sortCorrespondencesByQueryIndex
	sortCorrespondencesByQueryIndex : a functor for sorting correspondences by query index More...
struct	pcl::registration::sortCorrespondencesByMatchIndex
	sortCorrespondencesByMatchIndex : a functor for sorting correspondences by match index More...
struct	pcl::registration::sortCorrespondencesByDistance
	sortCorrespondencesByDistance : a functor for sorting correspondences by distance More...
struct	pcl::registration::sortCorrespondencesByQueryIndexAndDistance
	sortCorrespondencesByQueryIndexAndDistance : a functor for sorting correspondences by query index and distance More...
struct	pcl::registration::sortCorrespondencesByMatchIndexAndDistance
	sortCorrespondencesByMatchIndexAndDistance : a functor for sorting correspondences by match index and distance More...
class	pcl::registration::DefaultConvergenceCriteria< Scalar >
	DefaultConvergenceCriteria represents an instantiation of ConvergenceCriteria, and implements the following criteria for registration loop evaluation: More...
struct	pcl::registration::NullMeasurement
	NullMeasurement struct More...
struct	pcl::registration::PoseMeasurement< VertexT, InformationT >
	PoseMeasurement struct More...
class	pcl::registration::ELCH< PointT >
	ELCH (Explicit Loop Closing Heuristic) class More...
class	pcl::GeneralizedIterativeClosestPoint< PointSource, PointTarget >
	GeneralizedIterativeClosestPoint is an ICP variant that implements the generalized iterative closest point algorithm as described by Alex Segal et al. More...
class	pcl::GeneralizedIterativeClosestPoint6D
	GeneralizedIterativeClosestPoint6D integrates L*a*b* color space information into the Generalized Iterative Closest Point (GICP) algorithm. More...
class	pcl::registration::GraphHandler< GraphT >
	GraphHandler class is a wrapper for a general SLAM graph The actual graph class must fulfill the following boost::graph concepts: More...
class	pcl::registration::GraphOptimizer< GraphT >
	GraphOptimizer class; derive and specialize for each graph type More...
class	pcl::GraphRegistration< GraphT >
	GraphRegistration class is the base class for graph-based registration methods More...
class	pcl::registration::FPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >
	FPCSInitialAlignment computes corresponding four point congruent sets as described in: "4-points congruent sets for robust pairwise surface registration", Dror Aiger, Niloy Mitra, Daniel Cohen-Or. More...
class	pcl::registration::KFPCSInitialAlignment< PointSource, PointTarget, NormalT, Scalar >
	KFPCSInitialAlignment computes corresponding four point congruent sets based on keypoints as described in: "Markerless point cloud registration with keypoint-based 4-points congruent sets", Pascal Theiler, Jan Dirk Wegner, Konrad Schindler. More...
class	pcl::SampleConsensusInitialAlignment< PointSource, PointTarget, FeatureT >
	SampleConsensusInitialAlignment is an implementation of the initial alignment algorithm described in section IV of "Fast Point Feature Histograms (FPFH) for 3D Registration," Rusu et al. More...
class	pcl::IterativeClosestPoint< PointSource, PointTarget, Scalar >
	IterativeClosestPoint provides a base implementation of the Iterative Closest Point algorithm. More...
class	pcl::IterativeClosestPointWithNormals< PointSource, PointTarget, Scalar >
	IterativeClosestPointWithNormals is a special case of IterativeClosestPoint, that uses a transformation estimated based on Point to Plane distances by default. More...
class	pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >
	IterativeClosestPointNonLinear is an ICP variant that uses Levenberg-Marquardt optimization backend. More...
class	pcl::registration::IncrementalRegistration< PointT, Scalar >
	Incremental IterativeClosestPoint class. More...
class	pcl::JointIterativeClosestPoint< PointSource, PointTarget, Scalar >
	JointIterativeClosestPoint extends ICP to multiple frames which share the same transform. More...
class	pcl::registration::LUM< PointT >
	Globally Consistent Scan Matching based on an algorithm by Lu and Milios. More...
class	pcl::registration::MetaRegistration< PointT, Scalar >
	Meta Registration class. More...
class	pcl::PairwiseGraphRegistration< GraphT, PointT >
	PairwiseGraphRegistration class aligns the clouds two by two More...
class	pcl::Registration< PointSource, PointTarget, Scalar >
	Registration represents the base registration class for general purpose, ICP-like methods. More...
class	pcl::SampleConsensusPrerejective< PointSource, PointTarget, FeatureT >
	Pose estimation and alignment class using a prerejective RANSAC routine. More...
class	pcl::registration::TransformationEstimation< PointSource, PointTarget, Scalar >
	TransformationEstimation represents the base class for methods for transformation estimation based on: More...
class	pcl::registration::TransformationEstimation2D< PointSource, PointTarget, Scalar >
	TransformationEstimation2D implements a simple 2D rigid transformation estimation (x, y, theta) for a given pair of datasets. More...
class	pcl::registration::TransformationEstimation3Point< PointSource, PointTarget, Scalar >
	TransformationEstimation3Points represents the class for transformation estimation based on: More...
class	pcl::registration::TransformationEstimationDQ< PointSource, PointTarget, Scalar >
	TransformationEstimationDQ implements dual quaternion based estimation of the transformation aligning the given correspondences. More...
class	pcl::registration::TransformationEstimationDualQuaternion< PointSource, PointTarget, Scalar >
	TransformationEstimationDualQuaternion implements dual quaternion based estimation of the transformation aligning the given correspondences. More...
class	pcl::registration::TransformationEstimationLM< PointSource, PointTarget, MatScalar >
	TransformationEstimationLM implements Levenberg Marquardt-based estimation of the transformation aligning the given correspondences. More...
class	pcl::registration::TransformationEstimationPointToPlane< PointSource, PointTarget, Scalar >
	TransformationEstimationPointToPlane uses Levenberg Marquardt optimization to find the transformation that minimizes the point-to-plane distance between the given correspondences. More...
class	pcl::registration::TransformationEstimationPointToPlaneLLS< PointSource, PointTarget, Scalar >
	TransformationEstimationPointToPlaneLLS implements a Linear Least Squares (LLS) approximation for minimizing the point-to-plane distance between two clouds of corresponding points with normals. More...
class	pcl::registration::TransformationEstimationPointToPlaneLLSWeighted< PointSource, PointTarget, Scalar >
	TransformationEstimationPointToPlaneLLSWeighted implements a Linear Least Squares (LLS) approximation for minimizing the point-to-plane distance between two clouds of corresponding points with normals, with the possibility of assigning weights to the correspondences. More...
class	pcl::registration::TransformationEstimationPointToPlaneWeighted< PointSource, PointTarget, MatScalar >
	TransformationEstimationPointToPlaneWeighted uses Levenberg Marquardt optimization to find the transformation that minimizes the point-to-plane distance between the given correspondences. More...
class	pcl::registration::TransformationEstimationSVD< PointSource, PointTarget, Scalar >
	TransformationEstimationSVD implements SVD-based estimation of the transformation aligning the given correspondences. More...
class	pcl::registration::TransformationEstimationSVDScale< PointSource, PointTarget, Scalar >
	TransformationEstimationSVD implements SVD-based estimation of the transformation aligning the given correspondences. More...
class	pcl::registration::TransformationEstimationSymmetricPointToPlaneLLS< PointSource, PointTarget, Scalar >
	TransformationEstimationSymmetricPointToPlaneLLS implements a Linear Least Squares (LLS) approximation for minimizing the symmetric point-to-plane distance between two clouds of corresponding points with normals. More...
class	pcl::registration::TransformationValidation< PointSource, PointTarget, Scalar >
	TransformationValidation represents the base class for methods that validate the correctness of a transformation found through TransformationEstimation. More...
class	pcl::registration::TransformationValidationEuclidean< PointSource, PointTarget, Scalar >
	TransformationValidationEuclidean computes an L2SQR norm between a source and target dataset. More...
struct	pcl::registration::NullEstimate
	NullEstimate struct More...
struct	pcl::registration::PoseEstimate< PointT >
	PoseEstimate struct More...
class	pcl::registration::WarpPointRigid< PointSourceT, PointTargetT, Scalar >
	Base warp point class. More...
class	pcl::registration::WarpPointRigid3D< PointSourceT, PointTargetT, Scalar >
	WarpPointRigid3D enables 3D (1D rotation + 2D translation) transformations for points. More...
class	pcl::registration::WarpPointRigid6D< PointSourceT, PointTargetT, Scalar >
	WarpPointRigid3D enables 6D (3D rotation + 3D translation) transformations for points. More...