pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar > Class Template Reference
[Module registration]

IterativeClosestPointNonLinear is an ICP variant that uses Levenberg-Marquardt optimization backend. More...

#include <pcl/registration/icp_nl.h>

Inheritance diagram for pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >:

[legend]

Collaboration diagram for pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >:

[legend]

List of all members.

Public Types
typedef boost::shared_ptr < IterativeClosestPointNonLinear < PointSource, PointTarget, Scalar > >	Ptr
typedef boost::shared_ptr < const IterativeClosestPointNonLinear < PointSource, PointTarget, Scalar > >	ConstPtr
typedef Registration < PointSource, PointTarget, Scalar >::Matrix4	Matrix4
Public Member Functions
	IterativeClosestPointNonLinear ()
	Empty constructor.

---

Detailed Description

template<typename PointSource, typename PointTarget, typename Scalar = float>
class pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >

IterativeClosestPointNonLinear is an ICP variant that uses Levenberg-Marquardt optimization backend.

The resultant transformation is optimized as a quaternion.

The algorithm has several termination criteria:

1. Number of iterations has reached the maximum user imposed number of iterations (via setMaximumIterations)
2. The epsilon (difference) between the previous transformation and the current estimated transformation is smaller than an user imposed value (via setTransformationEpsilon)
3. The sum of Euclidean squared errors is smaller than a user defined threshold (via setEuclideanFitnessEpsilon)

Author:

Radu B. Rusu, Michael Dixon

Definition at line 68 of file icp_nl.h.

---

Member Typedef Documentation

template<typename PointSource , typename PointTarget , typename Scalar = float>

typedef boost::shared_ptr< const IterativeClosestPointNonLinear<PointSource, PointTarget, Scalar> > pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >::ConstPtr

Reimplemented from pcl::IterativeClosestPoint< PointSource, PointTarget, Scalar >.

Definition at line 78 of file icp_nl.h.

template<typename PointSource , typename PointTarget , typename Scalar = float>

typedef Registration<PointSource, PointTarget, Scalar>::Matrix4 pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >::Matrix4

Reimplemented from pcl::IterativeClosestPoint< PointSource, PointTarget, Scalar >.

Definition at line 80 of file icp_nl.h.

template<typename PointSource , typename PointTarget , typename Scalar = float>

typedef boost::shared_ptr< IterativeClosestPointNonLinear<PointSource, PointTarget, Scalar> > pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >::Ptr

Reimplemented from pcl::IterativeClosestPoint< PointSource, PointTarget, Scalar >.

Definition at line 77 of file icp_nl.h.

---

Constructor & Destructor Documentation

template<typename PointSource , typename PointTarget , typename Scalar = float>

pcl::IterativeClosestPointNonLinear< PointSource, PointTarget, Scalar >::IterativeClosestPointNonLinear

(

)

[inline]

Empty constructor.

Definition at line 83 of file icp_nl.h.

References pcl::Registration< PointSource, PointTarget, Scalar >::min_number_correspondences_, pcl::Registration< PointSource, PointTarget, Scalar >::reg_name_, and pcl::Registration< PointSource, PointTarget, Scalar >::transformation_estimation_.

---

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

• /builddir/build/BUILD/pcl-pcl-1.7.1/registration/include/pcl/registration/icp_nl.h