/tmp/B.s_fpak9v/BUILD/pcl-1.15.1-build/pcl-pcl-1.15.1/registration/registration.doxy

/**
  \addtogroup registration Module registration

  \section secRegistrationPresentation 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 <b>pcl_registration</b> library implements a plethora of point cloud
registration algorithms for both organized and unorganized (general purpose)
datasets.

PCL's methods to register one point cloud to another can be divided into two groups: the first group needs an initial guess of the transformation (pcl::IterativeClosestPoint, pcl::IterativeClosestPointWithNormals, pcl::IterativeClosestPointNonLinear, pcl::GeneralizedIterativeClosestPoint, pcl::GeneralizedIterativeClosestPoint6D, pcl::NormalDistributionsTransform, pcl::NormalDistributionsTransform2D), and the second group does not need a guess but is usually slower and less accurate (pcl::registration::FPCSInitialAlignment, pcl::registration::KFPCSInitialAlignment, pcl::SampleConsensusInitialAlignment, pcl::SampleConsensusPrerejective, pcl::PPFRegistration). Many parts of the registration process can be configured and swapped out, like the correspondence estimation, correspondence rejection, or the transformation estimation. And finally, PCL also has methods if there are more than two point clouds to align (pcl::registration::ELCH, pcl::registration::LUM, pcl::PairwiseGraphRegistration, pcl::registration::IncrementalRegistration, pcl::registration::MetaRegistration).

\image html http://www.pointclouds.org/assets/images/contents/documentation/registration_outdoor.png
\image html http://www.pointclouds.org/assets/images/contents/documentation/registration_closeup.png

  \section secRegistrationRequirements Requirements
  - \ref common "common"
  - \ref kdtree "kdtree"
  - \ref sample_consensus "sample_consensus"
  - \ref features "features"

*/