template<typename PointSource, typename PointTarget>
class pcl::IterativeClosestPointNonLinear< PointSource, PointTarget >
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:
Number of iterations has reached the maximum user imposed number of iterations (via setMaximumIterations)
The epsilon (difference) between the previous transformation and the current estimated transformation is smaller than an user imposed value (via setTransformationEpsilon)
The sum of Euclidean squared errors is smaller than a user defined threshold (via setEuclideanFitnessEpsilon)
- Radu Bogdan Rusu, Michael Dixon
Definition at line 67 of file icp_nl.h.