It generates random rotations in three-dimensional space that follow a probability distribution, matrix Fisher distribution, arising in fitting and matching problem.
An arbitrary 3 x 3 matrix represents the parameter matrix of this distribution.
Firstly rotation matrices X are chosen which are the closest to F, and then parameterized using euler angles. Then a Gibbs sampling algorithm is implemented to generate rotation matrices from the resulting disribution of the euler angles.
A simulated rotation matrix.
R implementation and documentation: Anamul Sajib<firstname.lastname@example.org>
Habeck M (2009). Generation of three-dimensional random rotations in fitting and matching problems. Computational Statistics, 24, 719–731.
1 2 3