Package org.openimaj.math.geometry.transforms

Interface Summary

Interface	Description
MatrixTransformProvider	Interface for classes implementing a model of a matrix transformation.

Class Summary

Class	Description
AffineTransformModel	Concrete implementation of a model of an Affine transform.
AffineTransformModel3d	Concrete implementation of a model of an Affine transform.
FundamentalModel	Implementation of a Fundamental matrix model that estimates the epipolar geometry.
FundamentalModel.EpipolarResidual	Geometric residual that sums the distance of points from the closest epipolar line.
FundamentalModel.Fundamental8PtResidual	Computes the algebraic residual of the point pairs applied to the F matrix
FundamentalModel.SampsonGeometricResidual	ResidualCalculator based on Sampson's geometric error.
FundamentalRefinement.Base
FundamentalRefinement.F12Epipolar	Based on the following matlab:
FundamentalRefinement.F12Sampson	Based on the following matlab:
FundamentalRefinement.F13Epipolar	Based on the following matlab:
FundamentalRefinement.F13Sampson	Based on the following matlab:
FundamentalRefinement.F23Epipolar	Based on the following matlab:
FundamentalRefinement.F23Sampson	Based on the following matlab:
FundamentalRefinement.FastSolveNormal3x2
HomographyModel	Implementation of a Homogeneous Homography model - a transform that models the relationship between planes under projective constraints (8 D.o.F)
NullModel<T>	A NullModel models a one-to-one mapping of data.
RigidTransformModel3d	Concrete implementation of a model of a 3D rigid transform with only rotation and translation allowed.
TransformUtilities	A collection of static methods for creating transform matrices.

Enum Summary

Enum	Description
FundamentalRefinement	Refinement of fundamental matrix estimates using non-linear optimisation (Levenberg-Marquardt) under different geometric distance/error assumptions.
FundamentalRefinement.Parameterisation	Parameterisations of the fundamental matrix that preserve the rank-2 constraint by writing one of the rows as a weighted combination of the other two.
HomographyRefinement	Refinement of homographies estimates using non-linear optimisation (Levenberg-Marquardt) under different geometric distance/error assumptions.