Package net.preibisch.mvrecon.process.fusion.intensity.mpicbg

Class FastAffineModel1D

java.lang.Object

mpicbg.models.AbstractModel<mpicbg.models.AffineModel1D>

mpicbg.models.AbstractAffineModel1D<mpicbg.models.AffineModel1D>

mpicbg.models.AffineModel1D

net.preibisch.mvrecon.process.fusion.intensity.mpicbg.FastAffineModel1D

All Implemented Interfaces:

Serializable, mpicbg.models.Affine1D<mpicbg.models.AffineModel1D>, mpicbg.models.Boundable, mpicbg.models.CoordinateTransform, mpicbg.models.InverseBoundable, mpicbg.models.InverseCoordinateTransform, mpicbg.models.InvertibleBoundable, mpicbg.models.InvertibleCoordinateTransform, mpicbg.models.Model<mpicbg.models.AffineModel1D>

public class FastAffineModel1D
extends mpicbg.models.AffineModel1D

See Also:

• Serialized Form

Field Summary

Fields inherited from class mpicbg.models.AffineModel1D

i00, i01, isInvertible, m00, m01, MIN_NUM_MATCHES

Fields inherited from class mpicbg.models.AbstractModel

cost, rnd

Constructor Summary

Constructors

Constructor	Description
FastAffineModel1D()

Method Summary

Modifier and Type	Method	Description
double	apply(double l)
FastAffineModel1D	copy()
MatchIndices	fastFilterRansac(FlattenedMatches candidates, int iterations, double maxEpsilon, double minInlierRatio, int minNumInliers, double maxTrust)	Estimate a AffineModel1D from a set with many outliers by first filtering the worst outliers with RANSAC and filter potential outliers by robust iterative regression.
void	fit(FlattenedMatches matches)

Methods inherited from class mpicbg.models.AffineModel1D

apply, applyInPlace, applyInverse, applyInverseInPlace, concatenate, createInverse, fit, fit, fit, getMatrix, getMinNumMatches, invert, preConcatenate, reset, set, set, set, toArray, toMatrix, toString

Methods inherited from class mpicbg.models.AbstractAffineModel1D

estimateBounds, estimateInverseBounds

Methods inherited from class mpicbg.models.AbstractModel

betterThan, filter, filter, filter, filterRansac, filterRansac, filterRansac, filterRansac, getCost, icp, localSmoothnessFilter, ransac, ransac, setCost, test, test

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface mpicbg.models.Boundable

estimateBounds

Methods inherited from interface mpicbg.models.InverseBoundable

estimateInverseBounds

Constructor Details

FastAffineModel1D

public FastAffineModel1D()

Method Details

copy

public FastAffineModel1D copy()

Specified by:

copy in interface mpicbg.models.Model<mpicbg.models.AffineModel1D>

Overrides:

copy in class mpicbg.models.AffineModel1D

fit

public void fit(FlattenedMatches matches)
         throws mpicbg.models.NotEnoughDataPointsException,
mpicbg.models.IllDefinedDataPointsException

Throws:

mpicbg.models.NotEnoughDataPointsException

mpicbg.models.IllDefinedDataPointsException

fastFilterRansac

public MatchIndices fastFilterRansac(FlattenedMatches candidates,
 int iterations,
 double maxEpsilon,
 double minInlierRatio,
 int minNumInliers,
 double maxTrust)
                              throws mpicbg.models.NotEnoughDataPointsException

Estimate a AffineModel1D from a set with many outliers by first filtering the worst outliers with RANSAC and filter potential outliers by robust iterative regression.

Parameters:

candidates - candidate data points including (many) outliers

iterations - number of RANSAC iterations

maxEpsilon - maximal allowed transfer error

minInlierRatio - minimal number of inliers to number of candidates

minNumInliers - minimally required absolute number of inliers

maxTrust - reject candidates with a cost larger than maxTrust * median cost

Returns:

indices of candidates that are inliers, or null if the model could not be fitted (this model remains unchanged in that case).

Throws:

mpicbg.models.NotEnoughDataPointsException

apply

public double apply(double l)