mpi.cbg.fly
Class TRModel2D

java.lang.Object
  mpi.cbg.fly.Model
      mpi.cbg.fly.TRModel2D

public class TRModel2D
extends Model

Field Summary

static int

MIN_SET_SIZE

Fields inherited from class mpi.cbg.fly.Model

error

Constructor Summary

TRModel2D()

Method Summary

float[]	apply(float[] point) apply the model to a point location
void	applyInPlace(float[] point) apply the model to a point location
float[]	applyInverse(float[] point) apply the inverse of the model to a point location
void	applyInverseInPlace(float[] point) apply the inverse of the model to a point location
TRModel2D	clone() clone
void	concatenate(TRModel2D model)
static TRModel2D	estimateBestModel(java.util.List<PointMatch> candidates, java.util.Collection<PointMatch> inliers, float min_epsilon, float max_epsilon, float min_inlier_ratio) estimate the transformation model for a set of feature correspondences containing a high number of outliers using RANSAC increase the error as long as not more inliers occur
static TRModel2D	estimateModel(java.util.List<PointMatch> candidates, java.util.Collection<PointMatch> inliers, int iterations, float epsilon, float min_inlier_ratio) estimate the transformation model for a set of feature correspondences containing a high number of outliers using RANSAC
boolean	fit(PointMatch[] min_matches) fit the model to a minimal set of point correpondences estimates a model to transform match.p2.local to match.p1.world
java.awt.geom.AffineTransform	getAffine()
void	minimize(java.util.Collection<PointMatch> matches)
void	preConcatenate(TRModel2D model)
void	shake(java.util.Collection<PointMatch> matches, float scale, float[] center) change the model a bit estimates the necessary amount of shaking for each single dimensional distance in the set of matches
java.lang.String	toString() string to output stream

Methods inherited from class mpi.cbg.fly.Model

betterThan, test

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

MIN_SET_SIZE

public static final int MIN_SET_SIZE

See Also:

Constant Field Values

Constructor Detail

TRModel2D

public TRModel2D()

Method Detail

getAffine

public java.awt.geom.AffineTransform getAffine()

Specified by:

getAffine in class Model

apply

public float[] apply(float[] point)

Description copied from class: Model

apply the model to a point location

Specified by:

apply in class Model

Returns:

transformed point

applyInPlace

public void applyInPlace(float[] point)

Description copied from class: Model

apply the model to a point location

Specified by:

applyInPlace in class Model

applyInverse

public float[] applyInverse(float[] point)

Description copied from class: Model

apply the inverse of the model to a point location

Specified by:

applyInverse in class Model

Returns:

transformed point

applyInverseInPlace

public void applyInverseInPlace(float[] point)

Description copied from class: Model

apply the inverse of the model to a point location

Specified by:

applyInverseInPlace in class Model

fit

public boolean fit(PointMatch[] min_matches)

Description copied from class: Model

fit the model to a minimal set of point correpondences estimates a model to transform match.p2.local to match.p1.world

Specified by:

fit in class Model

Parameters:

min_matches - minimal set of point correpondences

Returns:

true if a model was estimated

toString

public java.lang.String toString()

Description copied from class: Model

string to output stream

Specified by:

toString in class Model

minimize

public void minimize(java.util.Collection<PointMatch> matches)

Specified by:

minimize in class Model

shake

public final void shake(java.util.Collection<PointMatch> matches,
                        float scale,
                        float[] center)

change the model a bit estimates the necessary amount of shaking for each single dimensional distance in the set of matches

Specified by:

shake in class Model

Parameters:

matches - point matches

scale - gives a multiplicative factor to each dimensional distance (increases the amount of shaking)

center - local pivot point

estimateModel

public static TRModel2D estimateModel(java.util.List<PointMatch> candidates,
                                      java.util.Collection<PointMatch> inliers,
                                      int iterations,
                                      float epsilon,
                                      float min_inlier_ratio)

estimate the transformation model for a set of feature correspondences containing a high number of outliers using RANSAC

Parameters:

candidates - set of correspondence candidates

inliers - set ot correspondences that fit the finally estimated model if any

iterations - number of iterations

epsilon - maximally allowed displacement

min_inlier_ratio - minimal amount of inliers

Returns:

TRModel2D or null Bibtex reference:

estimateBestModel

public static TRModel2D estimateBestModel(java.util.List<PointMatch> candidates,
                                          java.util.Collection<PointMatch> inliers,
                                          float min_epsilon,
                                          float max_epsilon,
                                          float min_inlier_ratio)

estimate the transformation model for a set of feature correspondences containing a high number of outliers using RANSAC increase the error as long as not more inliers occur

clone

public TRModel2D clone()

Description copied from class: Model

clone

Specified by:

clone in class Model

preConcatenate

public void preConcatenate(TRModel2D model)

concatenate

public void concatenate(TRModel2D model)