imagingbook.pub.lucaskanade

Class LucasKanadeMatcher

java.lang.Object

imagingbook.pub.lucaskanade.LucasKanadeMatcher

Direct Known Subclasses:

LucasKanadeForwardMatcher, LucasKanadeInverseMatcher

public abstract class LucasKanadeMatcher
extends Object

This is the common super-class for different variants of the Lucas-Kanade matcher.

Version:

2014/02/08

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	LucasKanadeMatcher.Parameters Default parameters for the containing class and its sub-classes; a (usually modified) instance of this class is passed to the constructor of a non-abstract sub-class.

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	LucasKanadeMatcher(ij.process.FloatProcessor I, ij.process.FloatProcessor R, LucasKanadeMatcher.Parameters params) Creates a new Lucas-Kanade-type matcher.

Method Summary

Modifier and Type	Method and Description
int	getIteration()
ProjectiveMapping	getMatch(ProjectiveMapping Tinit) Performs the full optimization on the given image pair (I, R).
ProjectiveMapping	getReferenceMappingTo(Point2D[] Q) Calculates the transformation that maps the reference image R (centered around the origin) to the given quad Q.
Point2D[]	getReferencePoints()
abstract double	getRmsError() Measures the RMS intensity difference between the reference image R and the patch in the search image I defined by the current warp Tp.
protected ij.process.FloatProcessor	gradientX(ij.process.FloatProcessor fp)
protected ij.process.FloatProcessor	gradientY(ij.process.FloatProcessor fp)
abstract boolean	hasConverged() Checks if the matcher has converged.
abstract ProjectiveMapping	iterateOnce(ProjectiveMapping Tp) Performs a single matching iteration on the given image pair (I, R).
protected void	showSteepestDescentImages(double[][][] S)

Methods inherited from class java.lang.Object

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

Constructor Detail

LucasKanadeMatcher

protected LucasKanadeMatcher(ij.process.FloatProcessor I,
                             ij.process.FloatProcessor R,
                             LucasKanadeMatcher.Parameters params)

Creates a new Lucas-Kanade-type matcher.

Parameters:

I - the search image (of type FloatProcessor).

R - the reference image (of type FloatProcessor)

params - a parameter object of type LucasKanadeMatcher.Parameters.

Method Detail

getReferenceMappingTo

public ProjectiveMapping getReferenceMappingTo(Point2D[] Q)

Calculates the transformation that maps the reference image R (centered around the origin) to the given quad Q.

Parameters:

Q - an arbitrary quad (should be inside the search image I);

Returns:

the transformation from R's bounding rectangle to Q.

getReferencePoints

public Point2D[] getReferencePoints()

Returns:

the corner points of the bounding rectangle of R, centered at the origin.

getMatch

public ProjectiveMapping getMatch(ProjectiveMapping Tinit)

Performs the full optimization on the given image pair (I, R).

Parameters:

Tinit - the transformation from the reference image R to the initial search patch, assuming that R is centered at the coordinate origin!

Returns:

the transformation to the best-matching patch in the search image I (again assuming that R is centered at the coordinate origin) or null if no match was found.

iterateOnce

public abstract ProjectiveMapping iterateOnce(ProjectiveMapping Tp)

Performs a single matching iteration on the given image pair (I, R).

Parameters:

Tp - the warp transformation from the reference image R to the initial search patch, assuming that R is centered at the coordinate origin!

Returns:

a new warp transformation (again assuming that R is centered at the coordinate origin) or null if the iteration was unsuccessful.

hasConverged

public abstract boolean hasConverged()

Checks if the matcher has converged.

Returns:

true if minimization criteria have been reached.

getRmsError

public abstract double getRmsError()

Measures the RMS intensity difference between the reference image R and the patch in the search image I defined by the current warp Tp.

Returns:

the RMS error under the current warp

getIteration

public int getIteration()

gradientX

protected ij.process.FloatProcessor gradientX(ij.process.FloatProcessor fp)

gradientY

protected ij.process.FloatProcessor gradientY(ij.process.FloatProcessor fp)

showSteepestDescentImages

protected void showSteepestDescentImages(double[][][] S)