Package boofcv.alg.disparity.block

Class SparseScoreRectifiedNcc<T extends ImageGray<T>>

java.lang.Object

boofcv.alg.disparity.block.score.DisparitySparseRectifiedScoreBM<float[],T>

boofcv.alg.disparity.block.SparseScoreRectifiedNcc<T>

public class SparseScoreRectifiedNcc<T extends ImageGray<T>>
extends DisparitySparseRectifiedScoreBM<float[],T>

Compute NCC error for sparse disparity. Should produce similar results to dense version. Image normalization is computed using local statistics instead of global statistics across input image.

Field Summary

Fields

Modifier and Type	Field	Description
float	eps
boolean	normalizeInput
protected float[]	scoreLtoR
protected float[]	scoreRtoL
boofcv.alg.disparity.block.SparseScoreRectifiedNcc.SparseStatistics	statsLeft
boofcv.alg.disparity.block.SparseScoreRectifiedNcc.SparseStatistics	statsRight

Fields inherited from class boofcv.alg.disparity.block.score.DisparitySparseRectifiedScoreBM

blockHeight, blockWidth, border, disparityMax, disparityMin, disparityRange, inputType, left, localRangeLtoR, localRangeRtoL, patchCompare, patchTemplate, radiusX, radiusY, right, sampledHeight, sampledWidth, sampleRadiusX, sampleRadiusY

Constructor Summary

Constructors

Constructor	Description
SparseScoreRectifiedNcc(int blockRadiusX, int blockRadiusY, Class<T> imageType)

Method Summary

Modifier and Type	Method	Description
void	configure(int disparityMin, int disparityRange)	Configures the disparity search
protected void	scoreDisparity(int disparityRange, boolean leftToRight)	Scores the disparity using image patches.

Methods inherited from class boofcv.alg.disparity.block.score.DisparitySparseRectifiedScoreBM

copy, getScoreLtoR, getScoreRtoL, processLeftToRight, processRightToLeft, setBorder, setImages, setSampleRegion

Methods inherited from class java.lang.Object

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

Field Details

statsLeft

public final boofcv.alg.disparity.block.SparseScoreRectifiedNcc.SparseStatistics statsLeft

statsRight

public final boofcv.alg.disparity.block.SparseScoreRectifiedNcc.SparseStatistics statsRight

eps

public float eps

normalizeInput

public boolean normalizeInput

scoreLtoR

protected float[] scoreLtoR

scoreRtoL

protected float[] scoreRtoL

Constructor Details

SparseScoreRectifiedNcc

public SparseScoreRectifiedNcc(int blockRadiusX,
int blockRadiusY,
Class<T> imageType)

Method Details

configure

public void configure(int disparityMin,
int disparityRange)

Description copied from class: DisparitySparseRectifiedScoreBM

Configures the disparity search

Overrides:

configure in class DisparitySparseRectifiedScoreBM<float[],T extends ImageGray<T>>

Parameters:

disparityMin - Minimum disparity that it will check. Must be ≥ 0 and < disparityMax

disparityRange - Number of possible disparity values estimated. The max possible disparity is min+range-1.

scoreDisparity

protected void scoreDisparity(int disparityRange,
boolean leftToRight)

Description copied from class: DisparitySparseRectifiedScoreBM

Scores the disparity using image patches.

Specified by:

scoreDisparity in class DisparitySparseRectifiedScoreBM<float[],T extends ImageGray<T>>

Parameters:

disparityRange - The local range for disparity

leftToRight - If true then the disparity is being from in left to right direction (the typical)