Package boofcv.factory.disparity

Class FactoryStereoDisparity

java.lang.Object

boofcv.factory.disparity.FactoryStereoDisparity

public class FactoryStereoDisparity
extends Object

Creates high level interfaces for computing the disparity between two rectified stereo images. Algorithms which select the best disparity for each region independent of all the others are referred to as Winner Takes All (WTA) in the literature. Dense algorithms compute the disparity for the whole image while sparse algorithms do it in a per pixel basis as requested.

Typically disparity calculations with regions will produce less erratic results, but their precision will be decreased. This is especially evident along the border of objects. Computing a wider range of disparities can better results, but is very computationally expensive.

Dense vs Sparse. Here dense refers to computing the disparity across the whole image at once. Sparse refers to computing the disparity for a single pixel at a time as requested by the user,

Constructor Summary

Constructors

Constructor	Description
FactoryStereoDisparity()

Method Summary

Modifier and Type	Method	Description
static <T extends ImageGray<T>, DI extends ImageGray<DI>> StereoDisparity<T,DI>	blockMatch(@Nullable ConfigDisparityBM config, Class<T> imageType, Class<DI> dispType)
static <T extends ImageGray<T>, DI extends ImageGray<DI>> StereoDisparity<T,DI>	blockMatchBest5(@Nullable ConfigDisparityBMBest5 config, Class<T> imageType, Class<DI> dispType)
static <T extends ImageGray<T>> DisparityBlockMatchRowFormat	createBestFive(ConfigDisparityBM config, Class<T> imageType, DisparitySelect select, BlockRowScore rowScore)
static <T extends ImageGray<T>> DisparityBlockMatchRowFormat	createBlockMatching(ConfigDisparityBM config, Class<T> imageType, DisparitySelect select, BlockRowScore rowScore)
static BlockRowScore	createCensusRowScore(ConfigDisparityBM config, FilterImageInterface censusTran)
static <T extends ImageGray<T>> DisparitySelect	createDisparitySelect(ConfigDisparityBM config, Class<T> imageType, int maxError)
static <T extends ImageGray<T>> BlockRowScore	createScoreRowNcc(ConfigDisparityBM config, Class<T> imageType)
static <T extends ImageGray<T>> BlockRowScore	createScoreRowSad(ConfigDisparityBM config, Class<T> imageType)
static <T extends ImageGray<T>, DI extends ImageGray<DI>> StereoDisparity<T,DI>	generic(ConfigDisparity config, Class<T> imageType)
static <T extends ImageGray<T>, DI extends ImageGray<DI>> StereoDisparity<T,DI>	generic(ConfigDisparity config, Class<T> imageType, Class<DI> dispType)	Function for creating any dense stereo disparity algorithm in BoofCV
static <T extends ImageGray<T>, DI extends ImageGray<DI>> DisparitySmoother<T,DI>	removeSpeckle(@Nullable ConfigSpeckleFilter config, Class<DI> dispType)	Post processing filter the removes small regions from disparity image
static <T extends ImageGray<T>, DI extends ImageGray<DI>> StereoDisparity<T,DI>	sgm(@Nullable ConfigDisparitySGM config, Class<T> imageType, Class<DI> dispType)	Disparity computed using Semi Global Matching (SGM)
static <T extends ImageGray<T>> StereoDisparitySparse<T>	sparseRectifiedBM(ConfigDisparityBM config, Class<T> imageType)

Methods inherited from class java.lang.Object

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

Constructor Details

FactoryStereoDisparity

public FactoryStereoDisparity()

Method Details

generic

public static <T extends ImageGray<T>,
DI extends ImageGray<DI>>
StereoDisparity<T,DI> generic(ConfigDisparity config,
 Class<T> imageType,
 Class<DI> dispType)

Function for creating any dense stereo disparity algorithm in BoofCV

generic

public static <T extends ImageGray<T>,
DI extends ImageGray<DI>>
StereoDisparity<T,DI> generic(ConfigDisparity config,
 Class<T> imageType)

blockMatch

public static <T extends ImageGray<T>,
DI extends ImageGray<DI>>
StereoDisparity<T,DI> blockMatch(@Nullable
 @Nullable ConfigDisparityBM config,
 Class<T> imageType,
 Class<DI> dispType)

createCensusRowScore

public static BlockRowScore createCensusRowScore(ConfigDisparityBM config,
 FilterImageInterface censusTran)

createDisparitySelect

public static <T extends ImageGray<T>>
DisparitySelect createDisparitySelect(ConfigDisparityBM config,
 Class<T> imageType,
 int maxError)

blockMatchBest5

public static <T extends ImageGray<T>,
DI extends ImageGray<DI>>
StereoDisparity<T,DI> blockMatchBest5(@Nullable
 @Nullable ConfigDisparityBMBest5 config,
 Class<T> imageType,
 Class<DI> dispType)

createScoreRowSad

public static <T extends ImageGray<T>>
BlockRowScore createScoreRowSad(ConfigDisparityBM config,
 Class<T> imageType)

createScoreRowNcc

public static <T extends ImageGray<T>>
BlockRowScore createScoreRowNcc(ConfigDisparityBM config,
 Class<T> imageType)

createBlockMatching

public static <T extends ImageGray<T>>
DisparityBlockMatchRowFormat createBlockMatching(ConfigDisparityBM config,
 Class<T> imageType,
 DisparitySelect select,
 BlockRowScore rowScore)

createBestFive

public static <T extends ImageGray<T>>
DisparityBlockMatchRowFormat createBestFive(ConfigDisparityBM config,
 Class<T> imageType,
 DisparitySelect select,
 BlockRowScore rowScore)

sparseRectifiedBM

public static <T extends ImageGray<T>>
StereoDisparitySparse<T> sparseRectifiedBM(ConfigDisparityBM config,
 Class<T> imageType)

sgm

public static <T extends ImageGray<T>,
DI extends ImageGray<DI>>
StereoDisparity<T,DI> sgm(@Nullable
 @Nullable ConfigDisparitySGM config,
 Class<T> imageType,
 Class<DI> dispType)

Disparity computed using Semi Global Matching (SGM)

Parameters:

config - Configuration for SGM

imageType - Type of input image

dispType - Type of disparity image. F32 is sub-pixel is turned on, U8 otherwise

Returns:

The algorithm.

removeSpeckle

public static <T extends ImageGray<T>,
DI extends ImageGray<DI>>
DisparitySmoother<T,DI> removeSpeckle(@Nullable
 @Nullable ConfigSpeckleFilter config,
 Class<DI> dispType)

Post processing filter the removes small regions from disparity image