Stereo Correspondance Algorithms

Classes
struct	cv::stereo::Match
struct	cv::stereo::PropagationParameters
class	cv::stereo::QuasiDenseStereo
	Class containing the methods needed for Quasi Dense Stereo computation. More...
class	cv::stereo::StereoBinaryBM
	Class for computing stereo correspondence using the block matching algorithm, introduced and contributed to OpenCV by K. Konolige. More...
class	cv::stereo::StereoBinarySGBM
	The class implements the modified H. Hirschmuller algorithm. More...
class	cv::stereo::StereoMatcher
	Filters off small noise blobs (speckles) in the disparity map. More...

Enumerations
enum	{   cv::stereo::CV_SPECKLE_REMOVAL_ALGORITHM,   cv::stereo::CV_SPECKLE_REMOVAL_AVG_ALGORITHM }
	speckle removal algorithms. These algorithms have the purpose of removing small regions More...
enum	{   cv::stereo::CV_QUADRATIC_INTERPOLATION,   cv::stereo::CV_SIMETRICV_INTERPOLATION }
	subpixel interpolationm methods for disparities. More...

Functions
virtual	cv::stereo::QuasiDenseStereo::~QuasiDenseStereo ()=0
	destructor Method to free all the memory allocated by matrices and vectors in this class.
static cv::Ptr< QuasiDenseStereo >	cv::stereo::QuasiDenseStereo::create (cv::Size monoImgSize, cv::String paramFilepath=cv::String())
virtual void	cv::stereo::QuasiDenseStereo::getDenseMatches (std::vector< stereo::Match > &denseMatches)=0
	Get The dense corresponding points.
virtual cv::Mat	cv::stereo::QuasiDenseStereo::getDisparity (uint8_t disparityLvls=50)=0
	Compute and return the disparity map based on the correspondences found in the "process" method.
virtual cv::Point2f	cv::stereo::QuasiDenseStereo::getMatch (const int x, const int y)=0
	Specify pixel coordinates in the left image and get its corresponding location in the right image.
virtual void	cv::stereo::QuasiDenseStereo::getSparseMatches (std::vector< stereo::Match > &sMatches)=0
	Get The sparse corresponding points.
virtual int	cv::stereo::QuasiDenseStereo::loadParameters (cv::String filepath)=0
	Load a file containing the configuration parameters of the class.
bool	cv::stereo::Match::operator< (const Match &rhs) const
virtual void	cv::stereo::QuasiDenseStereo::process (const cv::Mat &imgLeft, const cv::Mat &imgRight)=0
	Main process of the algorithm. This method computes the sparse seeds and then densifies them.
virtual int	cv::stereo::QuasiDenseStereo::saveParameters (cv::String filepath)=0
	Save a file containing all the configuration parameters the class is currently set to.

Variables
int	cv::stereo::PropagationParameters::borderX
int	cv::stereo::PropagationParameters::borderY
float	cv::stereo::Match::corr
float	cv::stereo::PropagationParameters::correlationThreshold
int	cv::stereo::PropagationParameters::corrWinSizeX
int	cv::stereo::PropagationParameters::corrWinSizeY
int	cv::stereo::PropagationParameters::disparityGradient
int	cv::stereo::PropagationParameters::gftMaxNumFeatures
int	cv::stereo::PropagationParameters::gftMinSeperationDist
float	cv::stereo::PropagationParameters::gftQualityThres
int	cv::stereo::PropagationParameters::lkPyrLvl
int	cv::stereo::PropagationParameters::lkTemplateSize
int	cv::stereo::PropagationParameters::lkTermParam1
float	cv::stereo::PropagationParameters::lkTermParam2
int	cv::stereo::PropagationParameters::neighborhoodSize
cv::Point2i	cv::stereo::Match::p0
cv::Point2i	cv::stereo::Match::p1
PropagationParameters	cv::stereo::QuasiDenseStereo::Param
float	cv::stereo::PropagationParameters::textrureThreshold

Detailed Description

Enumeration Type Documentation

anonymous enum

speckle removal algorithms. These algorithms have the purpose of removing small regions

Enumerator
CV_SPECKLE_REMOVAL_ALGORITHM
CV_SPECKLE_REMOVAL_AVG_ALGORITHM

anonymous enum

subpixel interpolationm methods for disparities.

Enumerator
CV_QUADRATIC_INTERPOLATION
CV_SIMETRICV_INTERPOLATION

Function Documentation

virtual cv::stereo::QuasiDenseStereo::~QuasiDenseStereo ( )

pure virtual

destructor Method to free all the memory allocated by matrices and vectors in this class.

static cv::Ptr<QuasiDenseStereo> cv::stereo::QuasiDenseStereo::create ( cv::Size  monoImgSize, cv::String  paramFilepath = cv::String()  )

static

virtual void cv::stereo::QuasiDenseStereo::getDenseMatches ( std::vector< stereo::Match > &  denseMatches )

pure virtual

Get The dense corresponding points.

Parameters

[out]

denseMatches

A vector containing all dense matches.

Note

The method clears the denseMatches vector.

The returned Match elements inside the sMatches vector, do not use corr member.

virtual cv::Mat cv::stereo::QuasiDenseStereo::getDisparity ( uint8_t  disparityLvls = 50 )

pure virtual

Compute and return the disparity map based on the correspondences found in the "process" method.

Parameters

[in]

disparityLvls

The level of detail in output disparity image.

Note

Default level is 50

Returns

cv::Mat containing a the disparity image in grayscale.

See Also

computeDisparity

quantizeDisparity

virtual cv::Point2f cv::stereo::QuasiDenseStereo::getMatch ( const int  x, const int  y  )

pure virtual

Specify pixel coordinates in the left image and get its corresponding location in the right image.

Parameters

[in]	x	The x pixel coordinate in the left image channel.
[in]	y	The y pixel coordinate in the left image channel.

Return values

cv::Point(x,y)	The location of the corresponding pixel in the right image.
cv::Point(0,0)	(NO_MATCH) if no match is found in the right image for the specified pixel location in the left image.

Note

This method should be always called after process, otherwise the matches will not be correct.

virtual void cv::stereo::QuasiDenseStereo::getSparseMatches ( std::vector< stereo::Match > &  sMatches )

pure virtual

Get The sparse corresponding points.

Parameters

[out]

sMatches

A vector containing all sparse correspondences.

Note

The method clears the sMatches vector.

The returned Match elements inside the sMatches vector, do not use corr member.

virtual int cv::stereo::QuasiDenseStereo::loadParameters ( cv::String  filepath )

pure virtual

Load a file containing the configuration parameters of the class.

Parameters

[in]

filepath

The location of the .YAML file containing the configuration parameters.

Note

default value is an empty string in which case the default parameters will be loaded.

Return values

1,:	If the path is not empty and the program loaded the parameters successfully.
0,:	If the path is empty and the program loaded default parameters.
-1,:	If the file location is not valid or the program could not open the file and loaded default parameters from defaults.hpp.

Note

The method is automatically called in the constructor and configures the class.

Loading different parameters will have an effect on the output. This is useful for tuning in case of video processing.

See Also

loadParameters

bool cv::stereo::Match::operator< ( const Match &  rhs ) const

inline

virtual void cv::stereo::QuasiDenseStereo::process ( const cv::Mat &  imgLeft, const cv::Mat &  imgRight  )

pure virtual

Main process of the algorithm. This method computes the sparse seeds and then densifies them.

Initially input images are converted to gray-scale and then the sparseMatching method is called to obtain the sparse stereo. Finally quasiDenseMatching is called to densify the corresponding points.

Parameters

[in]	imgLeft	The left Channel of a stereo image pair.
[in]	imgRight	The right Channel of a stereo image pair.

Note

If input images are in color, the method assumes that are BGR and converts them to grayscale.

See Also

sparseMatching

quasiDenseMatching

virtual int cv::stereo::QuasiDenseStereo::saveParameters ( cv::String  filepath )

pure virtual

Save a file containing all the configuration parameters the class is currently set to.

Parameters

[in]

filepath

The location to store the parameters file.

Note

Calling this method with no arguments will result in storing class parameters to a file names "qds_parameters.yaml" in the root project folder.

This method can be used to generate a template file for tuning the class.

See Also

loadParameters

Variable Documentation

int cv::stereo::PropagationParameters::borderX

int cv::stereo::PropagationParameters::borderY

float cv::stereo::Match::corr

float cv::stereo::PropagationParameters::correlationThreshold

int cv::stereo::PropagationParameters::corrWinSizeX

int cv::stereo::PropagationParameters::corrWinSizeY

int cv::stereo::PropagationParameters::disparityGradient

int cv::stereo::PropagationParameters::gftMaxNumFeatures

int cv::stereo::PropagationParameters::gftMinSeperationDist

float cv::stereo::PropagationParameters::gftQualityThres

int cv::stereo::PropagationParameters::lkPyrLvl

int cv::stereo::PropagationParameters::lkTemplateSize

int cv::stereo::PropagationParameters::lkTermParam1

float cv::stereo::PropagationParameters::lkTermParam2

int cv::stereo::PropagationParameters::neighborhoodSize

cv::Point2i cv::stereo::Match::p0

cv::Point2i cv::stereo::Match::p1

PropagationParameters cv::stereo::QuasiDenseStereo::Param

float cv::stereo::PropagationParameters::textrureThreshold