cv::StereoBM Class Reference

Class for computing stereo correspondence using the block matching algorithm, introduced and contributed to OpenCV by K. Konolige. More...

#include <opencv2/calib3d.hpp>

Collaboration diagram for cv::StereoBM:

Public Types
enum	{   PREFILTER_NORMALIZED_RESPONSE = 0 ,   PREFILTER_XSOBEL = 1 }
	Pre-filter types for the stereo matching algorithm. More...
Public Types inherited from cv::StereoMatcher
enum	{   DISP_SHIFT = 4 ,   DISP_SCALE = (1 << DISP_SHIFT) }

Public Member Functions
virtual int	getPreFilterCap () const =0
	Gets the current truncation value for prefiltered pixels.
virtual int	getPreFilterSize () const =0
	Gets the current size of the pre-filter kernel.
virtual int	getPreFilterType () const =0
	Gets the type of pre-filtering currently used in the algorithm.
virtual Rect	getROI1 () const =0
	Gets the current Region of Interest (ROI) for the left image.
virtual Rect	getROI2 () const =0
	Gets the current Region of Interest (ROI) for the right image.
virtual int	getSmallerBlockSize () const =0
	Gets the current size of the smaller block used for texture check.
virtual int	getTextureThreshold () const =0
	Gets the current texture threshold value.
virtual int	getUniquenessRatio () const =0
	Gets the current uniqueness ratio value.
virtual void	setPreFilterCap (int preFilterCap)=0
	Sets the truncation value for prefiltered pixels.
virtual void	setPreFilterSize (int preFilterSize)=0
	Sets the size of the pre-filter kernel.
virtual void	setPreFilterType (int preFilterType)=0
	Sets the type of pre-filtering used in the algorithm.
virtual void	setROI1 (Rect roi1)=0
	Sets the Region of Interest (ROI) for the left image.
virtual void	setROI2 (Rect roi2)=0
	Sets the Region of Interest (ROI) for the right image.
virtual void	setSmallerBlockSize (int blockSize)=0
	Sets the size of the smaller block used for texture check.
virtual void	setTextureThreshold (int textureThreshold)=0
	Sets the threshold for filtering low-texture regions.
virtual void	setUniquenessRatio (int uniquenessRatio)=0
	Sets the uniqueness ratio for filtering ambiguous matches.
Public Member Functions inherited from cv::StereoMatcher
virtual void	compute (InputArray left, InputArray right, OutputArray disparity)=0
	Computes disparity map for the specified stereo pair.
virtual int	getBlockSize () const =0
virtual int	getDisp12MaxDiff () const =0
virtual int	getMinDisparity () const =0
virtual int	getNumDisparities () const =0
virtual int	getSpeckleRange () const =0
virtual int	getSpeckleWindowSize () const =0
virtual void	setBlockSize (int blockSize)=0
virtual void	setDisp12MaxDiff (int disp12MaxDiff)=0
virtual void	setMinDisparity (int minDisparity)=0
virtual void	setNumDisparities (int numDisparities)=0
virtual void	setSpeckleRange (int speckleRange)=0
virtual void	setSpeckleWindowSize (int speckleWindowSize)=0
Public Member Functions inherited from cv::Algorithm
	Algorithm ()
virtual	~Algorithm ()
virtual void	clear ()
	Clears the algorithm state.
virtual bool	empty () const
	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.
virtual String	getDefaultName () const
virtual void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage.
virtual void	save (const String &filename) const
void	write (const Ptr< FileStorage > &fs, const String &name=String()) const
virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage.
void	write (FileStorage &fs, const String &name) const

Static Public Member Functions
static Ptr< StereoBM >	create (int numDisparities=0, int blockSize=21)
	Creates StereoBM object.
Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file.
template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String.
template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node.

Additional Inherited Members
Protected Member Functions inherited from cv::Algorithm
void	writeFormat (FileStorage &fs) const

Detailed Description

Class for computing stereo correspondence using the block matching algorithm, introduced and contributed to OpenCV by K. Konolige.

This class implements a block matching algorithm for stereo correspondence, which is used to compute disparity maps from stereo image pairs. It provides methods to fine-tune parameters such as pre-filtering, texture thresholds, uniqueness ratios, and regions of interest (ROIs) to optimize performance and accuracy.

Member Enumeration Documentation

anonymous enum

anonymous enum

Pre-filter types for the stereo matching algorithm.

These constants define the type of pre-filtering applied to the images before computing the disparity map.

• PREFILTER_NORMALIZED_RESPONSE: Uses normalized response for pre-filtering.
• PREFILTER_XSOBEL: Uses the X-Sobel operator for pre-filtering.

Enumerator
PREFILTER_NORMALIZED_RESPONSE	Normalized response pre-filter.
PREFILTER_XSOBEL	X-Sobel pre-filter.

Member Function Documentation

create()

static Ptr< StereoBM > cv::StereoBM::create ( int numDisparities = 0, int blockSize = 21 )

static

Python:
	cv.StereoBM.create(	[, numDisparities[, blockSize]]	) ->	retval
	cv.StereoBM_create(	[, numDisparities[, blockSize]]	) ->	retval

Creates StereoBM object.

Parameters

numDisparities	The disparity search range. For each pixel, the algorithm will find the best disparity from 0 (default minimum disparity) to numDisparities. The search range can be shifted by changing the minimum disparity.
blockSize	The linear size of the blocks compared by the algorithm. The size should be odd (as the block is centered at the current pixel). Larger block size implies smoother, though less accurate disparity map. Smaller block size gives more detailed disparity map, but there is a higher chance for the algorithm to find a wrong correspondence.

Returns

A pointer to the created StereoBM object.

The function creates a StereoBM object. You can then call StereoBM::compute() to compute disparity for a specific stereo pair.

getPreFilterCap()

virtual int cv::StereoBM::getPreFilterCap ( ) const

pure virtual

Python:
	cv.StereoBM.getPreFilterCap(		) ->	retval

Gets the current truncation value for prefiltered pixels.

Returns

The current pre-filter cap value.

getPreFilterSize()

virtual int cv::StereoBM::getPreFilterSize ( ) const

pure virtual

Python:
	cv.StereoBM.getPreFilterSize(		) ->	retval

Gets the current size of the pre-filter kernel.

Returns

The current pre-filter size.

getPreFilterType()

virtual int cv::StereoBM::getPreFilterType ( ) const

pure virtual

Python:
	cv.StereoBM.getPreFilterType(		) ->	retval

Gets the type of pre-filtering currently used in the algorithm.

Returns

The current pre-filter type: 0 for PREFILTER_NORMALIZED_RESPONSE or 1 for PREFILTER_XSOBEL.

getROI1()

virtual Rect cv::StereoBM::getROI1 ( ) const

pure virtual

Python:
	cv.StereoBM.getROI1(		) ->	retval

Gets the current Region of Interest (ROI) for the left image.

Returns

The current ROI for the left image.

getROI2()

virtual Rect cv::StereoBM::getROI2 ( ) const

pure virtual

Python:
	cv.StereoBM.getROI2(		) ->	retval

Gets the current Region of Interest (ROI) for the right image.

Returns

The current ROI for the right image.

getSmallerBlockSize()

virtual int cv::StereoBM::getSmallerBlockSize ( ) const

pure virtual

Python:
	cv.StereoBM.getSmallerBlockSize(		) ->	retval

Gets the current size of the smaller block used for texture check.

Returns

The current smaller block size.

getTextureThreshold()

virtual int cv::StereoBM::getTextureThreshold ( ) const

pure virtual

Python:
	cv.StereoBM.getTextureThreshold(		) ->	retval

Gets the current texture threshold value.

Returns

The current texture threshold.

getUniquenessRatio()

virtual int cv::StereoBM::getUniquenessRatio ( ) const

pure virtual

Python:
	cv.StereoBM.getUniquenessRatio(		) ->	retval

Gets the current uniqueness ratio value.

Returns

The current uniqueness ratio.

setPreFilterCap()

virtual void cv::StereoBM::setPreFilterCap ( int preFilterCap )

pure virtual

Python:
	cv.StereoBM.setPreFilterCap(	preFilterCap	) ->	None

Sets the truncation value for prefiltered pixels.

Parameters

preFilterCap

The truncation value. Typically in the range [1, 63].

This value caps the output of the pre-filter to [-preFilterCap, preFilterCap], helping to reduce the impact of noise and outliers in the pre-filtered image.

setPreFilterSize()

virtual void cv::StereoBM::setPreFilterSize ( int preFilterSize )

pure virtual

Python:
	cv.StereoBM.setPreFilterSize(	preFilterSize	) ->	None

Sets the size of the pre-filter kernel.

Parameters

preFilterSize

The size of the pre-filter kernel. Must be an odd integer, typically between 5 and 255.

The pre-filter size determines the spatial extent of the pre-filtering operation, which prepares the images for disparity computation by normalizing brightness and enhancing texture. Larger sizes reduce noise but may blur details, while smaller sizes preserve details but are more susceptible to noise.

setPreFilterType()

virtual void cv::StereoBM::setPreFilterType ( int preFilterType )

pure virtual

Python:
	cv.StereoBM.setPreFilterType(	preFilterType	) ->	None

Sets the type of pre-filtering used in the algorithm.

Parameters

preFilterType

The type of pre-filter to use. Possible values are: PREFILTER_NORMALIZED_RESPONSE (0): Uses normalized response for pre-filtering. PREFILTER_XSOBEL (1): Uses the X-Sobel operator for pre-filtering.

The pre-filter type affects how the images are prepared before computing the disparity map. Different pre-filtering methods can enhance specific image features or reduce noise, influencing the quality of the disparity map.

setROI1()

virtual void cv::StereoBM::setROI1 ( Rect roi1 )

pure virtual

Python:
	cv.StereoBM.setROI1(	roi1	) ->	None

Sets the Region of Interest (ROI) for the left image.

Parameters

roi1	The ROI rectangle for the left image.

By setting the ROI, the stereo matching computation is limited to the specified region, improving performance and potentially accuracy by focusing on relevant parts of the image.

setROI2()

virtual void cv::StereoBM::setROI2 ( Rect roi2 )

pure virtual

Python:
	cv.StereoBM.setROI2(	roi2	) ->	None

Sets the Region of Interest (ROI) for the right image.

Parameters

roi2	The ROI rectangle for the right image.

Similar to setROI1, this limits the computation to the specified region in the right image.

setSmallerBlockSize()

virtual void cv::StereoBM::setSmallerBlockSize ( int blockSize )

pure virtual

Python:
	cv.StereoBM.setSmallerBlockSize(	blockSize	) ->	None

Sets the size of the smaller block used for texture check.

Parameters

blockSize

The size of the smaller block. Must be an odd integer between 5 and 255.

This parameter determines the size of the block used to compute texture variance. Smaller blocks capture finer details but are more sensitive to noise, while larger blocks are more robust but may miss fine details.

setTextureThreshold()

virtual void cv::StereoBM::setTextureThreshold ( int textureThreshold )

pure virtual

Python:
	cv.StereoBM.setTextureThreshold(	textureThreshold	) ->	None

Sets the threshold for filtering low-texture regions.

Parameters

textureThreshold

The threshold value. Must be non-negative.

This parameter filters out regions with low texture, where establishing correspondences is difficult, thus reducing noise in the disparity map. Higher values filter more aggressively but may discard valid information.

setUniquenessRatio()

virtual void cv::StereoBM::setUniquenessRatio ( int uniquenessRatio )

pure virtual

Python:
	cv.StereoBM.setUniquenessRatio(	uniquenessRatio	) ->	None

Sets the uniqueness ratio for filtering ambiguous matches.

Parameters

uniquenessRatio

The uniqueness ratio value. Typically in the range [5, 15], but can be from 0 to 100.

This parameter ensures that the best match is sufficiently better than the next best match, reducing false positives. Higher values are stricter but may filter out valid matches in difficult regions.

---

The documentation for this class was generated from the following file:

• opencv2/calib3d.hpp