OpenCV  4.5.0 Open Source Computer Vision
cv::ximgproc::DisparityWLSFilter Class Referenceabstract

Disparity map filter based on Weighted Least Squares filter (in form of Fast Global Smoother that is a lot faster than traditional Weighted Least Squares filter implementations) and optional use of left-right-consistency-based confidence to refine the results in half-occlusions and uniform areas. More...

#include <opencv2/ximgproc/disparity_filter.hpp>

Inheritance diagram for cv::ximgproc::DisparityWLSFilter:

## Public Member Functions

virtual Mat getConfidenceMap ()=0
Get the confidence map that was used in the last filter call. It is a CV_32F one-channel image with values ranging from 0.0 (totally untrusted regions of the raw disparity map) to 255.0 (regions containing correct disparity values with a high degree of confidence). More...

DepthDiscontinuityRadius is a parameter used in confidence computation. It defines the size of low-confidence regions around depth discontinuities. More...

virtual double getLambda ()=0
Lambda is a parameter defining the amount of regularization during filtering. Larger values force filtered disparity map edges to adhere more to source image edges. Typical value is 8000. More...

virtual int getLRCthresh ()=0
LRCthresh is a threshold of disparity difference used in left-right-consistency check during confidence map computation. The default value of 24 (1.5 pixels) is virtually always good enough. More...

virtual Rect getROI ()=0
Get the ROI used in the last filter call. More...

virtual double getSigmaColor ()=0
SigmaColor is a parameter defining how sensitive the filtering process is to source image edges. Large values can lead to disparity leakage through low-contrast edges. Small values can make the filter too sensitive to noise and textures in the source image. Typical values range from 0.8 to 2.0. More...

virtual void setLambda (double _lambda)=0

virtual void setLRCthresh (int _LRC_thresh)=0

virtual void setSigmaColor (double _sigma_color)=0

Public Member Functions inherited from cv::ximgproc::DisparityFilter
virtual void filter (InputArray disparity_map_left, InputArray left_view, OutputArray filtered_disparity_map, InputArray disparity_map_right=Mat(), Rect ROI=Rect(), InputArray right_view=Mat())=0
Apply filtering to the disparity map. More...

Public Member Functions inherited from cv::Algorithm
Algorithm ()

virtual ~Algorithm ()

virtual void clear ()
Clears the algorithm state. More...

virtual bool empty () const
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...

virtual String getDefaultName () const

virtual void read (const FileNode &fn)
Reads algorithm parameters from a file storage. More...

virtual void save (const String &filename) const

virtual void write (FileStorage &fs) const
Stores algorithm parameters in a file storage. More...

void write (const Ptr< FileStorage > &fs, const String &name=String()) const
simplified API for language bindings This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...

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. More...

template<typename _Tp >
static Ptr< _Tp > loadFromString (const String &strModel, const String &objname=String())
Loads algorithm from a String. More...

template<typename _Tp >
static Ptr< _Tp > read (const FileNode &fn)
Reads algorithm from the file node. More...

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

## Detailed Description

Disparity map filter based on Weighted Least Squares filter (in form of Fast Global Smoother that is a lot faster than traditional Weighted Least Squares filter implementations) and optional use of left-right-consistency-based confidence to refine the results in half-occlusions and uniform areas.

## ◆ getConfidenceMap()

 virtual Mat cv::ximgproc::DisparityWLSFilter::getConfidenceMap ( )
pure virtual
Python:
retval=cv.ximgproc_DisparityWLSFilter.getConfidenceMap()

Get the confidence map that was used in the last filter call. It is a CV_32F one-channel image with values ranging from 0.0 (totally untrusted regions of the raw disparity map) to 255.0 (regions containing correct disparity values with a high degree of confidence).

pure virtual
Python:

DepthDiscontinuityRadius is a parameter used in confidence computation. It defines the size of low-confidence regions around depth discontinuities.

## ◆ getLambda()

 virtual double cv::ximgproc::DisparityWLSFilter::getLambda ( )
pure virtual
Python:
retval=cv.ximgproc_DisparityWLSFilter.getLambda()

Lambda is a parameter defining the amount of regularization during filtering. Larger values force filtered disparity map edges to adhere more to source image edges. Typical value is 8000.

filter parameters

## ◆ getLRCthresh()

 virtual int cv::ximgproc::DisparityWLSFilter::getLRCthresh ( )
pure virtual
Python:
retval=cv.ximgproc_DisparityWLSFilter.getLRCthresh()

LRCthresh is a threshold of disparity difference used in left-right-consistency check during confidence map computation. The default value of 24 (1.5 pixels) is virtually always good enough.

confidence-related parameters

## ◆ getROI()

 virtual Rect cv::ximgproc::DisparityWLSFilter::getROI ( )
pure virtual
Python:
retval=cv.ximgproc_DisparityWLSFilter.getROI()

Get the ROI used in the last filter call.

## ◆ getSigmaColor()

 virtual double cv::ximgproc::DisparityWLSFilter::getSigmaColor ( )
pure virtual
Python:
retval=cv.ximgproc_DisparityWLSFilter.getSigmaColor()

SigmaColor is a parameter defining how sensitive the filtering process is to source image edges. Large values can lead to disparity leakage through low-contrast edges. Small values can make the filter too sensitive to noise and textures in the source image. Typical values range from 0.8 to 2.0.

pure virtual
Python:

## ◆ setLambda()

 virtual void cv::ximgproc::DisparityWLSFilter::setLambda ( double _lambda )
pure virtual
Python:
None=cv.ximgproc_DisparityWLSFilter.setLambda(_lambda)
getLambda

## ◆ setLRCthresh()

 virtual void cv::ximgproc::DisparityWLSFilter::setLRCthresh ( int _LRC_thresh )
pure virtual
Python:
None=cv.ximgproc_DisparityWLSFilter.setLRCthresh(_LRC_thresh)