OpenCV  4.10.0
Open Source Computer Vision
Loading...
Searching...
No Matches
Public Member Functions | List of all members
cv::ximgproc::EdgeAwareInterpolator Class Referenceabstract

Sparse match interpolation algorithm based on modified locally-weighted affine estimator from [224] and Fast Global Smoother as post-processing filter. More...

#include <opencv2/ximgproc/sparse_match_interpolator.hpp>

Collaboration diagram for cv::ximgproc::EdgeAwareInterpolator:

Public Member Functions

virtual float getFGSLambda ()=0
 
virtual float getFGSSigma ()=0
 
virtual int getK ()=0
 
virtual float getLambda ()=0
 
virtual float getSigma ()=0
 
virtual bool getUsePostProcessing ()=0
 
virtual void setCostMap (const Mat &_costMap)=0
 Interface to provide a more elaborated cost map, i.e. edge map, for the edge-aware term. This implementation is based on a rather simple gradient-based edge map estimation. To used more complex edge map estimator (e.g. StructuredEdgeDetection that has been used in the original publication) that may lead to improved accuracies, the internal edge map estimation can be bypassed here.
 
virtual void setFGSLambda (float _lambda)=0
 Sets the respective fastGlobalSmootherFilter() parameter.
 
virtual void setFGSSigma (float _sigma)=0
 
virtual void setK (int _k)=0
 Parameter to tune the approximate size of the superpixel used for oversegmentation.
 
virtual void setLambda (float _lambda)=0
 Lambda is a parameter defining the weight of the edge-aware term in geodesic distance, should be in the range of 0 to 1000.
 
virtual void setSigma (float _sigma)=0
 Sigma is a parameter defining how fast the weights decrease in the locally-weighted affine fitting. Higher values can help preserve fine details, lower values can help to get rid of noise in the output flow.
 
virtual void setUsePostProcessing (bool _use_post_proc)=0
 Sets whether the fastGlobalSmootherFilter() post-processing is employed. It is turned on by default.
 
- Public Member Functions inherited from cv::ximgproc::SparseMatchInterpolator
virtual void interpolate (InputArray from_image, InputArray from_points, InputArray to_image, InputArray to_points, OutputArray dense_flow)=0
 Interpolate input sparse matches.
 
- 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
 

Additional Inherited Members

- Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tpload (const String &filename, const String &objname=String())
 Loads algorithm from the file.
 
template<typename _Tp >
static Ptr< _TploadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String.
 
template<typename _Tp >
static Ptr< _Tpread (const FileNode &fn)
 Reads algorithm from the file node.
 
- Protected Member Functions inherited from cv::Algorithm
void writeFormat (FileStorage &fs) const
 

Detailed Description

Sparse match interpolation algorithm based on modified locally-weighted affine estimator from [224] and Fast Global Smoother as post-processing filter.

Member Function Documentation

◆ getFGSLambda()

virtual float cv::ximgproc::EdgeAwareInterpolator::getFGSLambda ( )
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.getFGSLambda() -> retval
See also
setFGSLambda

◆ getFGSSigma()

virtual float cv::ximgproc::EdgeAwareInterpolator::getFGSSigma ( )
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.getFGSSigma() -> retval
See also
setFGSLambda

◆ getK()

virtual int cv::ximgproc::EdgeAwareInterpolator::getK ( )
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.getK() -> retval
See also
setK

◆ getLambda()

virtual float cv::ximgproc::EdgeAwareInterpolator::getLambda ( )
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.getLambda() -> retval
See also
setLambda

◆ getSigma()

virtual float cv::ximgproc::EdgeAwareInterpolator::getSigma ( )
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.getSigma() -> retval
See also
setSigma

◆ getUsePostProcessing()

virtual bool cv::ximgproc::EdgeAwareInterpolator::getUsePostProcessing ( )
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.getUsePostProcessing() -> retval

◆ setCostMap()

virtual void cv::ximgproc::EdgeAwareInterpolator::setCostMap ( const Mat _costMap)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setCostMap(_costMap) -> None

Interface to provide a more elaborated cost map, i.e. edge map, for the edge-aware term. This implementation is based on a rather simple gradient-based edge map estimation. To used more complex edge map estimator (e.g. StructuredEdgeDetection that has been used in the original publication) that may lead to improved accuracies, the internal edge map estimation can be bypassed here.

Parameters
_costMapa type CV_32FC1 Mat is required.
See also
cv::ximgproc::createSuperpixelSLIC

◆ setFGSLambda()

virtual void cv::ximgproc::EdgeAwareInterpolator::setFGSLambda ( float  _lambda)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setFGSLambda(_lambda) -> None

Sets the respective fastGlobalSmootherFilter() parameter.

◆ setFGSSigma()

virtual void cv::ximgproc::EdgeAwareInterpolator::setFGSSigma ( float  _sigma)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setFGSSigma(_sigma) -> None
See also
setFGSLambda

◆ setK()

virtual void cv::ximgproc::EdgeAwareInterpolator::setK ( int  _k)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setK(_k) -> None

Parameter to tune the approximate size of the superpixel used for oversegmentation.

See also
cv::ximgproc::createSuperpixelSLIC

K is a number of nearest-neighbor matches considered, when fitting a locally affine model. Usually it should be around 128. However, lower values would make the interpolation noticeably faster.

◆ setLambda()

virtual void cv::ximgproc::EdgeAwareInterpolator::setLambda ( float  _lambda)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setLambda(_lambda) -> None

Lambda is a parameter defining the weight of the edge-aware term in geodesic distance, should be in the range of 0 to 1000.

◆ setSigma()

virtual void cv::ximgproc::EdgeAwareInterpolator::setSigma ( float  _sigma)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setSigma(_sigma) -> None

Sigma is a parameter defining how fast the weights decrease in the locally-weighted affine fitting. Higher values can help preserve fine details, lower values can help to get rid of noise in the output flow.

◆ setUsePostProcessing()

virtual void cv::ximgproc::EdgeAwareInterpolator::setUsePostProcessing ( bool  _use_post_proc)
pure virtual
Python:
cv.ximgproc.EdgeAwareInterpolator.setUsePostProcessing(_use_post_proc) -> None

Sets whether the fastGlobalSmootherFilter() post-processing is employed. It is turned on by default.


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