cv::ximgproc::RICInterpolator Class Reference

Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [130] and Variational and Fast Global Smoother as post-processing filter. The RICInterpolator is a extension of the EdgeAwareInterpolator. Main concept of this extension is an piece-wise affine model based on over-segmentation via SLIC superpixel estimation. The method contains an efficient propagation mechanism to estimate among the pieces-wise models. More...

#include <opencv2/ximgproc/sparse_match_interpolator.hpp>

Collaboration diagram for cv::ximgproc::RICInterpolator:

Public Member Functions
virtual float	getAlpha () const =0
	Alpha is a parameter defining a global weight for transforming geodesic distance into weight.
virtual float	getFGSLambda () const =0
	Sets the respective fastGlobalSmootherFilter() parameter.
virtual float	getFGSSigma () const =0
	Sets the respective fastGlobalSmootherFilter() parameter.
virtual int	getK () const =0
	K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of [130] uses 32.
virtual float	getMaxFlow () const =0
	MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead.
virtual int	getModelIter () const =0
	Parameter defining the number of iterations for piece-wise affine model estimation.
virtual bool	getRefineModels () const =0
	Parameter to choose wether additional refinement of the piece-wise affine models is employed.
virtual int	getSuperpixelMode () const =0
	Parameter to choose superpixel algorithm variant to use:
virtual int	getSuperpixelNNCnt () const =0
	Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.
virtual float	getSuperpixelRuler () const =0
	Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.
virtual int	getSuperpixelSize () const =0
	Get the internal cost, i.e. edge map, used for estimating the edge-aware term.
virtual bool	getUseGlobalSmootherFilter () const =0
	Sets whether the fastGlobalSmootherFilter() post-processing is employed.
virtual bool	getUseVariationalRefinement () const =0
	Parameter to choose wether the VariationalRefinement post-processing is employed.
virtual void	setAlpha (float alpha=0.7f)=0
	Alpha is a parameter defining a global weight for transforming geodesic distance into weight.
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=500.f)=0
	Sets the respective fastGlobalSmootherFilter() parameter.
virtual void	setFGSSigma (float sigma=1.5f)=0
	Sets the respective fastGlobalSmootherFilter() parameter.
virtual void	setK (int k=32)=0
	K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of [130] uses 32.
virtual void	setMaxFlow (float maxFlow=250.f)=0
	MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead.
virtual void	setModelIter (int modelIter=4)=0
	Parameter defining the number of iterations for piece-wise affine model estimation.
virtual void	setRefineModels (bool refineModles=true)=0
	Parameter to choose wether additional refinement of the piece-wise affine models is employed.
virtual void	setSuperpixelMode (int mode=100)=0
	Parameter to choose superpixel algorithm variant to use:
virtual void	setSuperpixelNNCnt (int spNN=150)=0
	Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.
virtual void	setSuperpixelRuler (float ruler=15.f)=0
	Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.
virtual void	setSuperpixelSize (int spSize=15)=0
	Get the internal cost, i.e. edge map, used for estimating the edge-aware term.
virtual void	setUseGlobalSmootherFilter (bool use_FGS=true)=0
	Sets whether the fastGlobalSmootherFilter() post-processing is employed.
virtual void	setUseVariationalRefinement (bool use_variational_refinement=false)=0
	Parameter to choose wether the VariationalRefinement post-processing is employed.
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
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< _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.
Protected Member Functions inherited from cv::Algorithm
void	writeFormat (FileStorage &fs) const

Detailed Description

Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [130] and Variational and Fast Global Smoother as post-processing filter. The RICInterpolator is a extension of the EdgeAwareInterpolator. Main concept of this extension is an piece-wise affine model based on over-segmentation via SLIC superpixel estimation. The method contains an efficient propagation mechanism to estimate among the pieces-wise models.

Member Function Documentation

getAlpha()

virtual float cv::ximgproc::RICInterpolator::getAlpha ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getAlpha(		) ->	retval

Alpha is a parameter defining a global weight for transforming geodesic distance into weight.

See also

setAlpha

getFGSLambda()

virtual float cv::ximgproc::RICInterpolator::getFGSLambda ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getFGSLambda(		) ->	retval

Sets the respective fastGlobalSmootherFilter() parameter.

See also

setFGSLambda

getFGSSigma()

virtual float cv::ximgproc::RICInterpolator::getFGSSigma ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getFGSSigma(		) ->	retval

Sets the respective fastGlobalSmootherFilter() parameter.

See also

setFGSSigma

getK()

virtual int cv::ximgproc::RICInterpolator::getK ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getK(		) ->	retval

K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of [130] uses 32.

See also

setK

getMaxFlow()

virtual float cv::ximgproc::RICInterpolator::getMaxFlow ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getMaxFlow(		) ->	retval

MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead.

See also

setMaxFlow

getModelIter()

virtual int cv::ximgproc::RICInterpolator::getModelIter ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getModelIter(		) ->	retval

Parameter defining the number of iterations for piece-wise affine model estimation.

See also

setModelIter

getRefineModels()

virtual bool cv::ximgproc::RICInterpolator::getRefineModels ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getRefineModels(		) ->	retval

Parameter to choose wether additional refinement of the piece-wise affine models is employed.

See also

setRefineModels

getSuperpixelMode()

virtual int cv::ximgproc::RICInterpolator::getSuperpixelMode ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getSuperpixelMode(		) ->	retval

Parameter to choose superpixel algorithm variant to use:

See also

setSuperpixelMode

getSuperpixelNNCnt()

virtual int cv::ximgproc::RICInterpolator::getSuperpixelNNCnt ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getSuperpixelNNCnt(		) ->	retval

Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.

See also

setSuperpixelNNCnt

getSuperpixelRuler()

virtual float cv::ximgproc::RICInterpolator::getSuperpixelRuler ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getSuperpixelRuler(		) ->	retval

Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.

See also

setSuperpixelRuler

getSuperpixelSize()

virtual int cv::ximgproc::RICInterpolator::getSuperpixelSize ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getSuperpixelSize(		) ->	retval

Get the internal cost, i.e. edge map, used for estimating the edge-aware term.

See also

setSuperpixelSize

getUseGlobalSmootherFilter()

virtual bool cv::ximgproc::RICInterpolator::getUseGlobalSmootherFilter ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getUseGlobalSmootherFilter(		) ->	retval

Sets whether the fastGlobalSmootherFilter() post-processing is employed.

See also

setUseGlobalSmootherFilter

getUseVariationalRefinement()

virtual bool cv::ximgproc::RICInterpolator::getUseVariationalRefinement ( ) const

pure virtual

Python:
	cv.ximgproc.RICInterpolator.getUseVariationalRefinement(		) ->	retval

Parameter to choose wether the VariationalRefinement post-processing is employed.

See also

setUseVariationalRefinement

setAlpha()

virtual void cv::ximgproc::RICInterpolator::setAlpha ( float alpha = 0.7f )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setAlpha(	[, alpha]	) ->	None

Alpha is a parameter defining a global weight for transforming geodesic distance into weight.

setCostMap()

virtual void cv::ximgproc::RICInterpolator::setCostMap ( const Mat & costMap )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.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

costMap

a type CV_32FC1 Mat is required.

See also

cv::ximgproc::createSuperpixelSLIC

setFGSLambda()

virtual void cv::ximgproc::RICInterpolator::setFGSLambda ( float lambda = 500.f )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setFGSLambda(	[, lambda_]	) ->	None

Sets the respective fastGlobalSmootherFilter() parameter.

setFGSSigma()

virtual void cv::ximgproc::RICInterpolator::setFGSSigma ( float sigma = 1.5f )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setFGSSigma(	[, sigma]	) ->	None

Sets the respective fastGlobalSmootherFilter() parameter.

setK()

virtual void cv::ximgproc::RICInterpolator::setK ( int k = 32 )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setK(	[, k]	) ->	None

K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of [130] uses 32.

setMaxFlow()

virtual void cv::ximgproc::RICInterpolator::setMaxFlow ( float maxFlow = 250.f )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setMaxFlow(	[, maxFlow]	) ->	None

MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead.

setModelIter()

virtual void cv::ximgproc::RICInterpolator::setModelIter ( int modelIter = 4 )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setModelIter(	[, modelIter]	) ->	None

Parameter defining the number of iterations for piece-wise affine model estimation.

setRefineModels()

virtual void cv::ximgproc::RICInterpolator::setRefineModels ( bool refineModles = true )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setRefineModels(	[, refineModles]	) ->	None

Parameter to choose wether additional refinement of the piece-wise affine models is employed.

setSuperpixelMode()

virtual void cv::ximgproc::RICInterpolator::setSuperpixelMode ( int mode = 100 )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setSuperpixelMode(	[, mode]	) ->	None

Parameter to choose superpixel algorithm variant to use:

• cv::ximgproc::SLICType SLIC segments image using a desired region_size (value: 100)
• cv::ximgproc::SLICType SLICO will optimize using adaptive compactness factor (value: 101)
• cv::ximgproc::SLICType MSLIC will optimize using manifold methods resulting in more content-sensitive superpixels (value: 102).

  See also

  cv::ximgproc::createSuperpixelSLIC

setSuperpixelNNCnt()

virtual void cv::ximgproc::RICInterpolator::setSuperpixelNNCnt ( int spNN = 150 )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setSuperpixelNNCnt(	[, spNN]	) ->	None

Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.

setSuperpixelRuler()

virtual void cv::ximgproc::RICInterpolator::setSuperpixelRuler ( float ruler = 15.f )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setSuperpixelRuler(	[, ruler]	) ->	None

Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.

See also

cv::ximgproc::createSuperpixelSLIC

setSuperpixelSize()

virtual void cv::ximgproc::RICInterpolator::setSuperpixelSize ( int spSize = 15 )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setSuperpixelSize(	[, spSize]	) ->	None

Get the internal cost, i.e. edge map, used for estimating the edge-aware term.

See also

setCostMap

setUseGlobalSmootherFilter()

virtual void cv::ximgproc::RICInterpolator::setUseGlobalSmootherFilter ( bool use_FGS = true )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setUseGlobalSmootherFilter(	[, use_FGS]	) ->	None

Sets whether the fastGlobalSmootherFilter() post-processing is employed.

setUseVariationalRefinement()

virtual void cv::ximgproc::RICInterpolator::setUseVariationalRefinement ( bool use_variational_refinement = false )

pure virtual

Python:
	cv.ximgproc.RICInterpolator.setUseVariationalRefinement(	[, use_variational_refinement]	) ->	None

Parameter to choose wether the VariationalRefinement post-processing is employed.

---

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

• opencv2/ximgproc/sparse_match_interpolator.hpp