Class cv::ximgproc::RICInterpolator#

Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [148] 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.

Collaboration diagram for cv::ximgproc::RICInterpolator:

Public Member Functions#

Public Member Functions inherited from cv::ximgproc::SparseMatchInterpolator
Public Member Functions inherited from cv::Algorithm

Return

Name

Description

Algorithm()

~Algorithm()

void

clear()

Clears the algorithm state.

bool

empty()

Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.

String

getDefaultName()

void

read(const FileNode & fn)

Reads algorithm parameters from a file storage.

void

save(const String & filename)

void

write(
    const Ptr< FileStorage > & fs,
    const String & name = String() )

void

write(FileStorage & fs)

Stores algorithm parameters in a file storage.

void

write(
    FileStorage & fs,
    const String & name )

Static Public Member Functions#

Static Public Member Functions inherited from cv::Algorithm

Return

Name

Description

static Ptr< _Tp >

load(
    const String & filename,
    const String & objname = String() )

Loads algorithm from the file.

static Ptr< _Tp >

loadFromString(
    const String & strModel,
    const String & objname = String() )

Loads algorithm from a String.

static Ptr< _Tp >

read(const FileNode & fn)

Reads algorithm from the file node.

Additional Inherited Members#

Protected Member Functions inherited from cv::Algorithm

Return

Name

Description

void

writeFormat(FileStorage & fs)

Detailed Description#

Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [148] 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()#

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

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

See also

setAlpha

getFGSLambda()#

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

Sets the respective fastGlobalSmootherFilter() parameter.

See also

setFGSLambda

getFGSSigma()#

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

Sets the respective fastGlobalSmootherFilter() parameter.

See also

setFGSSigma

getK()#

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

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 [148] uses 32.

See also

setK

getMaxFlow()#

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

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()#

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

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

See also

setModelIter

getRefineModels()#

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

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

See also

setRefineModels

getSuperpixelMode()#

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

Parameter to choose superpixel algorithm variant to use:

getSuperpixelNNCnt()#

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

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

getSuperpixelRuler()#

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

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

getSuperpixelSize()#

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

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

getUseGlobalSmootherFilter()#

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

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

getUseVariationalRefinement()#

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

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

setAlpha()#

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

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

setCostMap()#

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

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.

setFGSLambda()#

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

Sets the respective fastGlobalSmootherFilter() parameter.

setFGSSigma()#

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

Sets the respective fastGlobalSmootherFilter() parameter.

setK()#

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

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 [148] uses 32.

setMaxFlow()#

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

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()#

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

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

setRefineModels()#

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

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

setSuperpixelMode()#

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

Parameter to choose superpixel algorithm variant to use:

setSuperpixelNNCnt()#

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

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

setSuperpixelRuler()#

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

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

setSuperpixelSize()#

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

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

See also

setCostMap

setUseGlobalSmootherFilter()#

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

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

setUseVariationalRefinement()#

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

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

Source file#

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