Class RICInterpolator


  • public class RICInterpolator
    extends SparseMatchInterpolator
    Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from CITE: Hu2017 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.
    • Constructor Summary

      Constructors 
      Modifier Constructor Description
      protected RICInterpolator​(long addr)  
    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      static RICInterpolator __fromPtr__​(long addr)  
      protected void finalize()  
      float getAlpha()
      setAlpha SEE: setAlpha
      float getFGSLambda()
      setFGSLambda SEE: setFGSLambda
      float getFGSSigma()
      setFGSSigma SEE: setFGSSigma
      int getK()
      setK SEE: setK
      float getMaxFlow()
      setMaxFlow SEE: setMaxFlow
      int getModelIter()
      setModelIter SEE: setModelIter
      boolean getRefineModels()
      setRefineModels SEE: setRefineModels
      int getSuperpixelMode()
      setSuperpixelMode SEE: setSuperpixelMode
      int getSuperpixelNNCnt()
      setSuperpixelNNCnt SEE: setSuperpixelNNCnt
      float getSuperpixelRuler()
      setSuperpixelRuler SEE: setSuperpixelRuler
      int getSuperpixelSize()
      setSuperpixelSize SEE: setSuperpixelSize
      boolean getUseGlobalSmootherFilter()
      setUseGlobalSmootherFilter SEE: setUseGlobalSmootherFilter
      boolean getUseVariationalRefinement()
      setUseVariationalRefinement SEE: setUseVariationalRefinement
      void setAlpha()
      Alpha is a parameter defining a global weight for transforming geodesic distance into weight.
      void setAlpha​(float alpha)
      Alpha is a parameter defining a global weight for transforming geodesic distance into weight.
      void setCostMap​(Mat costMap)
      Interface to provide a more elaborated cost map, i.e.
      void setFGSLambda()
      Sets the respective fastGlobalSmootherFilter() parameter.
      void setFGSLambda​(float lambda)
      Sets the respective fastGlobalSmootherFilter() parameter.
      void setFGSSigma()
      Sets the respective fastGlobalSmootherFilter() parameter.
      void setFGSSigma​(float sigma)
      Sets the respective fastGlobalSmootherFilter() parameter.
      void setK()
      K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment.
      void setK​(int k)
      K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment.
      void setMaxFlow()
      MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model.
      void setMaxFlow​(float maxFlow)
      MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model.
      void setModelIter()
      Parameter defining the number of iterations for piece-wise affine model estimation.
      void setModelIter​(int modelIter)
      Parameter defining the number of iterations for piece-wise affine model estimation.
      void setRefineModels()
      Parameter to choose wether additional refinement of the piece-wise affine models is employed.
      void setRefineModels​(boolean refineModles)
      Parameter to choose wether additional refinement of the piece-wise affine models is employed.
      void setSuperpixelMode()
      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).
      void setSuperpixelMode​(int mode)
      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).
      void setSuperpixelNNCnt()
      Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.
      void setSuperpixelNNCnt​(int spNN)
      Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.
      void setSuperpixelRuler()
      Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.
      void setSuperpixelRuler​(float ruler)
      Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.
      void setSuperpixelSize()
      Get the internal cost, i.e.
      void setSuperpixelSize​(int spSize)
      Get the internal cost, i.e.
      void setUseGlobalSmootherFilter()
      Sets whether the fastGlobalSmootherFilter() post-processing is employed.
      void setUseGlobalSmootherFilter​(boolean use_FGS)
      Sets whether the fastGlobalSmootherFilter() post-processing is employed.
      void setUseVariationalRefinement()
      Parameter to choose wether the VariationalRefinement post-processing is employed.
      void setUseVariationalRefinement​(boolean use_variational_refinement)
      Parameter to choose wether the VariationalRefinement post-processing is employed.
      • Methods inherited from class java.lang.Object

        clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • RICInterpolator

        protected RICInterpolator​(long addr)
    • Method Detail

      • setK

        public void setK​(int k)
        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 CITE: Hu2017 uses 32.
        Parameters:
        k - automatically generated
      • setK

        public void setK()
        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 CITE: Hu2017 uses 32.
      • getK

        public int getK()
        setK SEE: setK
        Returns:
        automatically generated
      • setCostMap

        public void setCostMap​(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. SEE: cv::ximgproc::createSuperpixelSLIC
      • setSuperpixelSize

        public void setSuperpixelSize​(int spSize)
        Get the internal cost, i.e. edge map, used for estimating the edge-aware term. SEE: setCostMap
        Parameters:
        spSize - automatically generated
      • setSuperpixelSize

        public void setSuperpixelSize()
        Get the internal cost, i.e. edge map, used for estimating the edge-aware term. SEE: setCostMap
      • getSuperpixelSize

        public int getSuperpixelSize()
        setSuperpixelSize SEE: setSuperpixelSize
        Returns:
        automatically generated
      • setSuperpixelNNCnt

        public void setSuperpixelNNCnt​(int spNN)
        Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.
        Parameters:
        spNN - automatically generated
      • setSuperpixelNNCnt

        public void setSuperpixelNNCnt()
        Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.
      • getSuperpixelNNCnt

        public int getSuperpixelNNCnt()
        setSuperpixelNNCnt SEE: setSuperpixelNNCnt
        Returns:
        automatically generated
      • setSuperpixelRuler

        public void setSuperpixelRuler​(float ruler)
        Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation. SEE: cv::ximgproc::createSuperpixelSLIC
        Parameters:
        ruler - automatically generated
      • setSuperpixelRuler

        public void setSuperpixelRuler()
        Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation. SEE: cv::ximgproc::createSuperpixelSLIC
      • getSuperpixelRuler

        public float getSuperpixelRuler()
        setSuperpixelRuler SEE: setSuperpixelRuler
        Returns:
        automatically generated
      • setSuperpixelMode

        public void setSuperpixelMode​(int mode)
        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: cv::ximgproc::createSuperpixelSLIC
        Parameters:
        mode - automatically generated
      • setSuperpixelMode

        public void setSuperpixelMode()
        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: cv::ximgproc::createSuperpixelSLIC
      • getSuperpixelMode

        public int getSuperpixelMode()
        setSuperpixelMode SEE: setSuperpixelMode
        Returns:
        automatically generated
      • setAlpha

        public void setAlpha​(float alpha)
        Alpha is a parameter defining a global weight for transforming geodesic distance into weight.
        Parameters:
        alpha - automatically generated
      • setAlpha

        public void setAlpha()
        Alpha is a parameter defining a global weight for transforming geodesic distance into weight.
      • getAlpha

        public float getAlpha()
        setAlpha SEE: setAlpha
        Returns:
        automatically generated
      • setModelIter

        public void setModelIter​(int modelIter)
        Parameter defining the number of iterations for piece-wise affine model estimation.
        Parameters:
        modelIter - automatically generated
      • setModelIter

        public void setModelIter()
        Parameter defining the number of iterations for piece-wise affine model estimation.
      • getModelIter

        public int getModelIter()
        setModelIter SEE: setModelIter
        Returns:
        automatically generated
      • setRefineModels

        public void setRefineModels​(boolean refineModles)
        Parameter to choose wether additional refinement of the piece-wise affine models is employed.
        Parameters:
        refineModles - automatically generated
      • setRefineModels

        public void setRefineModels()
        Parameter to choose wether additional refinement of the piece-wise affine models is employed.
      • getRefineModels

        public boolean getRefineModels()
        setRefineModels SEE: setRefineModels
        Returns:
        automatically generated
      • setMaxFlow

        public void setMaxFlow​(float maxFlow)
        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.
        Parameters:
        maxFlow - automatically generated
      • setMaxFlow

        public void setMaxFlow()
        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.
      • getMaxFlow

        public float getMaxFlow()
        setMaxFlow SEE: setMaxFlow
        Returns:
        automatically generated
      • setUseVariationalRefinement

        public void setUseVariationalRefinement​(boolean use_variational_refinement)
        Parameter to choose wether the VariationalRefinement post-processing is employed.
        Parameters:
        use_variational_refinement - automatically generated
      • setUseVariationalRefinement

        public void setUseVariationalRefinement()
        Parameter to choose wether the VariationalRefinement post-processing is employed.
      • getUseVariationalRefinement

        public boolean getUseVariationalRefinement()
        setUseVariationalRefinement SEE: setUseVariationalRefinement
        Returns:
        automatically generated
      • setUseGlobalSmootherFilter

        public void setUseGlobalSmootherFilter​(boolean use_FGS)
        Sets whether the fastGlobalSmootherFilter() post-processing is employed.
        Parameters:
        use_FGS - automatically generated
      • setUseGlobalSmootherFilter

        public void setUseGlobalSmootherFilter()
        Sets whether the fastGlobalSmootherFilter() post-processing is employed.
      • getUseGlobalSmootherFilter

        public boolean getUseGlobalSmootherFilter()
        setUseGlobalSmootherFilter SEE: setUseGlobalSmootherFilter
        Returns:
        automatically generated
      • setFGSLambda

        public void setFGSLambda​(float lambda)
        Sets the respective fastGlobalSmootherFilter() parameter.
        Parameters:
        lambda - automatically generated
      • setFGSLambda

        public void setFGSLambda()
        Sets the respective fastGlobalSmootherFilter() parameter.
      • getFGSLambda

        public float getFGSLambda()
        setFGSLambda SEE: setFGSLambda
        Returns:
        automatically generated
      • setFGSSigma

        public void setFGSSigma​(float sigma)
        Sets the respective fastGlobalSmootherFilter() parameter.
        Parameters:
        sigma - automatically generated
      • setFGSSigma

        public void setFGSSigma()
        Sets the respective fastGlobalSmootherFilter() parameter.
      • getFGSSigma

        public float getFGSSigma()
        setFGSSigma SEE: setFGSSigma
        Returns:
        automatically generated