Package com.irurueta.numerical.robust

Class LMedSRobustEstimator.LMedSInliersData

java.lang.Object
com.irurueta.numerical.robust.InliersData
com.irurueta.numerical.robust.LMedSRobustEstimator.LMedSInliersData
Enclosing class:
LMedSRobustEstimator<T>
public static class LMedSRobustEstimator.LMedSInliersData extends InliersData
Contains data related to inliers estimated in one iteration.

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    private double
    bestMedianResidual
    Best median of error found so far taking into account all provided samples.
    private double
    estimatedThreshold
    Estimated threshold to determine whether samples are inliers or not.
    private BitSet
    inliers
    Efficiently stores which samples are considered inliers and which ones aren't.
    private boolean
    medianResidualImproved
    Indicates whether median residual computed in current iteration has improved respect to previous iterations.
    private double
    standardDeviation
    Standard deviation of error among all provided samples respect to currently estimated result.

    Fields inherited from class com.irurueta.numerical.robust.InliersData

    numInliers, residuals

  • Constructor Summary

    Constructors
    Modifier
    Constructor
    Description
    protected
    LMedSInliersData(int totalSamples)
    Constructor.

  • Method Summary

    Modifier and Type
    Method
    Description
    double
    getBestMedianResidual()
    Returns best median of error found so far taking into account all provided samples.
    double
    getEstimatedThreshold()
    Returns estimated threshold to determine whether samples are inliers or not.
    BitSet
    getInliers()
    Returns efficient array indicating which samples are considered inliers and which ones aren't.
    double
    getStandardDeviation()
    Returns standard deviation of error among all provided samples respect to currently estimated result.
    boolean
    isMedianResidualImproved()
    Returns boolean indicating whether median residual computed in current iteration has improved respect to previous iterations.
    protected void
    update(double bestMedianResidual, double standardDeviation, BitSet inliers, double[] residuals, int numInliers, double estimatedThreshold, boolean medianResidualImproved)
    Updates data contained in this instance.

    Methods inherited from class com.irurueta.numerical.robust.InliersData

    getNumInliers, getResiduals

    Methods inherited from class java.lang.Object

    clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

  • Field Details

    • bestMedianResidual

      private double bestMedianResidual
      Best median of error found so far taking into account all provided samples.

    • standardDeviation

      private double standardDeviation
      Standard deviation of error among all provided samples respect to currently estimated result.

    • inliers

      private BitSet inliers
      Efficiently stores which samples are considered inliers and which ones aren't.

    • estimatedThreshold

      private double estimatedThreshold
      Estimated threshold to determine whether samples are inliers or not.

    • medianResidualImproved

      private boolean medianResidualImproved
      Indicates whether median residual computed in current iteration has improved respect to previous iterations.

  • Constructor Details

    • LMedSInliersData

      protected LMedSInliersData(int totalSamples)
      Constructor.
      Parameters:
      totalSamples - total number of samples.

  • Method Details

    • getBestMedianResidual

      public double getBestMedianResidual()
      Returns best median of error found so far taking into account all provided samples.
      Returns:
      best median of error found so far taking into account all provided samples.

    • getStandardDeviation

      public double getStandardDeviation()
      Returns standard deviation of error among all provided samples respect to currently estimated result.
      Returns:
      standard deviation of error among all provided samples respect to currently estimated result.

    • getInliers

      public BitSet getInliers()
      Returns efficient array indicating which samples are considered inliers and which ones aren't.
      Specified by:
      getInliers in class InliersData
      Returns:
      array indicating which samples are considered inliers and which ones aren't.

    • getEstimatedThreshold

      public double getEstimatedThreshold()
      Returns estimated threshold to determine whether samples are inliers or not.
      Returns:
      estimated threshold to determine whether samples are inliers or not.

    • isMedianResidualImproved

      public boolean isMedianResidualImproved()
      Returns boolean indicating whether median residual computed in current iteration has improved respect to previous iterations.
      Returns:
      true if median residual improved, false otherwise.

    • update

      protected void update(double bestMedianResidual, double standardDeviation, BitSet inliers, double[] residuals, int numInliers, double estimatedThreshold, boolean medianResidualImproved)
      Updates data contained in this instance.
      Parameters:
      bestMedianResidual - best median of error found so far taking into account all provided samples.
      standardDeviation - standard deviation of error among all provided samples respect to currently estimated result.
      inliers - efficiently stores which samples are considered inliers and which ones aren't.
      residuals - residuals obtained for each sample of data.
      numInliers - number of inliers found on current iteration.
      estimatedThreshold - estimated threshold to determine whether samples are inliers or not.
      medianResidualImproved - indicates whether median residual computed in current iteration has improved respect to previous iteration.