Package com.irurueta.geometry.estimators

Class PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

java.lang.Object
com.irurueta.geometry.estimators.AffineTransformation3DRobustEstimator
com.irurueta.geometry.estimators.PlaneCorrespondenceAffineTransformation3DRobustEstimator
com.irurueta.geometry.estimators.PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator
public class PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator extends PlaneCorrespondenceAffineTransformation3DRobustEstimator
Finds the best affine 3D transformation for provided collections of matched planes using PROSAC algorithm.

  • Field Details

    • DEFAULT_THRESHOLD

      public static final double DEFAULT_THRESHOLD
      Constant defining default threshold to determine whether planes are inliers or not. Residuals to determine whether planes are inliers or not are computed by comparing two planes algebraically (e.g. doing the dot product of their parameters). A residual of 0 indicates that dot product was 1 or -1 and planes were equal. A residual of 1 indicates that dot product was 0 and planes were orthogonal. If dot product between lines is -1, then although their director vectors are opposed, planes are considered equal, since sign changes are not taken into account and their residuals will be 0.
      See Also:

    • MIN_THRESHOLD

      public static final double MIN_THRESHOLD
      Minimum value that can be set as threshold. Threshold must be strictly greater than 0.0.
      See Also:

    • DEFAULT_COMPUTE_AND_KEEP_INLIERS

      public static final boolean DEFAULT_COMPUTE_AND_KEEP_INLIERS
      Indicates that by default inliers will only be computed but not kept.
      See Also:

    • DEFAULT_COMPUTE_AND_KEEP_RESIDUALS

      public static final boolean DEFAULT_COMPUTE_AND_KEEP_RESIDUALS
      Indicates that by default residuals will only be computed but not kept.
      See Also:

    • threshold

      private double threshold
      Threshold to determine whether planes are inliers or not when testing possible estimation solutions. The threshold refers to the amount of error (i.e. distance and director vector angle difference) a possible solution has on a matched pair of planes.

    • qualityScores

      private double[] qualityScores
      Quality scores corresponding to each pair of matched planes. The larger the score value the better the quality of the matching.

    • computeAndKeepInliers

      private boolean computeAndKeepInliers
      Indicates whether inliers must be computed and kept.

    • computeAndKeepResiduals

      private boolean computeAndKeepResiduals
      Indicates whether residuals must be computed and kept.

  • Constructor Details

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator()
      Constructor.

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(List<Plane> inputPlanes, List<Plane> outputPlanes)
      Constructor with lists of planes to be used to estimate an affine 3D transformation. Planes in the list located at the same position are considered to be matched. Hence, both lists must have the same size, and their size must be greater or equal than MINIMUM_SIZE.
      Parameters:
      inputPlanes - list of input planes to be used to estimate an affine 3D transformation.
      outputPlanes - list of output planes to be used to estimate an affine 3D transformation.
      Throws:
      IllegalArgumentException - if provided lists of planes don't have the same size or their size is smaller than MINIMUM_SIZE.

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(AffineTransformation3DRobustEstimatorListener listener)
      Constructor.
      Parameters:
      listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes.

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(AffineTransformation3DRobustEstimatorListener listener, List<Plane> inputPlanes, List<Plane> outputPlanes)
      Constructor with listener and lists of planes to be used to estimate an affine 3D transformation. Planes in the list located at the same position are considered to be matched. Hence, both lists must have the same size, and their size must be greater or equal than MINIMUM_SIZE.
      Parameters:
      listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes.
      inputPlanes - list of input planes to be used to estimate an affine 3D transformation.
      outputPlanes - list of output planes to be used to estimate an affine 3D transformation.
      Throws:
      IllegalArgumentException - if provided lists of lines don't have the same size or their size is smaller than MINIMUM_SIZE.

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(double[] qualityScores)
      Constructor.
      Parameters:
      qualityScores - quality scores corresponding to each pair of matched points.
      Throws:
      IllegalArgumentException - if provided quality scores length is smaller than MINIMUM_SIZE (i.e. 3 samples).

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(List<Plane> inputPlanes, List<Plane> outputPlanes, double[] qualityScores)
      Constructor with lists of planes to be used to estimate an affine 2D transformation. Lines in the list located at the same position are considered to be matched. Hence, both lists must have the same size, and their size must be greater or equal than MINIMUM_SIZE.
      Parameters:
      inputPlanes - list of input planes to be used to estimate an affine 3D transformation.
      outputPlanes - list of output planes to be used to estimate an affine 3D transformation.
      qualityScores - quality scores corresponding to each pair of matched lines.
      Throws:
      IllegalArgumentException - if provided lists of planes and array of quality scores don't have the same size or their size is smaller than MINIMUM_SIZE.

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(AffineTransformation3DRobustEstimatorListener listener, double[] qualityScores)
      Constructor.
      Parameters:
      listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes.
      qualityScores - quality scores corresponding to each pair of matched lines.
      Throws:
      IllegalArgumentException - if provided quality scores length is smaller than MINIMUM_SIZE (i.e. 3 samples).

    • PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator

      public PROSACPlaneCorrespondenceAffineTransformation3DRobustEstimator(AffineTransformation3DRobustEstimatorListener listener, List<Plane> inputPlanes, List<Plane> outputPlanes, double[] qualityScores)
      Constructor with listener and lists of planes to be used to estimate an affine 3D transformation. Planes in the list located at the same position are considered to be matched. Hence, both lists must have the same size, and their size must be greater or equal than MINIMUM_SIZE.
      Parameters:
      listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes.
      inputPlanes - list of input planes to be used to estimate an affine 3D transformation.
      outputPlanes - list of output planes to be used to estimate an affine 3D transformation.
      qualityScores - quality scores corresponding to each pair of matched lines.
      Throws:
      IllegalArgumentException - if provided lists of points don't have the same size or their size is smaller than MINIMUM_SIZE.

  • Method Details

    • getThreshold

      public double getThreshold()
      Returns threshold to determine whether planes are inliers or not when testing possible estimation solutions. Residuals to determine whether planes are inliers or not are computed by comparing two planes algebraically (e.g. doing the dot product of their parameters). A residual of 0 indicates that dot product was 1 or -1 and planes were equal. A residual of 1 indicates that dot product was 0 and planes were orthogonal. If dot product between lines is -1, then although their director vectors are opposed, planes are considered equal, since sign changes are not taken into account and their residuals will be 0.
      Returns:
      threshold to determine whether matched planes are inliers or not.

    • setThreshold

      public void setThreshold(double threshold) throws LockedException
      Sets threshold to determine whether planes are inliers or not when testing possible estimation solutions. Residuals to determine whether planes are inliers or not are computed by comparing two planes algebraically (e.g. doing the dot product of their parameters). A residual of 0 indicates that dot product was 1 or -1 and planes were equal. A residual of 1 indicates that dot product was 0 and planes were orthogonal. If dot product between planes is -1, then although their director vectors are opposed, planes are considered equal, since sign changes are not taken into account and their residuals will be 0.
      Parameters:
      threshold - threshold to determine whether matched planes are inliers or not.
      Throws:
      IllegalArgumentException - if provided value is equal or less than zero.
      LockedException - if robust estimator is locked because an estimation is already in progress.

    • getQualityScores

      public double[] getQualityScores()
      Returns quality scores corresponding to each pair of matched planes. The larger the score value the better the quality of the matching.
      Overrides:
      getQualityScores in class PlaneCorrespondenceAffineTransformation3DRobustEstimator
      Returns:
      quality scores corresponding to each pair of matched planes.

    • setQualityScores

      public void setQualityScores(double[] qualityScores) throws LockedException
      Sets quality scores corresponding to each pair of matched planes. The larger the score value the better the quality of the matching.
      Overrides:
      setQualityScores in class PlaneCorrespondenceAffineTransformation3DRobustEstimator
      Parameters:
      qualityScores - quality scores corresponding to each pair of matched planes.
      Throws:
      LockedException - if robust estimator is locked because an estimation is already in progress.
      IllegalArgumentException - if provided quality scores length is smaller than MINIMUM_SIZE (i.e. 3 samples).

    • isReady

      public boolean isReady()
      Indicates if estimator is ready to start the affine 3D transformation estimation. This is true when input data (i.e. lists of matched planes and quality scores) are provided and a minimum of MINIMUM_SIZE planes are available.
      Overrides:
      isReady in class PlaneCorrespondenceAffineTransformation3DRobustEstimator
      Returns:
      true if estimator is ready, false otherwise.

    • isComputeAndKeepInliersEnabled

      public boolean isComputeAndKeepInliersEnabled()
      Indicates whether inliers must be computed and kept.
      Returns:
      true if inliers must be computed and kept, false if inliers only need to be computed but not kept.

    • setComputeAndKeepInliersEnabled

      public void setComputeAndKeepInliersEnabled(boolean computeAndKeepInliers) throws LockedException
      Specifies whether inliers must be computed and kept.
      Parameters:
      computeAndKeepInliers - true if inliers must be computed and kept, false if inliers only need to be computed but not kept.
      Throws:
      LockedException - if estimator is locked.

    • isComputeAndKeepResidualsEnabled

      public boolean isComputeAndKeepResidualsEnabled()
      Indicates whether residuals must be computed and kept.
      Returns:
      true if residuals must be computed and kept, false if residuals only need to be computed but not kept.

    • setComputeAndKeepResidualsEnabled

      public void setComputeAndKeepResidualsEnabled(boolean computeAndKeepResiduals) throws LockedException
      Specifies whether residuals must be computed and kept.
      Parameters:
      computeAndKeepResiduals - true if residuals must be computed and kept, false if residuals only need to be computed but not kept.
      Throws:
      LockedException - if estimator is locked.

    • estimate

      public AffineTransformation3D estimate() throws LockedException, NotReadyException, com.irurueta.numerical.robust.RobustEstimatorException
      Estimates an affine 3D transformation using a robust estimator and the best set of matched 3D planes correspondences found using the robust estimator.
      Specified by:
      estimate in class AffineTransformation3DRobustEstimator
      Returns:
      an affine 3D transformation.
      Throws:
      LockedException - if robust estimator is locked because an estimation is already in progress.
      NotReadyException - if provided input data is not enough to start the estimation.
      com.irurueta.numerical.robust.RobustEstimatorException - if estimation fails for any reason (i.e. numerical instability, no solution available, etc).

    • getMethod

      public com.irurueta.numerical.robust.RobustEstimatorMethod getMethod()
      Returns method being used for robust estimation.
      Specified by:
      getMethod in class AffineTransformation3DRobustEstimator
      Returns:
      method being used for robust estimation.

    • getRefinementStandardDeviation

      protected double getRefinementStandardDeviation()
      Gets standard deviation used for Levenberg-Marquardt fitting during refinement. Returned value gives an indication of how much variance each residual has. Typically, this value is related to the threshold used on each robust estimation, since residuals of found inliers are within the range of such threshold.
      Specified by:
      getRefinementStandardDeviation in class AffineTransformation3DRobustEstimator
      Returns:
      standard deviation used for refinement.

    • internalSetQualityScores

      private void internalSetQualityScores(double[] qualityScores)
      Sets quality scores corresponding to each pair of matched lines. This method is used internally and does not check whether instance is locked or not.
      Parameters:
      qualityScores - quality scores to be set.
      Throws:
      IllegalArgumentException - if provided quality scores length is smaller than MINIMUM_SIZE.