Package com.irurueta.numerical.robust

Class PROMedSRobustEstimator<T>

java.lang.Object

com.irurueta.numerical.robust.RobustEstimator<T>

com.irurueta.numerical.robust.PROMedSRobustEstimator<T>

Type Parameters:

T - type of object to be estimated.

public class PROMedSRobustEstimator<T>
extends RobustEstimator<T>

This class implements PROMedS (PROgressive least Median Sample) algorithm to robustly estimate a data model. This algorithm is a mixture between LMedS and PROSAC, taking the best of both. Firstly, it has the advantage that no threshold is required to be set beforehand, the same as LMedS. Threshold to determine inliers is computed dynamically, which helps for an easier setup that is problem independent and depending on the accuracy of the inliers, results will be more accurate than RANSAC or PROSAC, just the same as LMedS. On the other hand, if certain information about the quality of the samples is available, as in PROSAC, the algorithm takes advantage of this additional information to prioritize the samples with higher quality in order to find a solution much faster than RANSAC or LMedS. Finally, if by any chance a threshold to determine inliers is also used, the algorithm will try to get the solution that better fits in a pure median of residuals model or in a threshold based one to determine inliers. Hence, PROMedS can be as fast as PROSAC (which is typically about 100x faster than RANSAC or LMedS), can obtain the same accuracy as LMedS (which can be much better than RANSAC or PROSAC in certain scenarios), and has an easier setup, which is problem independent because no threshold is required to be known beforehand although one can be provided as well.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	PROMedSRobustEstimator.PROMedSInliersData	Contains data related to inliers estimated in one iteration.

Field Summary

Fields

Modifier and Type	Field	Description
private PROMedSRobustEstimator.PROMedSInliersData	bestInliersData	Data related to inliers found for best result.
private T	bestResult	Best solution that has been found so far during an estimation.
private double	beta	beta is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface.
static final double	CHI_SQUARED	Chi squared.
private double	confidence	Amount of confidence expressed as a value between 0 and 1.0 (which is equivalent to 100%).
static final double	DEFAULT_BETA	Defines the default value for beta, which is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface.
static final double	DEFAULT_CONFIDENCE	Constant defining default confidence of the estimated result, which is 99%.
static final double	DEFAULT_ETA0	Defines the default value for the maximum probability that a solution with more than inliersNStar in U_nStar exist and was not found after k samples.
static final double	DEFAULT_INLIER_FACTOR	Default factor to normalize threshold to determine inliers.
static final int	DEFAULT_MAX_ITERATIONS	Default maximum allowed number of iterations.
static final double	DEFAULT_MAX_OUTLIERS_PROPORTION	Default maximum allowed outliers proportion in the input data.
static final boolean	DEFAULT_STOP_THRESHOLD_ENABLED	Indicates whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener.
static final boolean	DEFAULT_USE_INLIER_THRESHOLD	Indicates whether the inlier threshold will be used to find inliers along with their median of residuals.
private double	eta0	eta0 is the maximum probability that a solution with more than inliersNStar inliers in U_nStar exists and was not found after k samples (typically set to 5%).
private double	inlierFactor	Factor to normalize threshold to determine inliers.
private int	iters	Number of iterations to be done to obtain required confidence.
static final double	MAX_BETA	Maximum allowed value for beta.
static final double	MAX_CONFIDENCE	Maximum allowed confidence value.
static final double	MAX_ETA0	Maximum allowed value for eta0.
static final double	MAX_MAX_OUTLIERS_PROPORTION	Maximum allowed value for maximum allowed outliers proportion in the input data.
private int	maxIterations	Maximum allowed number of iterations.
private double	maxOutliersProportion	In this implementation, PROSAC won't stop before having reached the corresponding inliers rate on the complete data set.
static final double	MIN_BETA	Minimum allowed value for beta.
static final double	MIN_CONFIDENCE	Minimum allowed confidence value.
static final double	MIN_ETA0	Minimum allowed value for eta0.
static final double	MIN_INLER_FACTOR	Minimum allowed value for inlier factor.
static final int	MIN_ITERATIONS	Minimum allowed number of iterations.
static final double	MIN_MAX_OUTLIERS_PROPORTION	Minimum allowed value for maximum allowed outliers proportion in the input data.
static final double	STD_CONSTANT	Constant to estimate standard deviation of residuals based on their median.
private boolean	stopThresholdEnabled	Indicates whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener.
private SubsetSelector	subsetSelector	Instance in charge of picking random subsets of samples.
private boolean	useInlierThresholds	Flag indicating whether thresholds to determine inliers are used, or if only median of residuals is used.

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

DEFAULT_PROGRESS_DELTA, listener, locked, MAX_PROGRESS_DELTA, MIN_PROGRESS_DELTA, progressDelta

Constructor Summary

Constructors

Constructor	Description
PROMedSRobustEstimator()	Constructor.
PROMedSRobustEstimator(PROMedSRobustEstimatorListener<T> listener)	Constructor with listener.

Method Summary

Modifier and Type	Method	Description
private static <T> void	computeInliers(T iterResult, int subsetSize, double inlierFactor, boolean useInlierThresholds, double inlierThreshold, double[] residualsTemp, LMedSRobustEstimatorListener<T> listener, com.irurueta.sorting.Sorter<Double> sorter, PROMedSRobustEstimator.PROMedSInliersData inliersData)	Computes inliers data for current iteration.
private static int	computeIterations(double probInlier, int subsetSize, double confidence)	Computes number of required iterations to achieve required confidence with current probability of inlier and sample subset size.
private static int[]	computeSortedQualityIndices(double[] qualityScores)	Obtains indices of samples corresponding to samples ordered in descending quality scores.
T	estimate()	Robustly estimates an instance of T.
protected PROMedSRobustEstimator.PROMedSInliersData	getBestInliersData()	Returns data related to inliers found for best result.
T	getBestResult()	Returns best solution that has been found so far during an estimation.
double	getBeta()	Returns beta, which is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface.
double	getConfidence()	Returns amount of confidence expressed as a value between 0 and 1.0 (which is equivalent to 100%).
double	getEta0()	Return eta0, which is the maximum probability that a solution with more than inliersNStar inliers in U_nStar exists and was not found after k samples (typically set to 5%).
double	getInlierFactor()	Returns factor to normalize or adjust threshold to determine inliers.
InliersData	getInliersData()	Returns data about inliers once estimation has been done.
int	getMaxIterations()	Maximum allowed number of iterations.
double	getMaxOutliersProportion()	Returns maximum allowed outliers proportion in the input data.
RobustEstimatorMethod	getMethod()	Returns method being used for robust estimation.
int	getNIters()	Returns number of iterations to be done to obtain required confidence.
private static int	imin(int subsetSize, int sampleSize, double beta)	Non randomness states that i-m (where i is the cardinal of the set of inliers for a wrong model) follows the binomial distribution B(n,beta).
boolean	isReady()	Indicates if estimator is ready to start the estimation process.
boolean	isStopThresholdEnabled()	Returns boolean indicating whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener.
boolean	isUseInlierThresholds()	Returns flag indicating whether thresholds to determine inliers are used, or if only median of residuals is used.
private void	keepInliersData(PROMedSRobustEstimator.PROMedSInliersData inliersData, int totalSamples)	Keeps inliers data stored and initializes a new one with proper initial values.
private static void	reverse(int[] array)	Reverses provided array.
void	setBeta(double beta)	Sets beta, which is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface.
void	setConfidence(double confidence)	Sets amount of confidence expressed as a value between 0 and 1.0 (which is equivalent to 100%).
void	setEta0(double eta0)	Sets eta0, which is the maximum probability that a solution with more than inliersNStar inliers in U_nStar exists and was not found after k samples (typically set to 5%).
void	setInlierFactor(double inlierFactor)	Sets factor to normalize or adjust threshold to determine inliers.
void	setMaxIterations(int maxIterations)	Sets maximum allowed number of iterations.
void	setMaxOutliersProportion(double maxOutliersProportion)	Sets maximum allowed outliers proportion in the input data.
void	setStopThresholdEnabled(boolean stopThresholdEnabled)	Sets boolean indicating whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener.
void	setUseInlierThresholds(boolean useInlierThresholds)	Sets flag indicating whether thresholds to determine inliers are used, or if only median of residuals is used.
private static void	transformIndices(int[] subsetIndices, int[] sortedIndices, int[] transformedSubsetIndices)	Transforms indices picked by the subset selector into the indices where samples are actually localed by taking into account their original position before sorting quality scores.

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

getListener, getProgressDelta, isListenerAvailable, isLocked, setListener, setProgressDelta

Methods inherited from class java.lang.Object

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

Field Details

DEFAULT_CONFIDENCE

public static final double DEFAULT_CONFIDENCE

Constant defining default confidence of the estimated result, which is 99%. This means that with a probability of 99% estimation will be accurate because chosen sub-samples will be inliers.

See Also:

• Constant Field Values

DEFAULT_MAX_ITERATIONS

public static final int DEFAULT_MAX_ITERATIONS

Default maximum allowed number of iterations.

See Also:

• Constant Field Values

MIN_CONFIDENCE

public static final double MIN_CONFIDENCE

Minimum allowed confidence value.

See Also:

• Constant Field Values

MAX_CONFIDENCE

public static final double MAX_CONFIDENCE

Maximum allowed confidence value.

See Also:

• Constant Field Values

MIN_ITERATIONS

public static final int MIN_ITERATIONS

Minimum allowed number of iterations.

See Also:

• Constant Field Values

DEFAULT_STOP_THRESHOLD_ENABLED

public static final boolean DEFAULT_STOP_THRESHOLD_ENABLED

Indicates whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener. When this flag is enabled accuracy of PROMedS worsens to a lever similar to PROSAC but the number of iterations is reduced (i.e. less computational cost). If more accuracy is desired at the expense of some additional computation cost, then disable this flag. By default, stop threshold is enabled, so that computational cost is similar to RANSAC and only accuracy gets better if inliers are more accurate.

See Also:

• Constant Field Values

DEFAULT_MAX_OUTLIERS_PROPORTION

public static final double DEFAULT_MAX_OUTLIERS_PROPORTION

Default maximum allowed outliers proportion in the input data. This is used do determine the number of required iterations.

See Also:

• Constant Field Values

MIN_MAX_OUTLIERS_PROPORTION

public static final double MIN_MAX_OUTLIERS_PROPORTION

Minimum allowed value for maximum allowed outliers proportion in the input data.

See Also:

• Constant Field Values

MAX_MAX_OUTLIERS_PROPORTION

public static final double MAX_MAX_OUTLIERS_PROPORTION

Maximum allowed value for maximum allowed outliers proportion in the input data.

See Also:

• Constant Field Values

DEFAULT_ETA0

public static final double DEFAULT_ETA0

Defines the default value for the maximum probability that a solution with more than inliersNStar in U_nStar exist and was not found after k samples.

See Also:

• Constant Field Values

MIN_ETA0

public static final double MIN_ETA0

Minimum allowed value for eta0.

See Also:

• Constant Field Values

MAX_ETA0

public static final double MAX_ETA0

Maximum allowed value for eta0.

See Also:

• Constant Field Values

DEFAULT_BETA

public static final double DEFAULT_BETA

Defines the default value for beta, which is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface. The inlier surface is a disc with radius 1.96s for homography/displacement computation, or a band with width 1.96*s*2 for epipolar geometry (s is the detection noise), and the total surface is the surface of the image.

See Also:

• Constant Field Values

MIN_BETA

public static final double MIN_BETA

Minimum allowed value for beta.

See Also:

• Constant Field Values

MAX_BETA

public static final double MAX_BETA

Maximum allowed value for beta.

See Also:

• Constant Field Values

DEFAULT_INLIER_FACTOR

public static final double DEFAULT_INLIER_FACTOR

Default factor to normalize threshold to determine inliers. This factor can be used to increase or lower the dynamically computed threshold so that the algorithm becomes more or less accurate. The stricter the threshold (lower factor), the more time the algorithm will need to converge, if it can converge. By default, the factor is 1.0, which makes the threshold to be computed as the median of residuals.

See Also:

• Constant Field Values

MIN_INLER_FACTOR

public static final double MIN_INLER_FACTOR

Minimum allowed value for inlier factor.

See Also:

• Constant Field Values

DEFAULT_USE_INLIER_THRESHOLD

public static final boolean DEFAULT_USE_INLIER_THRESHOLD

Indicates whether the inlier threshold will be used to find inliers along with their median of residuals.

See Also:

• Constant Field Values

STD_CONSTANT

public static final double STD_CONSTANT

Constant to estimate standard deviation of residuals based on their median.

See Also:

• Constant Field Values

CHI_SQUARED

public static final double CHI_SQUARED

Chi squared.

See Also:

• Constant Field Values

confidence

private double confidence

Amount of confidence expressed as a value between 0 and 1.0 (which is equivalent to 100%). The amount of confidence indicates the probability that the estimated result is correct. Usually this value will be close to 1.0, but not exactly 1.0.

maxIterations

private int maxIterations

Maximum allowed number of iterations. When the maximum number of iterations is exceeded, result will not be available, however an approximate result will be available for retrieval.

maxOutliersProportion

private double maxOutliersProportion

In this implementation, PROSAC won't stop before having reached the corresponding inliers rate on the complete data set. Maximum allowed outliers proportion in the input data: used to compute nIters (can be as high as 0.95).

eta0

private double eta0

eta0 is the maximum probability that a solution with more than inliersNStar inliers in U_nStar exists and was not found after k samples (typically set to 5%).

beta

private double beta

beta is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface. The inlier surface is a disc with radius 1.96s for homography/displacement computation, or a band with width 1.96s*2 for epipolar geometry (s is the detection noise), and the total surface is the surface of the image YOU MUST ADJUST THIS VALUE, DEPENDING ON YOUR PROBLEM!.

subsetSelector

private SubsetSelector subsetSelector

Instance in charge of picking random subsets of samples.

iters

private int iters

Number of iterations to be done to obtain required confidence.

bestResult

private T bestResult

Best solution that has been found so far during an estimation.

bestInliersData

private PROMedSRobustEstimator.PROMedSInliersData bestInliersData

Data related to inliers found for best result.

stopThresholdEnabled

private boolean stopThresholdEnabled

Indicates whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener. When this flag is enabled accuracy of PROMedS worsens to a lever similar to PROSAC but the number of iterations is reduced (i.e. less computational cost). If more accuracy is desired at the expense of some additional computation cost, then disable this flag.

inlierFactor

private double inlierFactor

Factor to normalize threshold to determine inliers. This factor can be used to increase or lower the dynamically computed threshold so that the algorithm becomes more or less accurate. The stricter the threshold (lower factor), the more time the algorithm will need to converge, if it can converge. By default, the factor is 1.0, which makes the threshold to be computed as the median of residuals.

useInlierThresholds

private boolean useInlierThresholds

Flag indicating whether thresholds to determine inliers are used, or if only median of residuals is used. When true, the algorithm will try to fit the best model, otherwise only median of residuals will be used.

Constructor Details

PROMedSRobustEstimator

public PROMedSRobustEstimator()

Constructor.

PROMedSRobustEstimator

public PROMedSRobustEstimator(PROMedSRobustEstimatorListener<T> listener)

Constructor with listener.

Parameters:

listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes, as well as in charge of picking samples and doing per-iteration estimations.

Method Details

getConfidence

public double getConfidence()

Returns amount of confidence expressed as a value between 0 and 1.0 (which is equivalent to 100%). The amount of confidence indicates the probability that the estimated result is correct. Usually this value will be close to 1.0, but not exactly 1.0.

Returns:

amount of confidence as a value between 0.0 and 1.0.

setConfidence

public void setConfidence(double confidence)
                   throws LockedException

Sets amount of confidence expressed as a value between 0 and 1.0 (which is equivalent to 100%). The amount of confidence indicates the probability that the estimated result is correct. Usually this value will be close to 1.0, but not exactly 1.0.

Parameters:

confidence - confidence to be set as a value between 0.0 and 1.0.

Throws:

IllegalArgumentException - if provided value is not between 0.0 and 1.0.

LockedException - if this estimator is locked because an estimation is being computed.

getMaxIterations

public int getMaxIterations()

Maximum allowed number of iterations. When the maximum number of iterations is exceeded, result will not be available, however an approximate result will be available for retrieval.

Returns:

maximum allowed number of iterations.

setMaxIterations

public void setMaxIterations(int maxIterations)
                      throws LockedException

Sets maximum allowed number of iterations. When the maximum number of iterations is exceeded, result will not be available, however an approximate result will be available for retrieval.

Parameters:

maxIterations - maximum allowed number of iterations to be set.

Throws:

IllegalArgumentException - if provided value is less than 1.

LockedException - if this estimator is locked because an estimation is being computed.

isStopThresholdEnabled

public boolean isStopThresholdEnabled()

Returns boolean indicating whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener. When this flag is enabled accuracy of PROMedS worsens to a lever similar to PROSAC but the number of iterations is reduced (i.e. less computational cost). If more accuracy is desired at the expense of some additional computation cost, then disable this flag.

Returns:

true if stop threshold is enabled, false otherwise.

setStopThresholdEnabled

public void setStopThresholdEnabled(boolean stopThresholdEnabled)
                             throws LockedException

Sets boolean indicating whether the algorithm must stop prematurely when dynamically computed threshold using median of residuals has a value lower than provided threshold in listener. When this flag is enabled accuracy of PROMedS worsens to a lever similar to PROSAC but the number of iterations is reduced (i.e. less computational cost). If more accuracy is desired at the expense of some additional computation cost, then disable this flag.

Parameters:

stopThresholdEnabled - true if stop threshold is enabled, false otherwise.

Throws:

LockedException - if this estimator is locked because an estimation is being computed.

getInlierFactor

public double getInlierFactor()

Returns factor to normalize or adjust threshold to determine inliers. This factor can be used to increase or lower the dynamically computed threshold so that the algorithm becomes more or less accurate. The stricter the threshold (lower factor), the more time the algorithm will need to converge, if it can converge. By default, the factor is 1.0, which makes the threshold to be computed as the median of residuals.

Returns:

factor to normalize threshold to determine inliers.

setInlierFactor

public void setInlierFactor(double inlierFactor)
                     throws LockedException

Sets factor to normalize or adjust threshold to determine inliers. This factor can be used to increase or lower the dynamically computed threshold so that the algorithm becomes more or less accurate. The stricter the threshold (lower factor), the more time the algorithm will need to converge, if it can converge. By default, the factor is 1.0, which makes the threshold to be computed as the median of residuals.

Parameters:

inlierFactor - inlier factor to be set.

Throws:

IllegalArgumentException - if provided value is less or equal than 0.0.

LockedException - if this estimator is locked because an estimation is being computed.

isUseInlierThresholds

public boolean isUseInlierThresholds()

Returns flag indicating whether thresholds to determine inliers are used, or if only median of residuals is used. When true, the algorithm will try to fit the best model, otherwise only median of residuals will be used.

Returns:

true if best model is used (threshold or median), otherwise only median of residuals will be used.

setUseInlierThresholds

public void setUseInlierThresholds(boolean useInlierThresholds)
                            throws LockedException

Sets flag indicating whether thresholds to determine inliers are used, or if only median of residuals is used. When true, the algorithm will try to fit the best model, otherwise only median of residuals will be used.

Parameters:

useInlierThresholds - true if best model is used (threshold or median), oitherwise only median of residuals will be used.

Throws:

LockedException - if this estimator is locked because an estimation is being computed.

getMaxOutliersProportion

public double getMaxOutliersProportion()

Returns maximum allowed outliers proportion in the input data. This is used to compute number of iterations to be done (nIters). It typically can be as high as 0.95. Higher values, up to 1 are possible but not recommended. In this implementation, PROSAC won't stop before having reached the corresponding inliers rate on the complete data set.

Returns:

maximum allowed outliers proportion in the input data.

setMaxOutliersProportion

public void setMaxOutliersProportion(double maxOutliersProportion)
                              throws LockedException

Sets maximum allowed outliers proportion in the input data. This is used to compute number of iterations to be done (nIters). It typically can be as high as 0.95. Higher values, up to 1 are possible but not recommended. In this implementation, PROSAC won't stop before having reached the corresponding inliers rate on the complete data set.

Parameters:

maxOutliersProportion - maximum allowed outliers proportion in the input data.

Throws:

IllegalArgumentException - if provided value is less than 0.0 or greater than 1.0.

LockedException - if this estimator is locked because an estimation is being computed.

getEta0

public double getEta0()

Return eta0, which is the maximum probability that a solution with more than inliersNStar inliers in U_nStar exists and was not found after k samples (typically set to 5%).

Returns:

eta0 value.

setEta0

public void setEta0(double eta0)
             throws LockedException

Sets eta0, which is the maximum probability that a solution with more than inliersNStar inliers in U_nStar exists and was not found after k samples (typically set to 5%).

Parameters:

eta0 - eta0 value to be set.

Throws:

IllegalArgumentException - if provided value is less than 0.0 or greater than 1.0.

LockedException - if this estimator is locked because an estimation is being computed.

getBeta

public double getBeta()

Returns beta, which is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface. The inlier surface is a disc with radius 1.96s for homography/displacement computation, or a band with width 1.96s*2 for epipolar geometry (s is the detection noise), and the total surface is the surface of the image YOU MUST ADJUST THIS VALUE, DEPENDING ON YOUR PROBLEM!

Returns:

beta value.

setBeta

public void setBeta(double beta)
             throws LockedException

Sets beta, which is the probability that a match is declared inlier by mistake, i.e. the ratio of the "inlier" surface by the total surface. The inlier surface is a disc with radius 1.96s for homography/displacement computation, or a band with width 1.96s*2 for epipolar geometry (s is the detection noise), and the total surface is the surface of the image YOU MUST ADJUST THIS VALUE, DEPENDING ON YOUR PROBLEM!

Parameters:

beta - beta value to be set.

Throws:

IllegalArgumentException - if provided value is less than 0.0 or greater than 1.0.

LockedException - if this estimator is locked because an estimation is being computed.

getNIters

public int getNIters()

Returns number of iterations to be done to obtain required confidence. This does not need to be equal to the actual number of iterations the algorithm finally required to obtain a solution.

Returns:

number of iterations to be done to obtain required confidence.

getBestResult

public T getBestResult()

Returns best solution that has been found so far during an estimation.

Returns:

best solution that has been found so far during an estimation.

getBestInliersData

protected PROMedSRobustEstimator.PROMedSInliersData getBestInliersData()

Returns data related to inliers found for best result.

Returns:

data related to inliers found for best result.

isReady

public boolean isReady()

Indicates if estimator is ready to start the estimation process.

Overrides:

isReady in class RobustEstimator<T>

Returns:

true if ready, false otherwise.

estimate

public T estimate()
           throws LockedException,
NotReadyException,
RobustEstimatorException

Robustly estimates an instance of T.

Specified by:

estimate in class RobustEstimator<T>

Returns:

estimated object.

Throws:

LockedException - if robust estimator is locked.

NotReadyException - if provided input data is not enough to start the estimation.

RobustEstimatorException - if estimation fails for any reason (i.e. numerical instability, no solution available, etc).

getInliersData

public InliersData getInliersData()

Returns data about inliers once estimation has been done.

Specified by:

getInliersData in class RobustEstimator<T>

Returns:

data about inliers or null if estimation has not been done.

getMethod

public RobustEstimatorMethod getMethod()

Returns method being used for robust estimation.

Specified by:

getMethod in class RobustEstimator<T>

Returns:

method being used for robust estimation.

transformIndices

private static void transformIndices(int[] subsetIndices,
 int[] sortedIndices,
 int[] transformedSubsetIndices)

Transforms indices picked by the subset selector into the indices where samples are actually localed by taking into account their original position before sorting quality scores.

Parameters:

subsetIndices - indices picked by the subset selector. These are positions after sorting. Must have the subset length.

sortedIndices - indices relating sorted positions to their original positions. Each position i-th in the array refers to the original position before sorting. Must have the number of samples length.

transformedSubsetIndices - array where result is stored. Must have the subset length.

computeInliers

private static <T> void computeInliers(T iterResult,
 int subsetSize,
 double inlierFactor,
 boolean useInlierThresholds,
 double inlierThreshold,
 double[] residualsTemp,
 LMedSRobustEstimatorListener<T> listener,
 com.irurueta.sorting.Sorter<Double> sorter,
 PROMedSRobustEstimator.PROMedSInliersData inliersData)

Computes inliers data for current iteration.

Type Parameters:

T - type of result to be estimated.

Parameters:

iterResult - result to be tested on current iteration.

subsetSize - subset sample size to be picked on each iteration.

inlierFactor - factor to adjust threshold to determine whether samples are inliers or not.

useInlierThresholds - true to use thresholds to determine inliers, false otherwise.

inlierThreshold - threshold to determine which samples are inliers.

residualsTemp - temporal array to store residuals, since median computation requires modifying the original array.

listener - listener to obtain residuals for samples.

sorter - sorter instance to compute median of residuals.

inliersData - inliers data to be reused on each iteration

computeSortedQualityIndices

private static int[] computeSortedQualityIndices(double[] qualityScores)
                                          throws com.irurueta.sorting.SortingException

Obtains indices of samples corresponding to samples ordered in descending quality scores.

Parameters:

qualityScores - quality scores associated to each sample to be used to obtain indices to sort samples in descending order of quality values.

Returns:

indices to sort samples in descending order of quality values.

Throws:

com.irurueta.sorting.SortingException - if sorting fails.

reverse

private static void reverse(int[] array)

Reverses provided array.

Parameters:

array - array to be reversed.

computeIterations

private static int computeIterations(double probInlier,
 int subsetSize,
 double confidence)

Computes number of required iterations to achieve required confidence with current probability of inlier and sample subset size.

Parameters:

probInlier - probability of inlier.

subsetSize - sample subset size.

confidence - required confidence of result.

Returns:

number of required iterations.

imin

private static int imin(int subsetSize,
 int sampleSize,
 double beta)

Non randomness states that i-m (where i is the cardinal of the set of inliers for a wrong model) follows the binomial distribution B(n,beta). For n big enough, B(n,beta) approximates to normal distribution N(mu, sigma^2) by the central limit theorem, with mu = n*beta and sigma = sqrt(n*beta*(1 - beta)). Psi, the probability that In_star out of n_star data points are by chance inliers to an arbitrary incorrect model, is set to 0.05 (5%, as in the original paper), and you must change the Chi2 value if you chose a different value for psi.

Parameters:

subsetSize - sample subset size.

sampleSize - total number of samples.

beta - beta value.

Returns:

i-m.

keepInliersData

private void keepInliersData(PROMedSRobustEstimator.PROMedSInliersData inliersData,
 int totalSamples)

Keeps inliers data stored and initializes a new one with proper initial values.

Parameters:

inliersData - inliers data to be stored.

totalSamples - total number of samples.