Package com.irurueta.geometry.estimators

Class LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator

java.lang.Object

com.irurueta.geometry.estimators.PinholeCameraRobustEstimator

com.irurueta.geometry.estimators.LinePlaneCorrespondencePinholeCameraRobustEstimator

com.irurueta.geometry.estimators.DLTLinePlaneCorrespondencePinholeCameraRobustEstimator

com.irurueta.geometry.estimators.LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator

public class LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator
extends DLTLinePlaneCorrespondencePinholeCameraRobustEstimator

Finds the best pinhole camera for provided collections of matched lines and planes using LMedS algorithm.

Field Summary

Fields

Modifier and Type	Field	Description
static final double	DEFAULT_STOP_THRESHOLD	Default value to be used for stop threshold.
static final double	MIN_STOP_THRESHOLD	Minimum allowed stop threshold value.
private double	stopThreshold	Threshold to be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough.

Fields inherited from class com.irurueta.geometry.estimators.LinePlaneCorrespondencePinholeCameraRobustEstimator

DEFAULT_ROBUST_METHOD, lines, MIN_NUMBER_OF_LINE_PLANE_CORRESPONDENCES, planes

Fields inherited from class com.irurueta.geometry.estimators.PinholeCameraRobustEstimator

confidence, covariance, DEFAULT_CONFIDENCE, DEFAULT_KEEP_COVARIANCE, DEFAULT_MAX_ITERATIONS, DEFAULT_PROGRESS_DELTA, DEFAULT_REFINE_RESULT, DEFAULT_SUGGEST_ASPECT_RATIO_ENABLED, DEFAULT_SUGGEST_CENTER_ENABLED, DEFAULT_SUGGEST_HORIZONTAL_FOCAL_LENGTH_ENABLED, DEFAULT_SUGGEST_PRINCIPAL_POINT_ENABLED, DEFAULT_SUGGEST_ROTATION_ENABLED, DEFAULT_SUGGEST_SKEWNESS_VALUE_ENABLED, DEFAULT_SUGGEST_VERTICAL_FOCAL_LENGTH_ENABLED, DEFAULT_SUGGESTED_ASPECT_RATIO_VALUE, DEFAULT_SUGGESTED_SKEWNESS_VALUE, DEFAULT_USE_FAST_REFINEMENT, inliersData, keepCovariance, listener, locked, MAX_CONFIDENCE, MAX_PROGRESS_DELTA, maxIterations, MIN_CONFIDENCE, MIN_ITERATIONS, MIN_PROGRESS_DELTA, progressDelta, refineResult, suggestAspectRatioEnabled, suggestCenterEnabled, suggestedAspectRatioValue, suggestedCenterValue, suggestedHorizontalFocalLengthValue, suggestedPrincipalPointValue, suggestedRotationValue, suggestedSkewnessValue, suggestedVerticalFocalLengthValue, suggestHorizontalFocalLengthEnabled, suggestPrincipalPointEnabled, suggestRotationEnabled, suggestSkewnessValueEnabled, suggestVerticalFocalLengthEnabled, useFastRefinement

Constructor Summary

Constructors

Constructor	Description
LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator()	Constructor.
LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator(PinholeCameraRobustEstimatorListener listener)	Constructor with listener.
LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator(PinholeCameraRobustEstimatorListener listener, List<Plane> planes, List<Line2D> lines)	Constructor with listener and lists of matched planes and 2D lines to estimate a pinhole camera.
LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator(List<Plane> planes, List<Line2D> lines)	Constructor with lists of matched planes and 2D lines to estimate a pinhole camera.

Method Summary

Modifier and Type	Method	Description
PinholeCamera	estimate()	Estimates a pinhole camera using a robust estimator and the best set of matched 2D line/3D plane correspondences found using the robust estimator.
com.irurueta.numerical.robust.RobustEstimatorMethod	getMethod()	Returns method being used for robust estimation.
protected double	getRefinementStandardDeviation()	Gets standard deviation used for Levenberg-Marquardt fitting during refinement.
double	getStopThreshold()	Returns threshold to be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough.
void	setStopThreshold(double stopThreshold)	Sets threshold to be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough.

Methods inherited from class com.irurueta.geometry.estimators.DLTLinePlaneCorrespondencePinholeCameraRobustEstimator

create, create, create, create, create, create, create, create, create, create, create, create, create, create, create, create

Methods inherited from class com.irurueta.geometry.estimators.LinePlaneCorrespondencePinholeCameraRobustEstimator

attemptRefine, getLines, getPlanes, getQualityScores, isReady, setLinesAndPlanes, setQualityScores, singleBackprojectionResidual

Methods inherited from class com.irurueta.geometry.estimators.PinholeCameraRobustEstimator

createFromPlanesAndLines, createFromPlanesAndLines, createFromPlanesAndLines, createFromPlanesAndLines, createFromPlanesAndLines, createFromPlanesAndLines, createFromPlanesAndLines, createFromPlanesAndLines, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, createFromPoints, getConfidence, getCovariance, getInliersData, getListener, getMaxIterations, getProgressDelta, getSuggestedAspectRatioValue, getSuggestedCenterValue, getSuggestedHorizontalFocalLengthValue, getSuggestedPrincipalPointValue, getSuggestedRotationValue, getSuggestedSkewnessValue, getSuggestedVerticalFocalLengthValue, hasSuggestions, isCovarianceKept, isFastRefinementUsed, isListenerAvailable, isLocked, isResultRefined, isSuggestAspectRatioEnabled, isSuggestCenterEnabled, isSuggestHorizontalFocalLengthEnabled, isSuggestPrincipalPointEnabled, isSuggestRotationEnabled, isSuggestSkewnessValueEnabled, isSuggestVerticalFocalLengthEnabled, setConfidence, setCovarianceKept, setFastRefinementUsed, setListener, setMaxIterations, setProgressDelta, setResultRefined, setSuggestAspectRatioEnabled, setSuggestCenterEnabled, setSuggestedAspectRatioValue, setSuggestedCenterValue, setSuggestedHorizontalFocalLengthValue, setSuggestedPrincipalPointValue, setSuggestedRotationValue, setSuggestedSkewnessValue, setSuggestedVerticalFocalLengthValue, setSuggestHorizontalFocalLengthEnabled, setSuggestPrincipalPointEnabled, setSuggestRotationEnabled, setSuggestSkewnessValueEnabled, setSuggestVerticalFocalLengthEnabled

Methods inherited from class java.lang.Object

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

Field Details

DEFAULT_STOP_THRESHOLD

public static final double DEFAULT_STOP_THRESHOLD

Default value to be used for stop threshold. Stop threshold can be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough. Once a solution is found that generates a threshold below this value, the algorithm will stop. The stop threshold can be used to prevent the LMedS algorithm iterating too many times in cases where samples have a very similar accuracy. For instance, in cases where proportion of outliers is very small (close to 0%), and samples are very accurate (i.e. 1e-6), the algorithm would iterate for a long time trying to find the best solution when indeed there is no need to do that if a reasonable threshold has already been reached. Because of this behaviour the stop threshold can be set to a value much lower than the one typically used in RANSAC, and yet the algorithm could still produce even smaller thresholds in estimated results.

See Also:

• Constant Field Values

MIN_STOP_THRESHOLD

public static final double MIN_STOP_THRESHOLD

Minimum allowed stop threshold value.

See Also:

• Constant Field Values

stopThreshold

private double stopThreshold

Threshold to be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough. Once a solution is found that generates a threshold below this value, the algorithm will stop. The stop threshold can be used to prevent the LMedS algorithm iterating too many times in cases where samples have a very similar accuracy. For instance, in cases where proportion of outliers is very small (close to 0%), and samples are very accurate (i.e. 1e-6), the algorithm would iterate for a long time trying to find the best solution when indeed there is no need to do that if a reasonable threshold has already been reached. Because of this behaviour the stop threshold can be set to a value much lower than the one typically used in RANSAC, and yet the algorithm could still produce even smaller thresholds in estimated results.

Constructor Details

LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator

public LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator()

Constructor.

LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator

public LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator(List<Plane> planes,
 List<Line2D> lines)

Constructor with lists of matched planes and 2D lines to estimate a pinhole camera. Points and lines in the lists 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 MIN_NUMBER_OF_LINE_PLANE_CORRESPONDENCES (4 matches).

Parameters:

planes - list of planes used to estimate a pinhole camera.

lines - list of corresponding projected 2D lines used to estimate a pinhole camera.

Throws:

IllegalArgumentException - if provided lists don't have the same size or their size is smaller than required minimum size (4 matches).

LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator

public LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator(PinholeCameraRobustEstimatorListener listener)

Constructor with listener.

Parameters:

listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes.

LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator

public LMedSDLTLinePlaneCorrespondencePinholeCameraRobustEstimator(PinholeCameraRobustEstimatorListener listener,
 List<Plane> planes,
 List<Line2D> lines)

Constructor with listener and lists of matched planes and 2D lines to estimate a pinhole camera. Points and lines in the lists 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 MIN_NUMBER_OF_LINE_PLANE_CORRESPONDENCES (4 matches).

Parameters:

listener - listener to be notified of events such as when estimation starts, ends or its progress significantly changes.

planes - list of planes used to estimate a pinhole camera.

lines - list of corresponding projected 2D lines used to estimate a pinhole camera.

Throws:

IllegalArgumentException - if provided lists don't have the same size or their size is smaller than required minimum size (4 matches).

Method Details

getStopThreshold

public double getStopThreshold()

Returns threshold to be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough. Once a solution is found that generates a threshold below this value, the algorithm will stop. The stop threshold can be used to prevent the LMedS algorithm iterating too many times in cases where samples have a very similar accuracy. For instance, in cases where proportion of outliers is very small (close to 0%), and samples are very accurate (i.e. 1e-6), the algorithm would iterate for a long time trying to find the best solution when indeed there is no need to do that if a reasonable threshold has already been reached. Because of this behaviour the stop threshold can be set to a value much lower than the one typically used in RANSAC, and yet the algorithm could still produce even smaller thresholds in estimated results.

Returns:

stop threshold to stop the algorithm prematurely when a certain accuracy has been reached.

setStopThreshold

public void setStopThreshold(double stopThreshold)
                      throws LockedException

Sets threshold to be used to keep the algorithm iterating in case that best estimated threshold using median of residuals is not small enough. Once a solution is found that generates a threshold below this value, the algorithm will stop. The stop threshold can be used to prevent the LMedS algorithm iterating too many times in cases where samples have a very similar accuracy. For instance, in cases where proportion of outliers is very small (close to 0%), and samples are very accurate (i.e. 1e-6), the algorithm would iterate for a long time trying to find the best solution when indeed there is no need to do that if a reasonable threshold has already been reached. Because of this behaviour the stop threshold can be set to a value much lower than the one typically used in RANSAC, and yet the algorithm could still produce even smaller thresholds in estimated results.

Parameters:

stopThreshold - stop threshold to stop the algorithm prematurely when a certain accuracy has been reached.

Throws:

IllegalArgumentException - if provided value is zero or negative.

LockedException - if robust estimator is locked because an estimation is already in progress.

estimate

public PinholeCamera estimate()
                       throws LockedException,
NotReadyException,
com.irurueta.numerical.robust.RobustEstimatorException

Estimates a pinhole camera using a robust estimator and the best set of matched 2D line/3D plane correspondences found using the robust estimator.

Specified by:

estimate in class PinholeCameraRobustEstimator

Returns:

a pinhole camera.

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 PinholeCameraRobustEstimator

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 PinholeCameraRobustEstimator

Returns:

standard deviation used for refinement.