Class BoofCVCirculant
- java.lang.Object
-
- adams.core.logging.LoggingObject
-
- adams.core.logging.CustomLoggingLevelObject
-
- adams.core.option.AbstractOptionHandler
-
- adams.flow.transformer.objecttracker.AbstractObjectTracker
-
- adams.flow.transformer.objecttracker.AbstractSimpleReportBasedObjectTracker
-
- adams.flow.transformer.objecttracker.AbstractBoofCVObjectTracker
-
- adams.flow.transformer.objecttracker.BoofCVCirculant
-
- All Implemented Interfaces:
adams.core.Destroyable
,adams.core.GlobalInfoSupporter
,adams.core.logging.LoggingLevelHandler
,adams.core.logging.LoggingSupporter
,adams.core.option.OptionHandler
,adams.core.QuickInfoSupporter
,adams.core.SizeOfHandler
,ObjectTracker
,Serializable
public class BoofCVCirculant extends AbstractBoofCVObjectTracker
Creates the Circulant feature tracker. Texture based tracker which uses the theory of circulant matrices, Discrete Fourier Transform (DCF), and linear classifiers to track a target. Fixed sized rectangular target and only estimates translation. Can't detect when it loses track or re-aquire track.
-logging-level <OFF|SEVERE|WARNING|INFO|CONFIG|FINE|FINER|FINEST> (property: loggingLevel) The logging level for outputting errors and debugging output. default: WARNING
-image-type <FLOAT_32|FLOAT_64|SIGNED_INT_8|UNSIGNED_INT_8|SIGNED_INT_16|UNSIGNED_INT_16|SIGNED_INT_32|SIGNED_INT_64> (property: imageType) The image type to use. default: UNSIGNED_INT_8
-output-sigma-factor <double> (property: outputSigmaFactor) The spatial bandwidth. Proportional to target size. default: 0.0625
-sigma <double> (property: sigma) The gaussian kernel bandwidth. default: 0.2
-lambda <double> (property: lambda) The regularization term. default: 0.01
-interp-factor <double> (property: interpFactor) The weighting factor mixing old track image and new one. Effectively adjusts the rate at which it can adjust to changes in appearance. Values closer to zero slow down the rate of change. 0.0 is no update. 0.075 is recommended. default: 0.075
-max-pixel-value <double> (property: maxPixelValue) The maximum pixel value. Used to normalize image. 8-bit images are 255. default: 255.0
-padding <double> (property: padding) How much padding is added around the region requested by the user. Specified as fraction of original image. Padding of 1 = 2x original size. default: 1.0 minimum: 0.0
-work-space <int> (property: workSpace) The length of size in work space image. A total of N*N points are sampled. Should be set to a power of two to maximize speed. In general, larger numbers are more stable but slower. default: 64 minimum: 1
- Author:
- FracPete (fracpete at waikato dot ac dot nz)
- See Also:
- Serialized Form
-
-
Field Summary
Fields Modifier and Type Field Description protected double
m_InterpFactor
Weighting factor mixing old track image and new one.protected double
m_Lambda
Regularization term.protected double
m_MaxPixelValue
Maximum pixel value.protected double
m_OutputSigmaFactor
Spatial bandwidth.protected double
m_Padding
How much padding is added around the region requested by the user.protected double
m_Sigma
gaussian kernel bandwidth.protected int
m_WorkSpace
Length of size in work space image.-
Fields inherited from class adams.flow.transformer.objecttracker.AbstractBoofCVObjectTracker
m_ImageType, m_Tracker
-
Fields inherited from class adams.flow.transformer.objecttracker.AbstractSimpleReportBasedObjectTracker
m_Current, m_Init
-
Fields inherited from class adams.flow.transformer.objecttracker.AbstractObjectTracker
m_Initialized, m_LastLocations
-
-
Constructor Summary
Constructors Constructor Description BoofCVCirculant()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description void
defineOptions()
Adds options to the internal list of options.double
getInterpFactor()
Returns the weighting factor mixing old track image and new one.double
getLambda()
Returns the regularization term.double
getMaxPixelValue()
Returns the maximum pixel value.double
getOutputSigmaFactor()
Returns the spatial bandwidth.double
getPadding()
Returns the padding added around the region.double
getSigma()
Returns the gaussian kernel bandwidth.int
getWorkSpace()
Returns the gaussian kernel bandwidth.String
globalInfo()
Returns a string describing the object.String
interpFactorTipText()
Returns the tip text for this property.String
lambdaTipText()
Returns the tip text for this property.String
maxPixelValueTipText()
Returns the tip text for this property.protected boofcv.abst.tracker.TrackerObjectQuad
newTracker()
Instantiates a new tracker.String
outputSigmaFactorTipText()
Returns the tip text for this property.String
paddingTipText()
Returns the tip text for this property.void
setInterpFactor(double value)
Sets the weighting factor mixing old track image and new one.void
setLambda(double value)
Sets the regularization term.void
setMaxPixelValue(double value)
Sets the maximum pixel value.void
setOutputSigmaFactor(double value)
Sets the spatial bandwidth.void
setPadding(double value)
Sets the padding added around the region.void
setSigma(double value)
Sets the gaussian kernel bandwidth.void
setWorkSpace(int value)
Sets the gaussian kernel bandwidth.String
sigmaTipText()
Returns the tip text for this property.String
workSpaceTipText()
Returns the tip text for this property.-
Methods inherited from class adams.flow.transformer.objecttracker.AbstractBoofCVObjectTracker
doInitTracking, doTrackObjects, getImageType, imageTypeTipText, setImageType
-
Methods inherited from class adams.flow.transformer.objecttracker.AbstractSimpleReportBasedObjectTracker
currentTipText, getCurrent, getInit, getInitialLocations, getQuickInfo, initTipText, postProcessTrackedObjects, setCurrent, setInit
-
Methods inherited from class adams.flow.transformer.objecttracker.AbstractObjectTracker
checkInitTracking, checkTrackObjects, initTracking, isInitialized, reset, trackObjects
-
Methods inherited from class adams.core.option.AbstractOptionHandler
cleanUpOptions, destroy, finishInit, getDefaultLoggingLevel, getOptionManager, initialize, loggingLevelTipText, newOptionManager, setLoggingLevel, toCommandLine, toString
-
Methods inherited from class adams.core.logging.LoggingObject
configureLogger, getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled, sizeOf
-
-
-
-
Field Detail
-
m_OutputSigmaFactor
protected double m_OutputSigmaFactor
Spatial bandwidth. Proportional to target size.
-
m_Sigma
protected double m_Sigma
gaussian kernel bandwidth.
-
m_Lambda
protected double m_Lambda
Regularization term.
-
m_InterpFactor
protected double m_InterpFactor
Weighting factor mixing old track image and new one. Effectively adjusts the rate at which it can adjust to changes in appearance. Values closer to zero slow down the rate of change. 0f is no update. 0.075f is recommended.
-
m_MaxPixelValue
protected double m_MaxPixelValue
Maximum pixel value. Used to normalize image. 8-bit images are 255
-
m_Padding
protected double m_Padding
How much padding is added around the region requested by the user. Specified as fraction of original image. Padding of 1 = 2x original size.
-
m_WorkSpace
protected int m_WorkSpace
Length of size in work space image. A total of N*N points are sampled. Should be set to a power of two to maximize speed. In general, larger numbers are more stable but slower.
-
-
Method Detail
-
globalInfo
public String globalInfo()
Returns a string describing the object.- Specified by:
globalInfo
in interfaceadams.core.GlobalInfoSupporter
- Specified by:
globalInfo
in classadams.core.option.AbstractOptionHandler
- Returns:
- a description suitable for displaying in the gui
-
defineOptions
public void defineOptions()
Adds options to the internal list of options.- Specified by:
defineOptions
in interfaceadams.core.option.OptionHandler
- Overrides:
defineOptions
in classAbstractBoofCVObjectTracker
-
setOutputSigmaFactor
public void setOutputSigmaFactor(double value)
Sets the spatial bandwidth. Proportional to target size.- Parameters:
value
- the bandwidth
-
getOutputSigmaFactor
public double getOutputSigmaFactor()
Returns the spatial bandwidth. Proportional to target size.- Returns:
- the bandwidth
-
outputSigmaFactorTipText
public String outputSigmaFactorTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
setSigma
public void setSigma(double value)
Sets the gaussian kernel bandwidth.- Parameters:
value
- the bandwidth
-
getSigma
public double getSigma()
Returns the gaussian kernel bandwidth.- Returns:
- the bandwidth
-
sigmaTipText
public String sigmaTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
setLambda
public void setLambda(double value)
Sets the regularization term.- Parameters:
value
- the term
-
getLambda
public double getLambda()
Returns the regularization term.- Returns:
- the term
-
lambdaTipText
public String lambdaTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
setInterpFactor
public void setInterpFactor(double value)
Sets the weighting factor mixing old track image and new one.- Parameters:
value
- the factor
-
getInterpFactor
public double getInterpFactor()
Returns the weighting factor mixing old track image and new one.- Returns:
- the factor
-
interpFactorTipText
public String interpFactorTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
setMaxPixelValue
public void setMaxPixelValue(double value)
Sets the maximum pixel value. Used to normalize image. 8-bit images are 255.- Parameters:
value
- the maximum
-
getMaxPixelValue
public double getMaxPixelValue()
Returns the maximum pixel value. Used to normalize image. 8-bit images are 255.- Returns:
- the maximum
-
maxPixelValueTipText
public String maxPixelValueTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
setPadding
public void setPadding(double value)
Sets the padding added around the region.- Parameters:
value
- the padding
-
getPadding
public double getPadding()
Returns the padding added around the region.- Returns:
- the padding
-
paddingTipText
public String paddingTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
setWorkSpace
public void setWorkSpace(int value)
Sets the gaussian kernel bandwidth.- Parameters:
value
- the bandwidth
-
getWorkSpace
public int getWorkSpace()
Returns the gaussian kernel bandwidth.- Returns:
- the bandwidth
-
workSpaceTipText
public String workSpaceTipText()
Returns the tip text for this property.- Returns:
- tip text for this property suitable for displaying in the GUI or for listing the options.
-
newTracker
protected boofcv.abst.tracker.TrackerObjectQuad newTracker()
Instantiates a new tracker.- Specified by:
newTracker
in classAbstractBoofCVObjectTracker
- Returns:
- the tracker
-
-