C# Class Emgu.CV.Features2D.SURFTracker

Inheritance: DisposableObject

Public Methods

Method	Description
CamShiftTrack ( SURFFeature observedFeatures, MCvBox2D initRegion, Single>.Image priorMask ) : HomographyMatrix	Use camshift to track the feature
Detect ( SURFFeature observedFeatures, double uniquenessThreshold ) : HomographyMatrix	Detect the if the model features exist in the observed features. If true, an homography matrix is returned, otherwise, null is returned.
GetHomographyMatrixFromMatchedFeatures ( MatchedSURFFeature matchedFeatures ) : HomographyMatrix	Recover the homography matrix using RANDSAC. If the matrix cannot be recovered, null is returned.
MatchFeature ( SURFFeature observedFeatures, int k, int emax ) : MatchedSURFFeature[]	Match the SURF feature from the observed image to the features from the model image
SURFTracker ( SURFFeature modelFeatures ) : System	Create a SURF tracker, where SURF is matched with flann
VoteForSizeAndOrientation ( MatchedSURFFeature matchedFeatures, double scaleIncrement, int rotationBins ) : MatchedSURFFeature[]	Eliminate the matched features whose scale and rotation do not aggree with the majority's scale and rotation.
VoteForUniqueness ( MatchedSURFFeature matchedFeatures, double uniquenessThreshold ) : MatchedSURFFeature[]	Filter the matched Features, such that if a match is not unique, it is rejected.

Method	Description
DisposeObject ( ) : void	Release unmanaged memory
ReleaseManagedResources ( ) : void	Release the memory assocaited with this SURF Tracker

Use camshift to track the feature

public CamShiftTrack ( SURFFeature observedFeatures, MCvBox2D initRegion, Single>.Image priorMask ) : HomographyMatrix
observedFeatures	SURFFeature	The feature found from the observed image
initRegion	MCvBox2D	The predicted location of the model in the observed image. If not known, use MCvBox2D.Empty as default
priorMask	Single>.Image	The mask that should be the same size as the observed image. Contains a priori value of the probability a match can be found. If you are not sure, pass an image fills with 1.0s
return	HomographyMatrix

Detect the if the model features exist in the observed features. If true, an homography matrix is returned, otherwise, null is returned.

public Detect ( SURFFeature observedFeatures, double uniquenessThreshold ) : HomographyMatrix
observedFeatures	SURFFeature	The observed features
uniquenessThreshold	double	The distance different ratio which a match is consider unique, a good number will be 0.8
return	HomographyMatrix

Release unmanaged memory

protected DisposeObject ( ) : void
return	void

Recover the homography matrix using RANDSAC. If the matrix cannot be recovered, null is returned.

public static GetHomographyMatrixFromMatchedFeatures ( MatchedSURFFeature matchedFeatures ) : HomographyMatrix
matchedFeatures	MatchedSURFFeature	The Matched Features, only the first ModelFeature will be considered
return	HomographyMatrix

Match the SURF feature from the observed image to the features from the model image

public MatchFeature ( SURFFeature observedFeatures, int k, int emax ) : MatchedSURFFeature[]
observedFeatures	SURFFeature	The SURF feature from the observed image
k	int	The number of neighbors to find
emax	int	For k-d tree only: the maximum number of leaves to visit.
return	MatchedSURFFeature[]

Release the memory assocaited with this SURF Tracker

protected ReleaseManagedResources ( ) : void
return	void

Create a SURF tracker, where SURF is matched with flann

public SURFTracker ( SURFFeature modelFeatures ) : System
modelFeatures	SURFFeature	The SURF feature from the model image
return	System

Eliminate the matched features whose scale and rotation do not aggree with the majority's scale and rotation.

public static VoteForSizeAndOrientation ( MatchedSURFFeature matchedFeatures, double scaleIncrement, int rotationBins ) : MatchedSURFFeature[]
matchedFeatures	MatchedSURFFeature	The matched feature that will be participated in the voting. For each matchedFeatures, only the zero indexed ModelFeature will be considered.
scaleIncrement	double	This determins the different in scale for neighbour hood bins, a good value might be 1.5 (which means matched features in bin i+1 is scaled 1.5 times larger than matched features in bin i
rotationBins	int	The numbers of bins for rotation, a good value might be 20 (which means each bin covers 18 degree)
return	MatchedSURFFeature[]

Filter the matched Features, such that if a match is not unique, it is rejected.

public static VoteForUniqueness ( MatchedSURFFeature matchedFeatures, double uniquenessThreshold ) : MatchedSURFFeature[]
matchedFeatures	MatchedSURFFeature	The Matched SURF features, each of them has the model feature sorted by distance. (e.g. SortMatchedFeaturesByDistance )
uniquenessThreshold	double	The distance different ratio which a match is consider unique, a good number will be 0.8
return	MatchedSURFFeature[]