Class TrackerMIL

Namespace: Emgu.CV

Assembly: Emgu.CV.dll

The MIL algorithm trains a classifier in an online manner to separate the object from the background. Multiple Instance Learning avoids the drift problem for a robust tracking. Original code can be found here http://vision.ucsd.edu/~bbabenko/project_miltrack.shtml

public class TrackerMIL : Tracker, IDisposable

Inheritance: object

DisposableObject

UnmanagedObject

Tracker

TrackerMIL

Implements: IDisposable

Inherited Members: Tracker._trackerPtr

Tracker.Init(IInputArray, Rectangle)

Tracker.Update(IInputArray, out Rectangle)

UnmanagedObject._ptr

UnmanagedObject.Ptr

DisposableObject.Dispose()

DisposableObject.ReleaseManagedResources()

object.GetType()

object.MemberwiseClone()

object.ToString()

object.Equals(object)

object.Equals(object, object)

object.ReferenceEquals(object, object)

object.GetHashCode()

Constructors

TrackerMIL(float, int, float, float, int, int, int)

Creates a MIL Tracker

public TrackerMIL(float samplerInitInRadius = 3, int samplerInitMaxNegNum = 65, float samplerSearchWinSize = 25, float samplerTrackInRadius = 4, int samplerTrackMaxPosNum = 100000, int samplerTrackMaxNegNum = 65, int featureSetNumFeatures = 250)

Parameters

samplerInitInRadius float: radius for gathering positive instances during init
samplerInitMaxNegNum int: negative samples to use during init
samplerSearchWinSize float: size of search window
samplerTrackInRadius float: radius for gathering positive instances during tracking
samplerTrackMaxPosNum int: positive samples to use during tracking
samplerTrackMaxNegNum int: negative samples to use during tracking
featureSetNumFeatures int: features

Methods

DisposeObject()

Release all the unmanaged memory associated with this tracker