Table of Contents

Class TrackerKCF

Namespace
Emgu.CV
Assembly
Emgu.CV.dll

KCF is a novel tracking framework that utilizes properties of circulant matrix to enhance the processing speed. The original paper of KCF is available at http://home.isr.uc.pt/~henriques/circulant/index.html as well as the matlab implementation.

public class TrackerKCF : Tracker, IDisposable
Inheritance
TrackerKCF
Implements
Inherited Members

Constructors

TrackerKCF(float, float, float, float, float, float, bool, bool, bool, bool, int, int, Mode, Mode)

Creates a KCF Tracker

public TrackerKCF(float detectThresh = 0.5, float sigma = 0.2, float lambda = 0.01, float interpFactor = 0.075, float outputSigmaFactor = 0.0625, float pcaLearningRate = 0.15, bool resize = true, bool splitCoeff = true, bool wrapKernel = false, bool compressFeature = true, int maxPatchSize = 6400, int compressedSize = 2, TrackerKCF.Mode descPca = Mode.Cn, TrackerKCF.Mode descNpca = Mode.Gray)

Parameters

detectThresh float

detection confidence threshold

sigma float

gaussian kernel bandwidth

lambda float

regularization

interpFactor float

linear interpolation factor for adaptation

outputSigmaFactor float

spatial bandwidth (proportional to target)

pcaLearningRate float

compression learning rate

resize bool

activate the resize feature to improve the processing speed

splitCoeff bool

split the training coefficients into two matrices

wrapKernel bool

wrap around the kernel values

compressFeature bool

activate the pca method to compress the features

maxPatchSize int

threshold for the ROI size

compressedSize int

feature size after compression

descPca TrackerKCF.Mode

compressed descriptors of TrackerKCF::MODE

descNpca TrackerKCF.Mode

non-compressed descriptors of TrackerKCF::MODE

Methods

DisposeObject()

Release the unmanaged resources associated with this tracker

protected override void DisposeObject()