Package edu.gsu.cs.dmlab.tracking.appearance

Class HistoAppearanceModel

java.lang.Object

edu.gsu.cs.dmlab.tracking.appearance.HistoAppearanceModel

All Implemented Interfaces:

ISTAppearanceModel

public class HistoAppearanceModel
extends Object
implements ISTAppearanceModel

Appearance model based upon the distance of two histograms of image parameters. From Kempton et. al. 2015.

Author:

Dustin Kempton, Data Mining Lab, Georgia State University

Constructor Summary

Constructors

Constructor	Description
HistoAppearanceModel(double sameMean, double sameStdDev, double diffMean, double diffStdDev, ISTHistogramProducer histoProducer, IHistoComparator histoComparator, ImageDBWaveParamPair[] dims)	Constructor

Method Summary

Modifier and Type	Method	Description
double	calcProbAppearance(ISTTrackingTrajectory leftTrack, ISTTrackingTrajectory rightTrack)	Produces a likelihood value for the two input tracks being the same object based upon their appearance at the join point.
void	finalize()

Methods inherited from class java.lang.Object

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

Constructor Detail

HistoAppearanceModel

public HistoAppearanceModel(double sameMean,
                            double sameStdDev,
                            double diffMean,
                            double diffStdDev,
                            ISTHistogramProducer histoProducer,
                            IHistoComparator histoComparator,
                            ImageDBWaveParamPair[] dims)

Constructor

Parameters:

sameMean - The mean of the normal distribution of histogram distances from events in the same track.

sameStdDev - The standard deviation of the normal distribution of histogram distances from events in the same track.

diffMean - The mean of the normal distribution of histogram distances from events in different tracks.

diffStdDev - The standard deviation of the normal distribution of histogram distances from events in different tracks.

histoProducer - The object used to produce histograms of events that are to be compared.

histoComparator - The object that performs the histogram comparison and returns some distance value.

dims - The list of image parameters and wavelengths to use to produce the histograms for each event.

Method Detail

finalize

public void finalize()
              throws Throwable

Overrides:

finalize in class Object

Throws:

Throwable

calcProbAppearance

public double calcProbAppearance(ISTTrackingTrajectory leftTrack,
                                 ISTTrackingTrajectory rightTrack)

Description copied from interface: ISTAppearanceModel

Produces a likelihood value for the two input tracks being the same object based upon their appearance at the join point.

Specified by:

calcProbAppearance in interface ISTAppearanceModel

Parameters:

leftTrack - The track that is earlier in time.

rightTrack - The track that is later in time.

Returns:

The likelihood value for their similarity.