com.jsaragih

Class Tracker

java.lang.Object

com.jsaragih.Tracker

@Reference(type=Inproceedings,
           author={"Jason M. Saragih","Simon Lucey","Jeffrey F. Cohn"},
           title="Face alignment through subspace constrained mean-shifts",
           year="2009",
           booktitle="IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27 - October 4, 2009",
           pages={"1034","1041"},
           publisher="IEEE",
           customData={"doi","http://dx.doi.org/10.1109/ICCV.2009.5459377","researchr","http://researchr.org/publication/SaragihLC09","cites","0","citedby","0"})
public class Tracker
extends Object

The initial ported version of the CLMTracker that can only track a single face in an image. It's had only a few small changes to allow it to work with the list which the face detector class now returns. Unless you're sure you only want to track a single face, you should probably use the new OpenIMAJ org.openimaj.image.processing.face.tracking.clm.MultiTracker class from the faces sub-project instead.

Author:

Jason Mora Saragih, Jonathon Hare (jsh2@ecs.soton.ac.uk), David Dupplaw (dpd@ecs.soton.ac.uk)

Field Summary

Fields

Modifier and Type	Field and Description
CLM	_clm Constrained Local Model
Jama.Matrix	_rshape Reference shape
Jama.Matrix	_shape Current shape

Method Summary

Modifier and Type	Method and Description
void	frameReset() Reset frame number (will perform detection in next image)
static Tracker	load(InputStream in)
int	track(FImage im, int[] wSize, int fpd, int nIter, double clamp, double fTol, boolean fcheck)

Methods inherited from class java.lang.Object

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

Field Detail

_clm

public CLM _clm

Constrained Local Model

_shape

public Jama.Matrix _shape

Current shape

_rshape

public Jama.Matrix _rshape

Reference shape

Method Detail

frameReset

public void frameReset()

Reset frame number (will perform detection in next image)

load

public static Tracker load(InputStream in)

Parameters:

in -

Returns:

a tracker

track

public int track(FImage im,
                 int[] wSize,
                 int fpd,
                 int nIter,
                 double clamp,
                 double fTol,
                 boolean fcheck)

Parameters:

im -

wSize -

fpd -

nIter -

clamp -

fTol -

fcheck -

Returns:

0 for success, -1 for redetect