Package boofcv.alg.tracker.tld

Class TldRegionTracker<I extends ImageGray<I>,D extends ImageGray<D>>

java.lang.Object

boofcv.alg.tracker.tld.TldRegionTracker<I,D>

public class TldRegionTracker<I extends ImageGray<I>,D extends ImageGray<D>>
extends Object

Tracks features inside target's rectangle using pyramidal KLT and updates the rectangle using found motion. A scale and translation model model is used. A major departure from the paper is that KLT forward-backward (FB) error and robust model fitting is used to prune tracks and estimate motion. In the paper FB and NCC error is used to prune tracks and a (in my opinion) hack is used by computing median error values. The way the motion is computed is more mathematically sound this way. NCC would provide a good sanity check, but is probably not needed.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	TldRegionTracker.Track

Constructor Summary

Constructors

Constructor	Description
TldRegionTracker(int gridWidth, int featureRadius, double maxErrorFB, ImageGradient<I,D> gradient, PyramidKltTracker<I,D> tracker, Class<I> imageType, Class<D> derivType)	Configures tracker

Method Summary

Modifier and Type	Method	Description
protected void	declareDataStructures(PyramidDiscrete<I> image)	Declares internal data structures based on the input image pyramid
DogArray<AssociatedPair>	getPairs()
TldRegionTracker.Track[]	getTracks()
void	initialize(PyramidDiscrete<I> image)	Call for the first image being tracked
boolean	process(ImagePyramid<I> image, Rectangle2D_F64 targetRectangle)	Creates several tracks inside the target rectangle and compuets their motion
protected void	spawnGrid(Rectangle2D_F64 prevRect)	Spawn KLT tracks at evenly spaced points inside a grid
protected boolean	trackFeature()	Tracks KLT features in forward/reverse direction and the tracking error metrics
protected void	updateCurrent(ImagePyramid<I> image)	Computes the gradient and changes the reference to the current pyramid

Methods inherited from class java.lang.Object

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

Constructor Details

TldRegionTracker

public TldRegionTracker(int gridWidth,
 int featureRadius,
 double maxErrorFB,
 ImageGradient<I,D> gradient,
 PyramidKltTracker<I,D> tracker,
 Class<I> imageType,
 Class<D> derivType)

Configures tracker

Parameters:

gridWidth - Number of tracks spawned along a side in the grid. Try 10

featureRadius - Radius of KLT features being tracked. Try 5

maxErrorFB - Maximum allowed forwards-backwards error

gradient - Computes image gradient used by KLT tracker

tracker - Feature tracker

imageType - Type of input image

derivType - Type of derivative image

Method Details

initialize

public void initialize(PyramidDiscrete<I> image)

Call for the first image being tracked

Parameters:

image - Most recent video image.

declareDataStructures

protected void declareDataStructures(PyramidDiscrete<I> image)

Declares internal data structures based on the input image pyramid

process

public boolean process(ImagePyramid<I> image,
 Rectangle2D_F64 targetRectangle)

Creates several tracks inside the target rectangle and compuets their motion

Parameters:

image - Most recent video image.

targetRectangle - Location of target in previous frame. Not modified.

Returns:

true if tracking was successful or false if not

updateCurrent

protected void updateCurrent(ImagePyramid<I> image)

Computes the gradient and changes the reference to the current pyramid

trackFeature

protected boolean trackFeature()

Tracks KLT features in forward/reverse direction and the tracking error metrics

spawnGrid

protected void spawnGrid(Rectangle2D_F64 prevRect)

Spawn KLT tracks at evenly spaced points inside a grid

getPairs

public DogArray<AssociatedPair> getPairs()

getTracks

public TldRegionTracker.Track[] getTracks()