boofcv.alg.tracker.tld

Class TldTracker<T extends boofcv.struct.image.ImageGray<T>,D extends boofcv.struct.image.ImageGray<D>>

java.lang.Object

boofcv.alg.tracker.tld.TldTracker<T,D>

public class TldTracker<T extends boofcv.struct.image.ImageGray<T>,D extends boofcv.struct.image.ImageGray<D>>
extends java.lang.Object

Main class for Tracking-Learning-Detection (TLD) [1] (a.k.a Predator) object tracker for video sequences. TLD tracks an object which is specified by a user using a rectangle. The description of the object is dynamically updated using P and N constraints.

To start tracking initialize(ImageGray, int, int, int, int) must first be called to specify the region being tracked. Then each time a new image in the sequences arrives track(ImageGray) is called. Be sure to check its return value to see if tracking was successful or not. If tracking fails one frame it can recover. This is often the case where an object becomes obscured and then visible again.

NOTE: This implementation is based the description found in [1]. The spirit of the original algorithm is replicated, but there are a several algorithmic changes. The most significant modifications are as follow; 1) The KLT tracker used to update the rectangle does not use NCC features to validate a track or the median based outlier removal. Instead a robust model matching algorithm finds the best fit motion. 2) The non-maximum suppression algorithm has been changed so that it computes a more accurate local maximum and only uses local rectangles to compute the average response. 3) Fern selection is done by selecting the N best using a likelihood ratio conditional on the current image. 4) Learning only happens when a track is considered strong. See code for more details. Note, this is not a port of the OpenTLD project.

[1] Zdenek Kalal, "Tracking-Learning-Detection" University of Surrey, April 2011 Phd Thesis.

Constructor Summary

Constructors

Constructor and Description
TldTracker(TldParameters config, boofcv.alg.interpolate.InterpolatePixelS<T> interpolate, boofcv.abst.filter.derivative.ImageGradient<T,D> gradient, java.lang.Class<T> imageType, java.lang.Class<D> derivType) Configures the TLD tracker

Method Summary

Modifier and Type	Method and Description
TldParameters	getConfig()
TldDetection<T>	getDetection()
georegression.struct.shapes.Rectangle2D_F64	getTargetRegion() Returns the estimated location of the target in the current image
TldTemplateMatching<T>	getTemplateMatching()
georegression.struct.shapes.Rectangle2D_F64	getTrackerRegion()
protected boolean	hypothesisFusion(boolean trackingWorked, boolean detectionWorked) Combines hypotheses from tracking and detection.
void	initialize(T image, int x0, int y0, int x1, int y1) Starts tracking the rectangular region.
boolean	isPerformLearning()
static int[]	selectPyramidScale(int imageWidth, int imageHeight, int minSize) Selects the scale for the image pyramid based on image size and feature size
void	setPerformLearning(boolean performLearning)
void	setTrackerLocation(int x0, int y0, int x1, int y1) Used to set the location of the track without changing any appearance history.
boolean	track(T image) Updates track region.

Methods inherited from class java.lang.Object

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

Constructor Detail

TldTracker

public TldTracker(TldParameters config,
                  boofcv.alg.interpolate.InterpolatePixelS<T> interpolate,
                  boofcv.abst.filter.derivative.ImageGradient<T,D> gradient,
                  java.lang.Class<T> imageType,
                  java.lang.Class<D> derivType)

Configures the TLD tracker

Parameters:

config - Configuration class which specifies the tracker's behavior

Method Detail

initialize

public void initialize(T image,
                       int x0,
                       int y0,
                       int x1,
                       int y1)

Starts tracking the rectangular region.

Parameters:

image - First image in the sequence.

x0 - Top-left corner of rectangle. x-axis

y0 - Top-left corner of rectangle. y-axis

x1 - Bottom-right corner of rectangle. x-axis

y1 - Bottom-right corner of rectangle. y-axis

setTrackerLocation

public void setTrackerLocation(int x0,
                               int y0,
                               int x1,
                               int y1)

Used to set the location of the track without changing any appearance history. Move the track region but keep the same aspect ratio as it had before So scale the region and re-center it

track

public boolean track(T image)

Updates track region.

Parameters:

image - Next image in the sequence.

Returns:

true if the object could be found and false if not

hypothesisFusion

protected boolean hypothesisFusion(boolean trackingWorked,
                                   boolean detectionWorked)

Combines hypotheses from tracking and detection.

Parameters:

trackingWorked - If the sequential tracker updated the track region successfully or not

Returns:

true a hypothesis was found, false if it failed to find a hypothesis

selectPyramidScale

public static int[] selectPyramidScale(int imageWidth,
                                       int imageHeight,
                                       int minSize)

Selects the scale for the image pyramid based on image size and feature size

Returns:

scales for image pyramid

isPerformLearning

public boolean isPerformLearning()

setPerformLearning

public void setPerformLearning(boolean performLearning)

getTemplateMatching

public TldTemplateMatching<T> getTemplateMatching()

getTargetRegion

public georegression.struct.shapes.Rectangle2D_F64 getTargetRegion()

Returns the estimated location of the target in the current image

Returns:

Location of the target

getTrackerRegion

public georegression.struct.shapes.Rectangle2D_F64 getTrackerRegion()

getConfig

public TldParameters getConfig()

getDetection

public TldDetection<T> getDetection()