boofcv.alg.tracker.tld

Class TldLearning<T extends boofcv.struct.image.ImageGray<T>>

java.lang.Object

boofcv.alg.tracker.tld.TldLearning<T>

public class TldLearning<T extends boofcv.struct.image.ImageGray<T>>
extends java.lang.Object

Uses information from the user and from the tracker to update the positive and negative target model for both ferns and templates.

Constructor Summary

Constructors

Constructor and Description
TldLearning(java.util.Random rand, TldParameters config, TldTemplateMatching<T> template, TldVarianceFilter<T> variance, TldFernClassifier<T> fern, TldDetection<T> detection) Creates and configures learning

Method Summary

Modifier and Type	Method and Description
void	initialLearning(georegression.struct.shapes.Rectangle2D_F64 targetRegion, org.ddogleg.struct.FastQueue<boofcv.struct.ImageRectangle> cascadeRegions) Select positive and negative examples based on the region the user's initially selected region.
protected void	learnAmbiguousNegative(georegression.struct.shapes.Rectangle2D_F64 targetRegion) Mark regions which were local maximums and had high confidence as negative.
void	updateLearning(georegression.struct.shapes.Rectangle2D_F64 targetRegion) Updates learning using the latest tracking results.

Methods inherited from class java.lang.Object

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

Constructor Detail

TldLearning

public TldLearning(java.util.Random rand,
                   TldParameters config,
                   TldTemplateMatching<T> template,
                   TldVarianceFilter<T> variance,
                   TldFernClassifier<T> fern,
                   TldDetection<T> detection)

Creates and configures learning

Method Detail

initialLearning

public void initialLearning(georegression.struct.shapes.Rectangle2D_F64 targetRegion,
                            org.ddogleg.struct.FastQueue<boofcv.struct.ImageRectangle> cascadeRegions)

Select positive and negative examples based on the region the user's initially selected region. The selected region is used as a positive example while all the other regions far away are used as negative examples.

Parameters:

targetRegion - user selected region

cascadeRegions - Set of regions used by the cascade detector

updateLearning

public void updateLearning(georegression.struct.shapes.Rectangle2D_F64 targetRegion)

Updates learning using the latest tracking results.

Parameters:

targetRegion - Region selected by the fused tracking

learnAmbiguousNegative

protected void learnAmbiguousNegative(georegression.struct.shapes.Rectangle2D_F64 targetRegion)

Mark regions which were local maximums and had high confidence as negative. These regions were candidates for the tracker but were not selected