Package boofcv.alg.scene.vocabtree

Class LearnHierarchicalTree<Point>

java.lang.Object

boofcv.alg.scene.vocabtree.LearnHierarchicalTree<Point>

All Implemented Interfaces:

VerbosePrint

public class LearnHierarchicalTree<Point>
extends Object
implements VerbosePrint

The graph is constructed using a depth first search. Each level has its own k-means algorithm. Labeling results are used to segment points for each branch before going to the next level.

Field Summary

Fields

Modifier and Type	Field	Description
protected final DogArray<StandardKMeans<Point>>	listKMeans
protected final DogArray<PackedArray<Point>>	listPoints
protected final DogArray<DogArray_F64>	listWeights
ConfigLength	minimumPointsForChildren	If a node has less than this number of points it will not spawn children.
protected int	pointsRequiredForChildren
protected int	totalPoints
protected @Nullable PrintStream	verbose

Constructor Summary

Constructors

Constructor	Description
LearnHierarchicalTree(BoofLambdas.Factory<PackedArray<Point>> factoryStorage, BoofLambdas.Factory<StandardKMeans<Point>> factoryKMeans, long randomSeed)	Constructor which specifies factories for internal data structures which are dynamic bsaed on the maximum number of levels

Method Summary

Modifier and Type	Method	Description
void	process(PackedArray<Point> points, HierarchicalVocabularyTree<Point> tree)	Performs clustering
void	setVerbose(@Nullable PrintStream out, @Nullable Set<String> set)

Methods inherited from class java.lang.Object

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

Field Details

minimumPointsForChildren

public ConfigLength minimumPointsForChildren

If a node has less than this number of points it will not spawn children. This is intended to avoid over fitting. If relative then it will be relative to the total number of points.

listPoints

protected final DogArray<PackedArray<Point>> listPoints

listKMeans

protected final DogArray<StandardKMeans<Point>> listKMeans

listWeights

protected final DogArray<DogArray_F64> listWeights

pointsRequiredForChildren

protected int pointsRequiredForChildren

totalPoints

protected int totalPoints

verbose

@Nullable
protected @Nullable PrintStream verbose

Constructor Details

LearnHierarchicalTree

public LearnHierarchicalTree(BoofLambdas.Factory<PackedArray<Point>> factoryStorage,
 BoofLambdas.Factory<StandardKMeans<Point>> factoryKMeans,
 long randomSeed)

Constructor which specifies factories for internal data structures which are dynamic bsaed on the maximum number of levels

Parameters:

factoryStorage - Factory for point storage

factoryKMeans - Factory for new K-Means instances

randomSeed - Seed used in random number generators

Method Details

process

public void process(PackedArray<Point> points,
 HierarchicalVocabularyTree<Point> tree)

Performs clustering

Parameters:

points - (Input) points which are to be segmented into the hierarchical tree

tree - (Output) generated tree

setVerbose

public void setVerbose(@Nullable
 @Nullable PrintStream out,
 @Nullable
 @Nullable Set<String> set)

Specified by:

setVerbose in interface VerbosePrint