boofcv.abst.feature.dense

Class GenericDenseDescribeImageDense<T extends boofcv.struct.image.ImageBase,Desc extends TupleDesc>

java.lang.Object

boofcv.abst.feature.dense.GenericDenseDescribeImageDense<T,Desc>

All Implemented Interfaces:

DescribeImageDense<T,Desc>, DescriptorInfo<Desc>

public class GenericDenseDescribeImageDense<T extends boofcv.struct.image.ImageBase,Desc extends TupleDesc>
extends java.lang.Object
implements DescribeImageDense<T,Desc>

Dense feature computation which uses DescribeRegionPoint internally.

Constructor Summary

Constructors

Constructor and Description
GenericDenseDescribeImageDense(DescribeRegionPoint<T,Desc> alg, double scale, int featureWidth, int periodX, int periodY) Configures dense description.

Method Summary

Modifier and Type	Method and Description
Desc	createDescription() Creates new description instance which can be processed by this class
java.lang.Class<Desc>	getDescriptionType() The type of region descriptor generated
boofcv.struct.image.ImageType<T>	getImageType() Description of the type of image it can process
void	process(T input, org.ddogleg.struct.FastQueue<Desc> descriptions, org.ddogleg.struct.FastQueue<georegression.struct.point.Point2D_I32> locations) Processes the image and computes the dense image features.

Methods inherited from class java.lang.Object

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

Constructor Detail

GenericDenseDescribeImageDense

public GenericDenseDescribeImageDense(DescribeRegionPoint<T,Desc> alg,
                                      double scale,
                                      int featureWidth,
                                      int periodX,
                                      int periodY)

Configures dense description.

Parameters:

alg - Sparse feature sampler.

scale - The scale at which the features should be sampled

featureWidth - Tells it how wide a feature is so that it can avoid sampling outside the image

periodX - sample rate along the x-axis

periodY - sample rate along the y-axis

Method Detail

process

public void process(T input,
                    org.ddogleg.struct.FastQueue<Desc> descriptions,
                    org.ddogleg.struct.FastQueue<georegression.struct.point.Point2D_I32> locations)

Description copied from interface: DescribeImageDense

Processes the image and computes the dense image features.

Specified by:

process in interface DescribeImageDense<T extends boofcv.struct.image.ImageBase,Desc extends TupleDesc>

Parameters:

input - Input image.

descriptions - (Output) Storage for descriptors. The grow() command is used to request more data.

locations - (output) (Optional) Storage for location of feature sample center points. New locations are added by invoking grow(). If null then it's ignored.

getImageType

public boofcv.struct.image.ImageType<T> getImageType()

Description copied from interface: DescribeImageDense

Description of the type of image it can process

Specified by:

getImageType in interface DescribeImageDense<T extends boofcv.struct.image.ImageBase,Desc extends TupleDesc>

Returns:

ImageDataType

createDescription

public Desc createDescription()

Description copied from interface: DescriptorInfo

Creates new description instance which can be processed by this class

Specified by:

createDescription in interface DescriptorInfo<Desc extends TupleDesc>

Returns:

New descriptor

getDescriptionType

public java.lang.Class<Desc> getDescriptionType()

Description copied from interface: DescriptorInfo

The type of region descriptor generated

Specified by:

getDescriptionType in interface DescriptorInfo<Desc extends TupleDesc>

Returns:

Returns the descriptor type.