org.openimaj.image.feature.dense.gradient.dsift

Class PyramidDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

java.lang.Object

org.openimaj.image.feature.dense.gradient.dsift.AbstractDenseSIFT<IMAGE>

org.openimaj.image.feature.dense.gradient.dsift.PyramidDenseSIFT<IMAGE>

Type Parameters:

IMAGE - Type of image to be processed.

All Implemented Interfaces:

Cloneable, ImageAnalyser<IMAGE>

public class PyramidDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
extends AbstractDenseSIFT<IMAGE>

A scale-space pyramid of dense SIFT for FImages. Dense sift features are extracted for the given bin sizes (scales). The image is optionally smoothed with a Gaussian before each scale.

The PyramidDenseSIFT is not thread safe, but is reusable like the DenseSIFT analyser.

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk)

Constructor Summary

Constructors

Constructor and Description
PyramidDenseSIFT(AbstractDenseSIFT<IMAGE> dsift, float magFactor, int... sizes) Construct the pyramid dense sift extractor.

Method Summary

Modifier and Type	Method and Description
void	analyseImage(IMAGE image, Rectangle originalBounds) Compute the dense sift descriptors inside the bounds rectangle of the given image.
int	getBinHeight() This returns the bin size of the zeroth level only.
int	getBinWidth() This returns the bin size of the zeroth level only.
LocalFeatureList<ByteDSIFTKeypoint>	getByteKeypoints() Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors.
LocalFeatureList<ByteDSIFTKeypoint>	getByteKeypoints(float energyThreshold) Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors.
List<IntObjectPair<LocalFeatureList<ByteDSIFTKeypoint>>>	getByteKeypointsGrouped() Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors.
List<IntObjectPair<LocalFeatureList<ByteDSIFTKeypoint>>>	getByteKeypointsGrouped(float energyThreshold) Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors.
float[][]	getDescriptors() Get the computed raw dense SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) .
LocalFeatureList<FloatDSIFTKeypoint>	getFloatKeypoints() Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with float vectors.
LocalFeatureList<FloatDSIFTKeypoint>	getFloatKeypoints(float energyThreshold) Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with float vectors.
List<IntObjectPair<LocalFeatureList<FloatDSIFTKeypoint>>>	getFloatKeypointsGrouped() Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with float vectors.
List<IntObjectPair<LocalFeatureList<FloatDSIFTKeypoint>>>	getFloatKeypointsGrouped(float energyThreshold) Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with float vectors.
float[][][]	getLevelDescriptors() Get the computed raw dense SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) .
int	getNumBinsX() Get the number of spatial bins in the X direction
int	getNumBinsY() Get the number of spatial bins in the Y direction
int	getNumOriBins() Get the number of orientation bins
int[]	getSizes() Get the bin sizes
void	setBinHeight(int size) Not supported.
void	setBinWidth(int size) Not supported.

Methods inherited from class org.openimaj.image.feature.dense.gradient.dsift.AbstractDenseSIFT

analyseImage, clone

Methods inherited from class java.lang.Object

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

Constructor Detail

PyramidDenseSIFT

public PyramidDenseSIFT(AbstractDenseSIFT<IMAGE> dsift,
                        float magFactor,
                        int... sizes)

Construct the pyramid dense sift extractor. The magnification factor is used to determine how to smooth the image before extracting the features at each level: the smoothing sigma at each level is the bin size at that level divided by the magnification factor. If the magnification factor is 0, then no smoothing will be applied at any level.

Parameters:

dsift - the underlying dense sift extractor (typically a DenseSIFT (or ApproximateDenseSIFT) or ColourDenseSIFT depending on the image type).

magFactor - the magnification factor

sizes - the scales (bin sizes for dense sift)

Method Detail

analyseImage

public void analyseImage(IMAGE image,
                         Rectangle originalBounds)

Description copied from class: AbstractDenseSIFT

Compute the dense sift descriptors inside the bounds rectangle of the given image.

Specified by:

analyseImage in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Parameters:

image - the image

originalBounds - the bounds rectangle

getFloatKeypoints

public LocalFeatureList<FloatDSIFTKeypoint> getFloatKeypoints()

Description copied from class: AbstractDenseSIFT

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with float vectors.

Specified by:

getFloatKeypoints in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

a list of FloatDSIFTKeypoints.

getByteKeypoints

public LocalFeatureList<ByteDSIFTKeypoint> getByteKeypoints()

Description copied from class: AbstractDenseSIFT

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors.

Specified by:

getByteKeypoints in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

a list of ByteDSIFTKeypoints.

getFloatKeypoints

public LocalFeatureList<FloatDSIFTKeypoint> getFloatKeypoints(float energyThreshold)

Description copied from class: AbstractDenseSIFT

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with float vectors. Only the features with an energy above the given threshold will be returned.

Specified by:

getFloatKeypoints in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Parameters:

energyThreshold - the threshold on the feature energy

Returns:

a list of FloatDSIFTKeypoints.

getByteKeypoints

public LocalFeatureList<ByteDSIFTKeypoint> getByteKeypoints(float energyThreshold)

Description copied from class: AbstractDenseSIFT

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors. Only the features with an energy above the given threshold will be returned.

Specified by:

getByteKeypoints in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Parameters:

energyThreshold - the threshold on the feature energy

Returns:

a list of ByteDSIFTKeypoints.

getFloatKeypointsGrouped

public List<IntObjectPair<LocalFeatureList<FloatDSIFTKeypoint>>> getFloatKeypointsGrouped()

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with float vectors.

Returns:

a list of FloatDSIFTKeypoints.

getByteKeypointsGrouped

public List<IntObjectPair<LocalFeatureList<ByteDSIFTKeypoint>>> getByteKeypointsGrouped()

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors.

Returns:

a list of ByteDSIFTKeypoints.

getFloatKeypointsGrouped

public List<IntObjectPair<LocalFeatureList<FloatDSIFTKeypoint>>> getFloatKeypointsGrouped(float energyThreshold)

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with float vectors. Only the features with an energy above the given threshold will be returned.

Parameters:

energyThreshold - the threshold on the feature energy

Returns:

a list of FloatDSIFTKeypoints.

getByteKeypointsGrouped

public List<IntObjectPair<LocalFeatureList<ByteDSIFTKeypoint>>> getByteKeypointsGrouped(float energyThreshold)

Get the SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) in the form of a list of local features with byte vectors. Only the features with an energy above the given threshold will be returned.

Parameters:

energyThreshold - the threshold on the feature energy

Returns:

a list of ByteDSIFTKeypoints.

getLevelDescriptors

public float[][][] getLevelDescriptors()

Get the computed raw dense SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or analyseImage(Image, Rectangle) . The descriptors are grouped by the sizes at which they were extracted.

Returns:

the descriptors.

getSizes

public int[] getSizes()

Get the bin sizes

Returns:

the bin sizes

setBinWidth

public void setBinWidth(int size)

Not supported.

Specified by:

setBinWidth in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Parameters:

size - size to set

Throws:

UnsupportedOperationException

setBinHeight

public void setBinHeight(int size)

Not supported.

Specified by:

setBinHeight in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Parameters:

size - size to set

Throws:

UnsupportedOperationException

getBinWidth

public int getBinWidth()

This returns the bin size of the zeroth level only. (Optional operation) Get the width of a single bin of the sampling window (in pixels). Sampling window width is this multiplied by AbstractDenseSIFT.getNumBinsX().

Specified by:

getBinWidth in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

the bin width

getBinHeight

public int getBinHeight()

This returns the bin size of the zeroth level only. (Optional operation) Get the height of a single bin of the sampling window (in pixels). Sampling window height is this multiplied by AbstractDenseSIFT.getNumBinsY().

Specified by:

getBinHeight in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

the bin height

getNumBinsX

public int getNumBinsX()

Description copied from class: AbstractDenseSIFT

Get the number of spatial bins in the X direction

Specified by:

getNumBinsX in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

the number of bins in the x direction

getNumBinsY

public int getNumBinsY()

Description copied from class: AbstractDenseSIFT

Get the number of spatial bins in the Y direction

Specified by:

getNumBinsY in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

the number of bins in the y direction

getNumOriBins

public int getNumOriBins()

Description copied from class: AbstractDenseSIFT

Get the number of orientation bins

Specified by:

getNumOriBins in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

the number of orientation bins

getDescriptors

public float[][] getDescriptors()

Description copied from class: AbstractDenseSIFT

Get the computed raw dense SIFT descriptors from the previous call to AbstractDenseSIFT.analyseImage(Image) or AbstractDenseSIFT.analyseImage(Image, Rectangle) .

Specified by:

getDescriptors in class AbstractDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>

Returns:

the descriptors.