Create an ImageDescriber interface for VLFeat SIFT feature extractor. More...

#include <ImageDescriber_DSPSIFT_vlfeat.hpp>

Inheritance diagram for aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat:

Public Member Functions
	ImageDescriber_DSPSIFT_vlfeat (const DspSiftParams &params=DspSiftParams(), bool isOriented=true)

bool	useCuda () const override
	Check if the image describer use CUDA. More...

bool	useFloatImage () const override
	Check if the image describer use float image. More...

EImageDescriberType	getDescriberType () const override
	Get the corresponding EImageDescriberType. More...

std::size_t	getMemoryConsumption (std::size_t width, std::size_t height) const override
	Get the total amount of RAM needed for a feature extraction of an image of the given dimension. More...

void	setUpRight (bool upRight) override
	Set image describer always upRight. More...

void	setConfigurationPreset (ConfigurationPreset preset) override
	Use a preset to control the number of detected regions. More...

bool	describe (const image::Image< float > &image, std::unique_ptr< Regions > &regions, const image::Image< unsigned char > *mask=nullptr) override
	Detect regions on the float image and compute their attributes (description) More...

void	allocate (std::unique_ptr< Regions > &regions) const override
	Allocate Regions type depending of the ImageDescriber. More...

Public Member Functions inherited from aliceVision::feature::ImageDescriber
virtual void	setUpRight ([[maybe_unused]] bool upRight)
	Set whether the image describer is always upright. More...

virtual void	setUseCuda ([[maybe_unused]] bool useCuda)
	Set whether the image describer needs to use CUDA implementation. More...

virtual void	setCudaPipe ([[maybe_unused]] int pipe)
	Set the CUDA pipe. More...

virtual bool	describe ([[maybe_unused]] const image::Image< unsigned char > &image, [[maybe_unused]] std::unique_ptr< Regions > &regions, [[maybe_unused]] const image::Image< unsigned char > *mask=nullptr)
	Detect regions on the 8-bit image and compute their attributes (description) More...

virtual bool	describe ([[maybe_unused]] const image::Image< float > &image, [[maybe_unused]] std::unique_ptr< Regions > &regions, [[maybe_unused]] const image::Image< unsigned char > *mask=nullptr)
	Detect regions on the float image and compute their attributes (description) More...

void	Load (Regions *regions, const std::string &sfileNameFeats, const std::string &sfileNameDescs) const

void	Save (const Regions *regions, const std::string &sfileNameFeats, const std::string &sfileNameDescs) const

void	LoadFeatures (Regions *regions, const std::string &sfileNameFeats) const

Detailed Description

Create an ImageDescriber interface for VLFeat SIFT feature extractor.

"Domain-Size Pooling in Local Descriptors: DSP-SIFT", CVPR 2015 Jingming Dong, Stefano Soatto, University of California https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Dong_Domain-Size_Pooling_in_2015_CVPR_paper.pdf

"A Theory of Local Matching: SIFT and Beyond", 2016 Hossein Mobahi CSAIL MIT, Stefano Soatto, CS Dept. UCLA https://arxiv.org/pdf/1601.05116.pdf

DSP-SIFT has been shown to outperform other SIFT variants and learned descriptors in "Comparative Evaluation of Hand-Crafted and Learned Local Features", CVPR 2016 Sch�nberger, Hardmeier, Sattler, Pollefeys https://openaccess.thecvf.com/content_cvpr_2017/papers/Schonberger_Comparative_Evaluation_of_CVPR_2017_paper.pdf

Member Function Documentation

◆ allocate()

void aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::allocate ( std::unique_ptr< Regions > & regions ) const

inlineoverridevirtual

Allocate Regions type depending of the ImageDescriber.

Parameters

[in,out] regions

Implements aliceVision::feature::ImageDescriber.

◆ describe()

bool aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::describe	(	const image::Image< float > &	image,
		std::unique_ptr< Regions > &	regions,
		const image::Image< unsigned char > *	mask = `nullptr`
	)

inlineoverride

Detect regions on the float image and compute their attributes (description)

Parameters

[in]	image	Image.
[out]	regions	The detected regions and attributes (the caller must delete the allocated data)
[in]	mask	8-bit grayscale image for keypoint filtering (optional) Non-zero values depict the region of interest.

Returns: True if detection successful.

◆ getDescriberType()

EImageDescriberType aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::getDescriberType ( ) const

inlineoverridevirtual

Get the corresponding EImageDescriberType.

Returns: EImageDescriberType

Implements aliceVision::feature::ImageDescriber.

◆ getMemoryConsumption()

std::size_t aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::getMemoryConsumption	(	std::size_t	width,
		std::size_t	height
	)		const

inlineoverridevirtual

Get the total amount of RAM needed for a feature extraction of an image of the given dimension.

Parameters

[in]	width	The image width
[in]	height	The image height

Returns: total amount of memory needed

Implements aliceVision::feature::ImageDescriber.

◆ setConfigurationPreset()

void aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::setConfigurationPreset ( ConfigurationPreset preset )

inlineoverridevirtual

Use a preset to control the number of detected regions.

Parameters

[in] preset The preset configuration

Implements aliceVision::feature::ImageDescriber.

◆ setUpRight()

void aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::setUpRight ( bool upRight )

inlineoverride

Set image describer always upRight.

Parameters

[in] upRight

◆ useCuda()

bool aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::useCuda ( ) const

inlineoverridevirtual

Check if the image describer use CUDA.

Returns: True if the image describer use CUDA

Implements aliceVision::feature::ImageDescriber.

◆ useFloatImage()

bool aliceVision::feature::ImageDescriber_DSPSIFT_vlfeat::useFloatImage ( ) const

inlineoverridevirtual

Check if the image describer use float image.

Returns: True if the image describer use float image

Implements aliceVision::feature::ImageDescriber.

The documentation for this class was generated from the following file:

/home/docs/checkouts/readthedocs.org/user_builds/alicevision/checkouts/latest/src/aliceVision/feature/sift/ImageDescriber_DSPSIFT_vlfeat.hpp

Public Member Functions

Detailed Description

Member Function Documentation

◆ allocate()

◆ describe()

◆ getDescriberType()

◆ getMemoryConsumption()

◆ setConfigurationPreset()

◆ setUpRight()

◆ useCuda()

◆ useFloatImage()