Class cv::DISK

DISK feature detector and descriptor, based on a DNN model. View details

#include <opencv2/features.hpp>

Collaboration diagram for cv::DISK:

Public Member Functions

Public Member Functions inherited from cv::Feature2D

Return	Name	Description
	~Feature2D()
void	compute(     InputArray image,     std::vector< KeyPoint > & keypoints,     OutputArray descriptors )	Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).
void	compute(     InputArrayOfArrays images,     std::vector< std::vector< KeyPoint > > & keypoints,     OutputArrayOfArrays descriptors )
int	defaultNorm()
int	descriptorSize()
int	descriptorType()
void	detect(     InputArray image,     std::vector< KeyPoint > & keypoints,     InputArray mask = noArray() )	Detects keypoints in an image (first variant) or image set (second variant).
void	detect(     InputArrayOfArrays images,     std::vector< std::vector< KeyPoint > > & keypoints,     InputArrayOfArrays masks = noArray() )
void	detectAndCompute(     InputArray image,     InputArray mask,     std::vector< KeyPoint > & keypoints,     OutputArray descriptors,     bool useProvidedKeypoints = false )
bool	empty()	Return true if detector object is empty.
String	getDefaultName()
void	read(const FileNode & fn)	Reads algorithm parameters from a file storage.
void	read(const String & fileName)
void	write(const String & fileName)
void	write(FileStorage & fs)	Stores algorithm parameters in a file storage.
void	write(     FileStorage & fs,     const String & name )

Public Member Functions inherited from cv::Algorithm

Return	Name	Description
	Algorithm()
	~Algorithm()
void	clear()	Clears the algorithm state.
bool	empty()	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.
String	getDefaultName()
void	read(const FileNode & fn)	Reads algorithm parameters from a file storage.
void	save(const String & filename)
void	write(     const Ptr< FileStorage > & fs,     const String & name = String() )
void	write(FileStorage & fs)	Stores algorithm parameters in a file storage.
void	write(     FileStorage & fs,     const String & name )

Static Public Member Functions

Static Public Member Functions inherited from cv::Algorithm

Return	Name	Description
static Ptr< _Tp >	load(     const String & filename,     const String & objname = String() )	Loads algorithm from the file.
static Ptr< _Tp >	loadFromString(     const String & strModel,     const String & objname = String() )	Loads algorithm from a String.
static Ptr< _Tp >	read(const FileNode & fn)	Reads algorithm from the file node.

Additional Inherited Members

Protected Member Functions inherited from cv::Algorithm

Return	Name	Description
void	writeFormat(FileStorage & fs)

Detailed Description

DISK feature detector and descriptor, based on a DNN model.

DISK (Deep Image Structure and Keypoints) is a learned local-feature pipeline that produces keypoints and 128-D L2-normalized descriptors via a single forward pass through a fully convolutional network. This class wraps an ONNX export of the pre-trained DISK model through cv::dnn::Net and exposes it under the standard cv::Feature2D interface so it can be used as a drop-in alternative to SIFT/ORB.

The class assumes the ONNX model has a single input named image taking an N×3×H×W float32 tensor in [0, 1] (RGB channel order) and three outputs named keypoints (N×2), scores (N) and descriptors (N×128).

Member Function Documentation

create()

static Ptr< DISK > cv::DISK::create(
const std::vector< uchar > & bufferModel,
int maxKeypoints = -1,
float scoreThreshold = 0.0f,
const Size & imageSize = Size(),
int backendId = 0,
int targetId = 0 )

Python:

cv.DISK.create(modelPath[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

cv.DISK.createFromMemory(bufferModel[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

cv.DISK_create(modelPath[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

cv.DISK_createFromMemory(bufferModel[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

Creates a DISK detector from an in-memory model buffer.

This overload loads the DISK ONNX model from a buffer instead of a file on disk. It is intended for cases where the model is read from application resources (for example Android assets) and is not available as a path on the filesystem.

Note

In C++ this is an overload of create. The Python/Java/Objective-C bindings expose it as createFromMemory, because Objective-C selectors are not disambiguated by argument type and would otherwise clash with the file-path create.

Parameters

• bufferModel — A buffer containing the contents of the DISK ONNX model.

• maxKeypoints — Maximum number of keypoints to return per image. The strongest responses (by network score) are kept; -1 keeps all detections.

• scoreThreshold — Discard keypoints with network score strictly below this value.

• imageSize — Target input size (width, height) fed to the network. Use Size() (the default) to fall back to the network’s expected fixed input shape of 1024x1024. When overriding, both dimensions must be positive multiples of 16, since DISK downsamples by a factor of 16.

• backendId — DNN backend identifier (see cv::dnn::Backend); 0 = DNN_BACKEND_DEFAULT.

• targetId — DNN target identifier (see cv::dnn::Target); 0 = DNN_TARGET_CPU.

create()

static Ptr< DISK > cv::DISK::create(
const String & modelPath,
int maxKeypoints = -1,
float scoreThreshold = 0.0f,
const Size & imageSize = Size(),
int backendId = 0,
int targetId = 0 )

Python:

cv.DISK.create(modelPath[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

cv.DISK.createFromMemory(bufferModel[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

cv.DISK_create(modelPath[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

cv.DISK_createFromMemory(bufferModel[, maxKeypoints[, scoreThreshold[, imageSize[, backendId[, targetId]]]]]) -> retval

Creates a DISK detector.

Parameters

• modelPath — Path to the DISK ONNX model.

• maxKeypoints — Maximum number of keypoints to return per image. The strongest responses (by network score) are kept; -1 keeps all detections.

• scoreThreshold — Discard keypoints with network score strictly below this value.

• imageSize — Target input size (width, height) fed to the network. Use Size() (the default) to fall back to the network’s expected fixed input shape of 1024x1024. When overriding, both dimensions must be positive multiples of 16, since DISK downsamples by a factor of 16.

• backendId — DNN backend identifier (see cv::dnn::Backend); 0 = DNN_BACKEND_DEFAULT.

• targetId — DNN target identifier (see cv::dnn::Target); 0 = DNN_TARGET_CPU.

getDefaultName()

String cv::DISK::getDefaultName()

Python:

cv.DISK.getDefaultName() -> retval

Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.

getImageSize()

Size cv::DISK::getImageSize()

Python:

cv.DISK.getImageSize() -> retval

getMaxKeypoints()

int cv::DISK::getMaxKeypoints()

Python:

cv.DISK.getMaxKeypoints() -> retval

getScoreThreshold()

float cv::DISK::getScoreThreshold()

Python:

cv.DISK.getScoreThreshold() -> retval

setImageSize()

void cv::DISK::setImageSize(const Size & size)

Python:

cv.DISK.setImageSize(size)

setMaxKeypoints()

void cv::DISK::setMaxKeypoints(int maxKeypoints)

Python:

cv.DISK.setMaxKeypoints(maxKeypoints)

setScoreThreshold()

void cv::DISK::setScoreThreshold(float threshold)

Python:

cv.DISK.setScoreThreshold(threshold)

Source file

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

• opencv2/features.hpp