OpenCV  4.6.0-dev
Open Source Computer Vision
Public Types | Static Public Member Functions | List of all members
cv::xfeatures2d::TEBLID Class Reference

Class implementing TEBLID (Triplet-based Efficient Binary Local Image Descriptor), described in [237]. More...

#include <opencv2/xfeatures2d.hpp>

Inheritance diagram for cv::xfeatures2d::TEBLID:
cv::Feature2D cv::Algorithm

Public Types

enum  TeblidSize {
  SIZE_256_BITS = 102,
  SIZE_512_BITS = 103
}
 Descriptor number of bits, each bit is a box average difference. The user can choose between 256 or 512 bits. More...
 

Static Public Member Functions

static Ptr< TEBLIDcreate (float scale_factor, int n_bits=TEBLID::SIZE_256_BITS)
 Creates the TEBLID descriptor. More...
 
- Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp > load (const String &filename, const String &objname=String())
 Loads algorithm from the file. More...
 
template<typename _Tp >
static Ptr< _Tp > loadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String. More...
 
template<typename _Tp >
static Ptr< _Tp > read (const FileNode &fn)
 Reads algorithm from the file node. More...
 

Additional Inherited Members

- Public Member Functions inherited from cv::Feature2D
virtual ~Feature2D ()
 
virtual 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). More...
 
virtual void compute (InputArrayOfArrays images, std::vector< std::vector< KeyPoint > > &keypoints, OutputArrayOfArrays descriptors)
 
virtual int defaultNorm () const
 
virtual int descriptorSize () const
 
virtual int descriptorType () const
 
virtual void detect (InputArray image, std::vector< KeyPoint > &keypoints, InputArray mask=noArray())
 Detects keypoints in an image (first variant) or image set (second variant). More...
 
virtual void detect (InputArrayOfArrays images, std::vector< std::vector< KeyPoint > > &keypoints, InputArrayOfArrays masks=noArray())
 
virtual void detectAndCompute (InputArray image, InputArray mask, std::vector< KeyPoint > &keypoints, OutputArray descriptors, bool useProvidedKeypoints=false)
 
virtual bool empty () const CV_OVERRIDE
 Return true if detector object is empty. More...
 
virtual String getDefaultName () const CV_OVERRIDE
 
void read (const String &fileName)
 
virtual void read (const FileNode &) CV_OVERRIDE
 Reads algorithm parameters from a file storage. More...
 
void write (const String &fileName) const
 
virtual void write (FileStorage &) const CV_OVERRIDE
 Stores algorithm parameters in a file storage. More...
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 
- Public Member Functions inherited from cv::Algorithm
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 Clears the algorithm state. More...
 
virtual void save (const String &filename) const
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 simplified API for language bindings This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...
 
- Protected Member Functions inherited from cv::Algorithm
void writeFormat (FileStorage &fs) const
 

Detailed Description

Class implementing TEBLID (Triplet-based Efficient Binary Local Image Descriptor), described in [237].

TEBLID stands for Triplet-based Efficient Binary Local Image Descriptor, although originally it was called BAD [237]. It is an improvement over BEBLID [236], that uses triplet loss, hard negative mining, and anchor swap to improve the image matching results. It is able to describe keypoints from any detector just by changing the scale_factor parameter. TEBLID is as efficient as ORB, BEBLID or BRISK, but the triplet-based training objective selected more discriminative features that explain the accuracy gain. It is also more compact than BEBLID, when running the AKAZE example with 10000 keypoints detected by ORB, BEBLID obtains 561 inliers (75%) with 512 bits, whereas TEBLID obtains 621 (75.2%) with 256 bits. ORB obtains only 493 inliers (63%).

If you find this code useful, please add a reference to the following paper:

Iago Suárez, José M. Buenaposada, and Luis Baumela. Revisiting Binary Local Image Description for Resource Limited Devices. IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 8317-8324, Oct. 2021.

The descriptor was trained in Liberty split of the UBC datasets [278] .

Member Enumeration Documentation

◆ TeblidSize

Descriptor number of bits, each bit is a box average difference. The user can choose between 256 or 512 bits.

Enumerator
SIZE_256_BITS 
SIZE_512_BITS 

Member Function Documentation

◆ create()

static Ptr<TEBLID> cv::xfeatures2d::TEBLID::create ( float  scale_factor,
int  n_bits = TEBLID::SIZE_256_BITS 
)
static
Python:
cv.xfeatures2d.TEBLID.create(scale_factor[, n_bits]) -> retval
cv.xfeatures2d.TEBLID_create(scale_factor[, n_bits]) -> retval

Creates the TEBLID descriptor.

Parameters
scale_factorAdjust the sampling window around detected keypoints:
  • 1.00f should be the scale for ORB keypoints
  • 6.75f should be the scale for SIFT detected keypoints
  • 6.25f is default and fits for KAZE, SURF detected keypoints
  • 5.00f should be the scale for AKAZE, MSD, AGAST, FAST, BRISK keypoints
n_bitsDetermine the number of bits in the descriptor. Should be either TEBLID::SIZE_256_BITS or TEBLID::SIZE_512_BITS.

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