Experimental 2D Features Algorithms#
Detailed Description#
This section describes experimental algorithms for 2d feature detection.
Classes#
Name |
Description |
|---|---|
Class implementing affine adaptation for key points. View details |
|
Wrapping class for feature detection using the AGAST method. : View details |
|
|
Class implementing the AKAZE keypoint detector and descriptor extractor, described in [12]. View details |
|
Class implementing BEBLID (Boosted Efficient Binary Local Image Descriptor), described in [288] . View details |
Class implementing BoostDesc (Learning Image Descriptors with Boosting), described in [294] and [295]. View details |
|
Class for computing BRIEF descriptors described in [53] . View details |
|
|
Class implementing the BRISK keypoint detector and descriptor extractor, described in [177] . View details |
|
Class implementing DAISY descriptor, described in [304]. View details |
Elliptic region around an interest point. View details |
|
|
Class implementing the FREAK (Fast Retina Keypoint) keypoint descriptor, described in [10] . View details |
Class implementing the Harris-Laplace feature detector as described in [214]. View details |
|
|
Class implementing the KAZE keypoint detector and descriptor extractor, described in [11] . View details |
|
|
|
Class implementing the locally uniform comparison image descriptor, described in [360]. View details |
Class implementing the MSD (Maximal Self-Dissimilarity) keypoint detector, described in [305]. View details |
|
Class implementing PCT (position-color-texture) signature extraction as described in [171]. The algorithm is divided to a feature sampler and a clusterizer. Feature sampler produces samples at given set of coordinates. Clusterizer then produces clusters of these samples using k-means algorithm. Resulting set of clusters is the signature of the input image. View details |
|
Class implementing Signature Quadratic Form Distance (SQFD). View details |
|
The class implements the keypoint detector introduced by [3], synonym of StarDetector. : View details |
|
|
Class implementing the Tree Based Morse Regions (TBMR) as described in [344] extended with scaled extraction ability. View details |
|
Class implementing TEBLID (Triplet-based Efficient Binary Local Image Descriptor), described in [289]. View details |
|
Class implementing VGG (Oxford Visual Geometry Group) descriptor trained end to end using “Descriptor Learning Using Convex Optimisation” (DLCO) aparatus described in [275]. View details |
Function Documentation#
AGAST()#
void cv::xfeatures2d::AGAST(
InputArray image,
std::vector< KeyPoint > & keypoints,
int threshold,
bool nonmaxSuppression = true,
AgastFeatureDetector::DetectorType type = AgastFeatureDetector::OAST_9_16 )
#include <opencv2/xfeatures2d.hpp>
Detects corners using the AGAST algorithm.
For non-Intel platforms, there is a tree optimised variant of AGAST with same numerical results. The 32-bit binary tree tables were generated automatically from original code using perl script. The perl script and examples of tree generation are placed in features2d/doc folder. Detects corners using the AGAST algorithm by [201] .
Parameters
image— grayscale image where keypoints (corners) are detected.keypoints— keypoints detected on the image.threshold— threshold on difference between intensity of the central pixel and pixels of a circle around this pixel.nonmaxSuppression— if true, non-maximum suppression is applied to detected keypoints (corners).type— one of the four neighborhoods as defined in the paper: AgastFeatureDetector::AGAST_5_8, AgastFeatureDetector::AGAST_7_12d, AgastFeatureDetector::AGAST_7_12s, AgastFeatureDetector::OAST_9_16
FASTForPointSet()#
void cv::xfeatures2d::FASTForPointSet(
InputArray image,
std::vector< KeyPoint > & keypoints,
int threshold,
bool nonmaxSuppression = true,
cv::FastFeatureDetector::DetectorType type = FastFeatureDetector::TYPE_9_16 )
#include <opencv2/xfeatures2d.hpp>
Estimates cornerness for prespecified KeyPoints using the FAST algorithm.
Detects corners using the FAST algorithm by [253] .
Parameters
image— grayscale image where keypoints (corners) are detected.keypoints— keypoints which should be tested to fit the FAST criteria. Keypoints not being detected as corners are removed.threshold— threshold on difference between intensity of the central pixel and pixels of a circle around this pixel.nonmaxSuppression— if true, non-maximum suppression is applied to detected corners (keypoints).type— one of the three neighborhoods as defined in the paper: FastFeatureDetector::TYPE_9_16, FastFeatureDetector::TYPE_7_12, FastFeatureDetector::TYPE_5_8