OpenCV  4.5.1
Open Source Computer Vision
Classes | Functions

Classes

class  cv::cuda::CornernessCriteria
 Base class for Cornerness Criteria computation. : More...
 
class  cv::cuda::CornersDetector
 Base class for Corners Detector. : More...
 

Functions

Ptr< CornersDetectorcv::cuda::createGoodFeaturesToTrackDetector (int srcType, int maxCorners=1000, double qualityLevel=0.01, double minDistance=0.0, int blockSize=3, bool useHarrisDetector=false, double harrisK=0.04)
 Creates implementation for cuda::CornersDetector . More...
 
Ptr< CornernessCriteriacv::cuda::createHarrisCorner (int srcType, int blockSize, int ksize, double k, int borderType=BORDER_REFLECT101)
 Creates implementation for Harris cornerness criteria. More...
 
Ptr< CornernessCriteriacv::cuda::createMinEigenValCorner (int srcType, int blockSize, int ksize, int borderType=BORDER_REFLECT101)
 Creates implementation for the minimum eigen value of a 2x2 derivative covariation matrix (the cornerness criteria). More...
 

Detailed Description

Function Documentation

◆ createGoodFeaturesToTrackDetector()

Ptr<CornersDetector> cv::cuda::createGoodFeaturesToTrackDetector ( int  srcType,
int  maxCorners = 1000,
double  qualityLevel = 0.01,
double  minDistance = 0.0,
int  blockSize = 3,
bool  useHarrisDetector = false,
double  harrisK = 0.04 
)

#include <opencv2/cudaimgproc.hpp>

Creates implementation for cuda::CornersDetector .

Parameters
srcTypeInput source type. Only CV_8UC1 and CV_32FC1 are supported for now.
maxCornersMaximum number of corners to return. If there are more corners than are found, the strongest of them is returned.
qualityLevelParameter characterizing the minimal accepted quality of image corners. The parameter value is multiplied by the best corner quality measure, which is the minimal eigenvalue (see cornerMinEigenVal ) or the Harris function response (see cornerHarris ). The corners with the quality measure less than the product are rejected. For example, if the best corner has the quality measure = 1500, and the qualityLevel=0.01 , then all the corners with the quality measure less than 15 are rejected.
minDistanceMinimum possible Euclidean distance between the returned corners.
blockSizeSize of an average block for computing a derivative covariation matrix over each pixel neighborhood. See cornerEigenValsAndVecs .
useHarrisDetectorParameter indicating whether to use a Harris detector (see cornerHarris) or cornerMinEigenVal.
harrisKFree parameter of the Harris detector.

◆ createHarrisCorner()

Ptr<CornernessCriteria> cv::cuda::createHarrisCorner ( int  srcType,
int  blockSize,
int  ksize,
double  k,
int  borderType = BORDER_REFLECT101 
)

#include <opencv2/cudaimgproc.hpp>

Creates implementation for Harris cornerness criteria.

Parameters
srcTypeInput source type. Only CV_8UC1 and CV_32FC1 are supported for now.
blockSizeNeighborhood size.
ksizeAperture parameter for the Sobel operator.
kHarris detector free parameter.
borderTypePixel extrapolation method. Only BORDER_REFLECT101 and BORDER_REPLICATE are supported for now.
See also
cornerHarris

◆ createMinEigenValCorner()

Ptr<CornernessCriteria> cv::cuda::createMinEigenValCorner ( int  srcType,
int  blockSize,
int  ksize,
int  borderType = BORDER_REFLECT101 
)

#include <opencv2/cudaimgproc.hpp>

Creates implementation for the minimum eigen value of a 2x2 derivative covariation matrix (the cornerness criteria).

Parameters
srcTypeInput source type. Only CV_8UC1 and CV_32FC1 are supported for now.
blockSizeNeighborhood size.
ksizeAperture parameter for the Sobel operator.
borderTypePixel extrapolation method. Only BORDER_REFLECT101 and BORDER_REPLICATE are supported for now.
See also
cornerMinEigenVal