OpenCV  4.0.0-rc
Open Source Computer Vision
Classes | Typedefs | Functions

Classes

struct  cv::ximgproc::Box
 
class  cv::ximgproc::EdgeBoxes
 Class implementing EdgeBoxes algorithm from [236] : More...
 

Typedefs

typedef std::vector< Boxcv::ximgproc::Boxes
 

Functions

Ptr< EdgeBoxescv::ximgproc::createEdgeBoxes (float alpha=0.65f, float beta=0.75f, float eta=1, float minScore=0.01f, int maxBoxes=10000, float edgeMinMag=0.1f, float edgeMergeThr=0.5f, float clusterMinMag=0.5f, float maxAspectRatio=3, float minBoxArea=1000, float gamma=2, float kappa=1.5f)
 Creates a Edgeboxes. More...
 

Detailed Description

Typedef Documentation

§ Boxes

typedef std::vector<Box> cv::ximgproc::Boxes

Function Documentation

§ createEdgeBoxes()

Ptr<EdgeBoxes> cv::ximgproc::createEdgeBoxes ( float  alpha = 0.65f,
float  beta = 0.75f,
float  eta = 1,
float  minScore = 0.01f,
int  maxBoxes = 10000,
float  edgeMinMag = 0.1f,
float  edgeMergeThr = 0.5f,
float  clusterMinMag = 0.5f,
float  maxAspectRatio = 3,
float  minBoxArea = 1000,
float  gamma = 2,
float  kappa = 1.5f 
)
Python:
retval=cv.ximgproc.createEdgeBoxes([, alpha[, beta[, eta[, minScore[, maxBoxes[, edgeMinMag[, edgeMergeThr[, clusterMinMag[, maxAspectRatio[, minBoxArea[, gamma[, kappa]]]]]]]]]]]])

Creates a Edgeboxes.

Parameters
alphastep size of sliding window search.
betanms threshold for object proposals.
etaadaptation rate for nms threshold.
minScoremin score of boxes to detect.
maxBoxesmax number of boxes to detect.
edgeMinMagedge min magnitude. Increase to trade off accuracy for speed.
edgeMergeThredge merge threshold. Increase to trade off accuracy for speed.
clusterMinMagcluster min magnitude. Increase to trade off accuracy for speed.
maxAspectRatiomax aspect ratio of boxes.
minBoxAreaminimum area of boxes.
gammaaffinity sensitivity.
kappascale sensitivity.