Ximgproc_edgeboxes

クラス
struct	cv::ximgproc::Box
class	cv::ximgproc::EdgeBoxes
	Class implementing EdgeBoxes algorithm from [ZitnickECCV14edgeBoxes] : [詳解]

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

関数
CV_EXPORTS_W 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)
	Creates a Edgeboxes [詳解]

詳解

関数詳解

createEdgeBoxes()

CV_EXPORTS_W 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
	)

Creates a Edgeboxes

引数

alpha	step size of sliding window search.
beta	nms threshold for object proposals.
eta	adaptation rate for nms threshold.
minScore	min score of boxes to detect.
maxBoxes	max number of boxes to detect.
edgeMinMag	edge min magnitude. Increase to trade off accuracy for speed.
edgeMergeThr	edge merge threshold. Increase to trade off accuracy for speed.
clusterMinMag	cluster min magnitude. Increase to trade off accuracy for speed.
maxAspectRatio	max aspect ratio of boxes.
minBoxArea	minimum area of boxes.
gamma	affinity sensitivity.
kappa	scale sensitivity.