C# Class Emgu.CV.HOGDescriptor

A HOG discriptor

Inheritance: Emgu.Util.UnmanagedObject

Méthodes publiques

Méthode	Description
Compute ( Byte>.Image image, Size winStride, Size padding, Point locations ) : float[]
DetectMultiScale ( Byte>.Image image ) : System.Drawing.Rectangle[]	Perfroms object detection with increasing detection window.
DetectMultiScale ( Byte>.Image image, double hitThreshold, Size winStride, Size padding, double scale, int finalThreshold, bool useMeanshiftGrouping ) : System.Drawing.Rectangle[]	Perfroms object detection with increasing detection window.
GetDefaultPeopleDetector ( ) : float[]	Return the default people detector
HOGDescriptor ( ) : System	Create a new HOGDescriptor
HOGDescriptor ( Byte>.Image template ) : System	Create a new HogDescriptor using the specific template and default parameters.
HOGDescriptor ( Byte>.Image template, Size blockSize, Size blockStride, Size cellSize, int nbins, int derivAperture, double winSigma, double L2HysThreshold, bool gammaCorrection ) : System	Create a new HOGDescriptor using the specific parameters.
HOGDescriptor ( Size winSize, Size blockSize, Size blockStride, Size cellSize, int nbins, int derivAperture, double winSigma, double L2HysThreshold, bool gammaCorrection ) : System	Create a new HOGDescriptor using the specific parameters.
SetSVMDetector ( float detector ) : void	Set the SVM detector

Méthode	Description
DisposeObject ( ) : void	Release the unmanaged memory associated with this HOGDescriptor

public Compute ( Byte>.Image image, Size winStride, Size padding, Point locations ) : float[]
image	Byte>.Image	The image
winStride	System.Drawing.Size	Window stride. Must be a multiple of block stride. Use Size.Empty for default
padding	System.Drawing.Size	Padding. Use Size.Empty for default
locations	Point	Locations for the computation. Can be null if not needed
Résultat	float[]

Perfroms object detection with increasing detection window.

public DetectMultiScale ( Byte>.Image image ) : System.Drawing.Rectangle[]
image	Byte>.Image	The image to search in
Résultat	System.Drawing.Rectangle[]

Perfroms object detection with increasing detection window.

public DetectMultiScale ( Byte>.Image image, double hitThreshold, Size winStride, Size padding, double scale, int finalThreshold, bool useMeanshiftGrouping ) : System.Drawing.Rectangle[]
image	Byte>.Image	The image to search in
hitThreshold	double	/// Threshold for the distance between features and SVM classifying plane. /// Usually it is 0 and should be specfied in the detector coefficients (as the last free coefficient). /// But if the free coefficient is omitted (which is allowed), you can specify it manually here. ///
winStride	System.Drawing.Size	Window stride. Must be a multiple of block stride.
padding	System.Drawing.Size
scale	double	Coefficient of the detection window increase.
finalThreshold	int	After detection some objects could be covered by many rectangles. This coefficient regulates similarity threshold. 0 means don't perform grouping. Should be an integer if not using meanshift grouping. Use 2.0 for default
useMeanshiftGrouping	bool	If true, it will use meanshift grouping.
Résultat	System.Drawing.Rectangle[]

Release the unmanaged memory associated with this HOGDescriptor

protected DisposeObject ( ) : void
Résultat	void

Return the default people detector

public static GetDefaultPeopleDetector ( ) : float[]
Résultat	float[]

Create a new HOGDescriptor

public HOGDescriptor ( ) : System
Résultat	System

Create a new HogDescriptor using the specific template and default parameters.

public HOGDescriptor ( Byte>.Image template ) : System
template	Byte>.Image	The template image to be detected.
Résultat	System

Create a new HOGDescriptor using the specific parameters.

public HOGDescriptor ( Byte>.Image template, Size blockSize, Size blockStride, Size cellSize, int nbins, int derivAperture, double winSigma, double L2HysThreshold, bool gammaCorrection ) : System
template	Byte>.Image	The template image to be detected.
blockSize	System.Drawing.Size	Block size in cells. Use (16, 16) for default.
blockStride	System.Drawing.Size	Block stride. Must be a multiple of cell size. Use (8,8) for default.
cellSize	System.Drawing.Size	Cell size. Use (8, 8) for default.
nbins	int	Number of bins. Use 9 for default.
derivAperture	int	Use 1 for default.
winSigma	double	Gaussian smoothing window parameter. Use -1 for default.
L2HysThreshold	double	L2-Hys normalization method shrinkage. Use 0.2 for default.
gammaCorrection	bool	Do gamma correction preprocessing or not. Use true for default.
Résultat	System

Create a new HOGDescriptor using the specific parameters.

public HOGDescriptor ( Size winSize, Size blockSize, Size blockStride, Size cellSize, int nbins, int derivAperture, double winSigma, double L2HysThreshold, bool gammaCorrection ) : System
winSize	System.Drawing.Size	Detection window size. Must be aligned to block size and block stride. Must match the size of the training image. Use (64, 128) for default.
blockSize	System.Drawing.Size	Block size in cells. Use (16, 16) for default.
blockStride	System.Drawing.Size	Block stride. Must be a multiple of cell size. Use (8,8) for default.
cellSize	System.Drawing.Size	Cell size. Use (8, 8) for default.
nbins	int	Number of bins. Use 9 for default.
derivAperture	int	Use 1 for default.
winSigma	double	Gaussian smoothing window parameter. Use -1 for default.
L2HysThreshold	double	L2-Hys normalization method shrinkage. Use 0.2 for default.
gammaCorrection	bool	Do gamma correction preprocessing or not. Use true for default.
Résultat	System

Set the SVM detector

public SetSVMDetector ( float detector ) : void
detector	float	The SVM detector
Résultat	void