C# Class Emgu.CV.GPU.GpuHOGDescriptor

A HOG discriptor

Inheritance: Emgu.Util.UnmanagedObject

Public Methods

Method	Description
DetectMultiScale ( Byte>.GpuImage image ) : System.Drawing.Rectangle[]	Perfroms object detection with increasing detection window.
DetectMultiScale ( Byte>.GpuImage image, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) : System.Drawing.Rectangle[]	Perfroms object detection with increasing detection window.
DetectMultiScale ( Byte>.GpuImage image ) : System.Drawing.Rectangle[]	Perfroms object detection with increasing detection window.
DetectMultiScale ( Byte>.GpuImage image, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) : System.Drawing.Rectangle[]	Perfroms object detection with increasing detection window.
GetDefaultPeopleDetector ( ) : float[]	Returns coefficients of the classifier trained for people detection (for default window size).
GpuHOGDescriptor ( ) : System	Create a new HOGDescriptor
GpuHOGDescriptor ( Size winSize, Size blockSize, Size blockStride, Size cellSize, int nbins, double winSigma, double L2HysThreshold, bool gammaCorrection, int nLevels ) : System	Create a new HOGDescriptor using the specific parameters
SetSVMDetector ( float detector ) : void	Set the SVM detector

Method	Description
DisposeObject ( ) : void	Release the unmanaged memory associated with this HOGDescriptor
ReleaseManagedResources ( ) : void	Release the managed resources associated with this object

Method	Description
gpuHOGDescriptorCreate ( Size &winSize, Size &blockSize, Size &blockStride, Size &cellSize, int nbins, double winSigma, double L2HysThreshold, [ gammaCorrection, int nLevels ) : IntPtr
gpuHOGDescriptorCreateDefault ( ) : IntPtr
gpuHOGDescriptorDetectMultiScale ( IntPtr descriptor, IntPtr img, IntPtr foundLocations, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) : void
gpuHOGDescriptorPeopleDetectorCreate ( IntPtr seq ) : void
gpuHOGDescriptorRelease ( IntPtr descriptor ) : void
gpuHOGSetSVMDetector ( IntPtr descriptor, IntPtr svmDetector ) : void

Perfroms object detection with increasing detection window.

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

Perfroms object detection with increasing detection window.

public DetectMultiScale ( Byte>.GpuImage image, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) : System.Drawing.Rectangle[]
image	Byte>.GpuImage	The GpuImage to search in
hitThreshold	double	The threshold for the distance between features and classifying plane.
winStride	System.Drawing.Size	Window stride. Must be a multiple of block stride.
padding	System.Drawing.Size	Mock parameter to keep CPU interface compatibility. Must be (0,0).
scale	double	Coefficient of the detection window increase.
groupThreshold	int	After detection some objects could be covered by many rectangles. This coefficient regulates similarity threshold. 0 means don't perform grouping.
return	System.Drawing.Rectangle[]

Perfroms object detection with increasing detection window.

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

Perfroms object detection with increasing detection window.

public DetectMultiScale ( Byte>.GpuImage image, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) : System.Drawing.Rectangle[]
image	Byte>.GpuImage	The GpuImage to search in
hitThreshold	double	The threshold for the distance between features and classifying plane.
winStride	System.Drawing.Size	Window stride. Must be a multiple of block stride.
padding	System.Drawing.Size	Mock parameter to keep CPU interface compatibility. Must be (0,0).
scale	double	Coefficient of the detection window increase.
groupThreshold	int	After detection some objects could be covered by many rectangles. This coefficient regulates similarity threshold. 0 means don't perform grouping.
return	System.Drawing.Rectangle[]

Release the unmanaged memory associated with this HOGDescriptor

protected DisposeObject ( ) : void
return	void

Returns coefficients of the classifier trained for people detection (for default window size).

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

Create a new HOGDescriptor

public GpuHOGDescriptor ( ) : System
return	System

Create a new HOGDescriptor using the specific parameters

public GpuHOGDescriptor ( Size winSize, Size blockSize, Size blockStride, Size cellSize, int nbins, double winSigma, double L2HysThreshold, bool gammaCorrection, int nLevels ) : System
winSize	System.Drawing.Size	Detection window size. Must be aligned to block size and block stride.
blockSize	System.Drawing.Size	Block size in cells. Only (2,2) is supported for now.
blockStride	System.Drawing.Size	Block stride. Must be a multiple of cell size.
cellSize	System.Drawing.Size	Cell size. Only (8, 8) is supported for now.
nbins	int	Number of bins. Only 9 bins per cell is supported for now.
winSigma	double	Gaussian smoothing window parameter.
L2HysThreshold	double	L2-Hys normalization method shrinkage.
gammaCorrection	bool	Do gamma correction preprocessing or not.
nLevels	int	Maximum number of detection window increases.
return	System

Release the managed resources associated with this object

protected ReleaseManagedResources ( ) : void
return	void

Set the SVM detector

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