C# Class OpenCvSharp.HOGDescriptor

HOG (Histogram-of-Oriented-Gradients) Descriptor and Object Detector

Inheritance: OpenCvSharp.DisposableCvObject

Afficher le fichier Open project: shimat/opencvsharp Class Usage Examples

Méthodes publiques

Свойство	Type	Description
DaimlerPeopleDetector	float[]
DefaultPeopleDetector	float[]
SizeOf	int

Méthodes publiques

Méthode	Description
CheckDetectorSize ( ) : bool
Compute ( OpenCvSharp.Mat img, Size winStride = null, Size padding = null, System.Point locations = null ) : float[]
ComputeGradient ( OpenCvSharp.Mat img, OpenCvSharp.Mat grad, OpenCvSharp.Mat angleOfs, Size paddingTL = null, Size paddingBR = null ) : void
Detect ( OpenCvSharp.Mat img, double hitThreshold, Size winStride = null, Size padding = null, System.Point searchLocations = null ) : System.Point[]	Performs object detection without a multi-scale window.
Detect ( OpenCvSharp.Mat img, double &weights, double hitThreshold, Size winStride = null, Size padding = null, System.Point searchLocations = null ) : System.Point[]	Performs object detection without a multi-scale window.
DetectMultiScale ( OpenCvSharp.Mat img, double hitThreshold, Size winStride = null, Size padding = null, double scale = 1.05, int groupThreshold = 2 ) : Rect[]	Performs object detection with a multi-scale window.
DetectMultiScale ( OpenCvSharp.Mat img, double &foundWeights, double hitThreshold, Size winStride = null, Size padding = null, double scale = 1.05, int groupThreshold = 2 ) : Rect[]	Performs object detection with a multi-scale window.
DetectMultiScaleROI ( OpenCvSharp.Mat img, Rect &foundLocations, DetectionROI &locations, double hitThreshold, int groupThreshold ) : void	evaluate specified ROI and return confidence value for each location in multiple scales
DetectROI ( OpenCvSharp.Mat img, System.Point locations, System.Point &foundLocations, double &confidences, double hitThreshold, Size winStride = null, Size padding = null ) : void	evaluate specified ROI and return confidence value for each location
GetDaimlerPeopleDetector ( ) : float[]	This method returns 1981 SVM coeffs obtained from daimler's base. To use these coeffs the detection window size should be (48,96)
GetDefaultPeopleDetector ( ) : float[]	Returns coefficients of the classifier trained for people detection (for default window size).
GetDescriptorSize ( ) : int
GetWinSigma ( ) : double
GroupRectangles ( Rect &rectList, double &weights, int groupThreshold, double eps ) : void
HOGDescriptor ( ) : System	Default constructor
HOGDescriptor ( IntPtr ptr ) : System	Initializes from pointer
HOGDescriptor ( Size winSize = null, Size blockSize = null, Size blockStride = null, Size cellSize = null, int nbins = 9, int derivAperture = 1, double winSigma = -1, HistogramNormType histogramNormType = HistogramNormType.L2Hys, double l2HysThreshold = 0.2, bool gammaCorrection = true, int nlevels = DefaultNlevels ) : System	Creates the HOG descriptor and detector.
HOGDescriptor ( string fileName ) : System
Load ( string fileName, string objName = null ) : bool
ReadALTModel ( string modelFile ) : void	read/parse Dalal's alt model file
Save ( string fileName, string objName = null ) : void
SetSVMDetector ( float svmDetector ) : void

Méthodes protégées

Méthode	Description
Dispose ( bool disposing ) : void	Clean up any resources being used.

Method Details

CheckDetectorSize() public méthode

public CheckDetectorSize ( ) : bool
Résultat	bool

Compute() public méthode

public Compute ( OpenCvSharp.Mat img, Size winStride = null, Size padding = null, System.Point locations = null ) : float[]
img	OpenCvSharp.Mat
winStride	Size
padding	Size
locations	System.Point
Résultat	float[]

ComputeGradient() public méthode

public ComputeGradient ( OpenCvSharp.Mat img, OpenCvSharp.Mat grad, OpenCvSharp.Mat angleOfs, Size paddingTL = null, Size paddingBR = null ) : void
img	OpenCvSharp.Mat
grad	OpenCvSharp.Mat
angleOfs	OpenCvSharp.Mat
paddingTL	Size
paddingBR	Size
Résultat	void

Detect() public méthode

Performs object detection without a multi-scale window.

public Detect ( OpenCvSharp.Mat img, double hitThreshold, Size winStride = null, Size padding = null, System.Point searchLocations = null ) : System.Point[]
img	OpenCvSharp.Mat	Source image. CV_8UC1 and CV_8UC4 types are supported for now.
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	Size	Window stride. It must be a multiple of block stride.
padding	Size	Mock parameter to keep the CPU interface compatibility. It must be (0,0).
searchLocations	System.Point
Résultat	System.Point[]

Detect() public méthode

Performs object detection without a multi-scale window.

public Detect ( OpenCvSharp.Mat img, double &weights, double hitThreshold, Size winStride = null, Size padding = null, System.Point searchLocations = null ) : System.Point[]
img	OpenCvSharp.Mat	Source image. CV_8UC1 and CV_8UC4 types are supported for now.
weights	double
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	Size	Window stride. It must be a multiple of block stride.
padding	Size	Mock parameter to keep the CPU interface compatibility. It must be (0,0).
searchLocations	System.Point
Résultat	System.Point[]

DetectMultiScale() public méthode

Performs object detection with a multi-scale window.

public DetectMultiScale ( OpenCvSharp.Mat img, double hitThreshold, Size winStride = null, Size padding = null, double scale = 1.05, int groupThreshold = 2 ) : Rect[]
img	OpenCvSharp.Mat	Source image. CV_8UC1 and CV_8UC4 types are supported for now.
hitThreshold	double	Threshold for the distance between features and SVM classifying plane.
winStride	Size	Window stride. It must be a multiple of block stride.
padding	Size	Mock parameter to keep the CPU interface compatibility. It must be (0,0).
scale	double	Coefficient of the detection window increase.
groupThreshold	int	Coefficient to regulate the similarity threshold. /// When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
Résultat	Rect[]

DetectMultiScale() public méthode

Performs object detection with a multi-scale window.

public DetectMultiScale ( OpenCvSharp.Mat img, double &foundWeights, double hitThreshold, Size winStride = null, Size padding = null, double scale = 1.05, int groupThreshold = 2 ) : Rect[]
img	OpenCvSharp.Mat	Source image. CV_8UC1 and CV_8UC4 types are supported for now.
foundWeights	double
hitThreshold	double	Threshold for the distance between features and SVM classifying plane.
winStride	Size	Window stride. It must be a multiple of block stride.
padding	Size	Mock parameter to keep the CPU interface compatibility. It must be (0,0).
scale	double	Coefficient of the detection window increase.
groupThreshold	int	Coefficient to regulate the similarity threshold. /// When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
Résultat	Rect[]

DetectMultiScaleROI() public méthode

evaluate specified ROI and return confidence value for each location in multiple scales

public DetectMultiScaleROI ( OpenCvSharp.Mat img, Rect &foundLocations, DetectionROI &locations, double hitThreshold, int groupThreshold ) : void
img	OpenCvSharp.Mat
foundLocations	Rect
locations	DetectionROI
hitThreshold	double
groupThreshold	int
Résultat	void

DetectROI() public méthode

evaluate specified ROI and return confidence value for each location

public DetectROI ( OpenCvSharp.Mat img, System.Point locations, System.Point &foundLocations, double &confidences, double hitThreshold, Size winStride = null, Size padding = null ) : void
img	OpenCvSharp.Mat
locations	System.Point
foundLocations	System.Point
confidences	double
hitThreshold	double
winStride	Size
padding	Size
Résultat	void

Dispose() protected méthode

Clean up any resources being used.

protected Dispose ( bool disposing ) : void
disposing	bool	/// If disposing equals true, the method has been called directly or indirectly by a user's code. Managed and unmanaged resources can be disposed. /// If false, the method has been called by the runtime from inside the finalizer and you should not reference other objects. Only unmanaged resources can be disposed. ///
Résultat	void

GetDaimlerPeopleDetector() public static méthode

This method returns 1981 SVM coeffs obtained from daimler's base. To use these coeffs the detection window size should be (48,96)

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

GetDefaultPeopleDetector() public static méthode

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

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

GetDescriptorSize() public méthode

public GetDescriptorSize ( ) : int
Résultat	int

GetWinSigma() public méthode

public GetWinSigma ( ) : double
Résultat	double

GroupRectangles() public méthode

public GroupRectangles ( Rect &rectList, double &weights, int groupThreshold, double eps ) : void
rectList	Rect
weights	double
groupThreshold	int
eps	double
Résultat	void

HOGDescriptor() public méthode

Default constructor

public HOGDescriptor ( ) : System
Résultat	System

HOGDescriptor() public méthode

Initializes from pointer

public HOGDescriptor ( IntPtr ptr ) : System
ptr	System.IntPtr	class HOGDescriptor*
Résultat	System

HOGDescriptor() public méthode

Creates the HOG descriptor and detector.

public HOGDescriptor ( Size winSize = null, Size blockSize = null, Size blockStride = null, Size cellSize = null, int nbins = 9, int derivAperture = 1, double winSigma = -1, HistogramNormType histogramNormType = HistogramNormType.L2Hys, double l2HysThreshold = 0.2, bool gammaCorrection = true, int nlevels = DefaultNlevels ) : System
winSize	Size	Detection window size. Align to block size and block stride.
blockSize	Size	Block size in pixels. Align to cell size. Only (16,16) is supported for now.
blockStride	Size	Block stride. It must be a multiple of cell size.
cellSize	Size	Cell size. Only (8, 8) is supported for now.
nbins	int	Number of bins. Only 9 bins per cell are supported for now.
derivAperture	int
winSigma	double	Gaussian smoothing window parameter.
histogramNormType	HistogramNormType
l2HysThreshold	double	L2-Hys normalization method shrinkage.
gammaCorrection	bool	Flag to specify whether the gamma correction preprocessing is required or not.
nlevels	int	Maximum number of detection window increases.
Résultat	System

HOGDescriptor() public méthode

public HOGDescriptor ( string fileName ) : System
fileName	string
Résultat	System

Load() public méthode

public Load ( string fileName, string objName = null ) : bool
fileName	string
objName	string
Résultat	bool

ReadALTModel() public méthode

read/parse Dalal's alt model file

public ReadALTModel ( string modelFile ) : void
modelFile	string
Résultat	void

Save() public méthode

public Save ( string fileName, string objName = null ) : void
fileName	string
objName	string
Résultat	void

SetSVMDetector() public méthode

public SetSVMDetector ( float svmDetector ) : void
svmDetector	float
Résultat	void

Property Details

DaimlerPeopleDetector public_oe static_oe property

This field returns 1981 SVM coeffs obtained from daimler's base. To use these coeffs the detection window size should be (48,96)

public static float[] DaimlerPeopleDetector
Résultat	float[]

DefaultPeopleDetector public_oe static_oe property

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

public static float[] DefaultPeopleDetector
Résultat	float[]

SizeOf public_oe static_oe property

sizeof(HOGDescriptor)

public static int SizeOf
Résultat	int