Implementation of HOG (Histogram of Oriented Gradients) descriptor and object detector. More...

Inheritance diagram for OpenCVForUnity.ObjdetectModule.HOGDescriptor:

Public Member Functions
IntPtr	getNativeObjAddr ()

	HOGDescriptor ()
	Creates the HOG descriptor and detector with default parameters. More...

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture, double _winSigma, int _histogramNormType, double _L2HysThreshold, bool _gammaCorrection, int _nlevels, bool _signedGradient)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture, double _winSigma, int _histogramNormType, double _L2HysThreshold, bool _gammaCorrection, int _nlevels)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture, double _winSigma, int _histogramNormType, double _L2HysThreshold, bool _gammaCorrection)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture, double _winSigma, int _histogramNormType, double _L2HysThreshold)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture, double _winSigma, int _histogramNormType)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture, double _winSigma)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture)

	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins)

	HOGDescriptor (string filename)

long	getDescriptorSize ()
	Returns the number of coefficients required for the classification. More...

bool	checkDetectorSize ()
	Checks if detector size equal to descriptor size. More...

double	getWinSigma ()
	Returns winSigma value. More...

void	setSVMDetector (Mat svmdetector)
	Sets coefficients for the linear SVM classifier. More...

bool	load (string filename, string objname)
	loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file More...

bool	load (string filename)
	loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file More...

void	save (string filename, string objname)
	saves HOGDescriptor parameters and coefficients for the linear SVM classifier to a file More...

void	save (string filename)
	saves HOGDescriptor parameters and coefficients for the linear SVM classifier to a file More...

void	compute (Mat img, MatOfFloat descriptors, Size winStride, Size padding, MatOfPoint locations)
	Computes HOG descriptors of given image. More...

void	compute (Mat img, MatOfFloat descriptors, Size winStride, Size padding)
	Computes HOG descriptors of given image. More...

void	compute (Mat img, MatOfFloat descriptors, Size winStride)
	Computes HOG descriptors of given image. More...

void	compute (Mat img, MatOfFloat descriptors)
	Computes HOG descriptors of given image. More...

void	detect (Mat img, MatOfPoint foundLocations, MatOfDouble weights, double hitThreshold, Size winStride, Size padding, MatOfPoint searchLocations)
	Performs object detection without a multi-scale window. More...

void	detect (Mat img, MatOfPoint foundLocations, MatOfDouble weights, double hitThreshold, Size winStride, Size padding)
	Performs object detection without a multi-scale window. More...

void	detect (Mat img, MatOfPoint foundLocations, MatOfDouble weights, double hitThreshold, Size winStride)
	Performs object detection without a multi-scale window. More...

void	detect (Mat img, MatOfPoint foundLocations, MatOfDouble weights, double hitThreshold)
	Performs object detection without a multi-scale window. More...

void	detect (Mat img, MatOfPoint foundLocations, MatOfDouble weights)
	Performs object detection without a multi-scale window. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights, double hitThreshold, Size winStride, Size padding, double scale, double groupThreshold, bool useMeanshiftGrouping)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights, double hitThreshold, Size winStride, Size padding, double scale, double groupThreshold)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights, double hitThreshold, Size winStride, Size padding, double scale)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights, double hitThreshold, Size winStride, Size padding)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights, double hitThreshold, Size winStride)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights, double hitThreshold)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	detectMultiScale (Mat img, MatOfRect foundLocations, MatOfDouble foundWeights)
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. More...

void	computeGradient (Mat img, Mat grad, Mat angleOfs, Size paddingTL, Size paddingBR)
	Computes gradients and quantized gradient orientations. More...

void	computeGradient (Mat img, Mat grad, Mat angleOfs, Size paddingTL)
	Computes gradients and quantized gradient orientations. More...

void	computeGradient (Mat img, Mat grad, Mat angleOfs)
	Computes gradients and quantized gradient orientations. More...

Size	get_winSize ()

Size	get_blockSize ()

Size	get_blockStride ()

Size	get_cellSize ()

int	get_nbins ()

int	get_derivAperture ()

double	get_winSigma ()

int	get_histogramNormType ()

double	get_L2HysThreshold ()

bool	get_gammaCorrection ()

MatOfFloat	get_svmDetector ()

int	get_nlevels ()

bool	get_signedGradient ()

Public Member Functions inherited from OpenCVForUnity.DisposableObject
void	Dispose ()

void	ThrowIfDisposed ()

Static Public Member Functions
static HOGDescriptor	__fromPtr__ (IntPtr addr)

static MatOfFloat	getDefaultPeopleDetector ()
	Returns coefficients of the classifier trained for people detection (for 64x128 windows). More...

static MatOfFloat	getDaimlerPeopleDetector ()
	Returns coefficients of the classifier trained for people detection (for 48x96 windows). More...

Static Public Member Functions inherited from OpenCVForUnity.DisposableObject
static IntPtr	ThrowIfNullIntPtr (IntPtr ptr)

Public Attributes
const int	DEFAULT_NLEVELS = 64

const int	DESCR_FORMAT_COL_BY_COL = 0

const int	DESCR_FORMAT_ROW_BY_ROW = 1

const int	L2Hys = 0

Protected Member Functions
override void	Dispose (bool disposing)

Protected Member Functions inherited from OpenCVForUnity.DisposableOpenCVObject
	DisposableOpenCVObject ()

	DisposableOpenCVObject (IntPtr ptr)

	DisposableOpenCVObject (bool isEnabledDispose)

	DisposableOpenCVObject (IntPtr ptr, bool isEnabledDispose)

Protected Member Functions inherited from OpenCVForUnity.DisposableObject
	DisposableObject ()

	DisposableObject (bool isEnabledDispose)

Additional Inherited Members
Properties inherited from OpenCVForUnity.DisposableObject
bool	IsDisposed `[get, protected set]`

bool	IsEnabledDispose `[get, set]`

Detailed Description

Implementation of HOG (Histogram of Oriented Gradients) descriptor and object detector.

the HOG descriptor algorithm introduced by Navneet Dalal and Bill Triggs [Dalal2005] .

useful links:

https://hal.inria.fr/inria-00548512/document/

https://en.wikipedia.org/wiki/Histogram_of_oriented_gradients

https://software.intel.com/en-us/ipp-dev-reference-histogram-of-oriented-gradients-hog-descriptor

http://www.learnopencv.com/histogram-of-oriented-gradients

http://www.learnopencv.com/handwritten-digits-classification-an-opencv-c-python-tutorial

Constructor & Destructor Documentation

◆ HOGDescriptor() [1/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor ( )

Creates the HOG descriptor and detector with default parameters.

aqual to HOGDescriptor(Size(64,128), Size(16,16), Size(8,8), Size(8,8), 9 )

◆ HOGDescriptor() [2/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture,
		double	_winSigma,
		int	_histogramNormType,
		double	_L2HysThreshold,
		bool	_gammaCorrection,
		int	_nlevels,
		bool	_signedGradient
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [3/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture,
		double	_winSigma,
		int	_histogramNormType,
		double	_L2HysThreshold,
		bool	_gammaCorrection,
		int	_nlevels
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [4/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture,
		double	_winSigma,
		int	_histogramNormType,
		double	_L2HysThreshold,
		bool	_gammaCorrection
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [5/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture,
		double	_winSigma,
		int	_histogramNormType,
		double	_L2HysThreshold
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [6/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture,
		double	_winSigma,
		int	_histogramNormType
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [7/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture,
		double	_winSigma
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [8/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [9/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

_winSize	sets winSize with given value.
_blockSize	sets blockSize with given value.
_blockStride	sets blockStride with given value.
_cellSize	sets cellSize with given value.
_nbins	sets nbins with given value.
_derivAperture	sets derivAperture with given value.
_winSigma	sets winSigma with given value.
_histogramNormType	sets histogramNormType with given value.
_L2HysThreshold	sets L2HysThreshold with given value.
_gammaCorrection	sets gammaCorrection with given value.
_nlevels	sets nlevels with given value.
_signedGradient	sets signedGradient with given value.

◆ HOGDescriptor() [10/10]

OpenCVForUnity.ObjdetectModule.HOGDescriptor.HOGDescriptor ( string filename )

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Creates the HOG descriptor and detector and loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file.

Parameters

filename The file name containing HOGDescriptor properties and coefficients for the linear SVM classifier.

Member Function Documentation

◆ fromPtr()

static HOGDescriptor OpenCVForUnity.ObjdetectModule.HOGDescriptor.__fromPtr__ ( IntPtr addr )

static

◆ checkDetectorSize()

bool OpenCVForUnity.ObjdetectModule.HOGDescriptor.checkDetectorSize ( )

Checks if detector size equal to descriptor size.

◆ compute() [1/4]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.compute	(	Mat	img,
		MatOfFloat	descriptors,
		Size	winStride,
		Size	padding,
		MatOfPoint	locations
	)

Computes HOG descriptors of given image.

Parameters

img	Matrix of the type CV_8U containing an image where HOG features will be calculated.
descriptors	Matrix of the type CV_32F
winStride	Window stride. It must be a multiple of block stride.
padding	Padding
locations	Vector of Point

◆ compute() [2/4]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.compute	(	Mat	img,
		MatOfFloat	descriptors,
		Size	winStride,
		Size	padding
	)

Computes HOG descriptors of given image.

Parameters

img	Matrix of the type CV_8U containing an image where HOG features will be calculated.
descriptors	Matrix of the type CV_32F
winStride	Window stride. It must be a multiple of block stride.
padding	Padding
locations	Vector of Point

◆ compute() [3/4]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.compute	(	Mat	img,
		MatOfFloat	descriptors,
		Size	winStride
	)

Computes HOG descriptors of given image.

Parameters

img	Matrix of the type CV_8U containing an image where HOG features will be calculated.
descriptors	Matrix of the type CV_32F
winStride	Window stride. It must be a multiple of block stride.
padding	Padding
locations	Vector of Point

◆ compute() [4/4]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.compute	(	Mat	img,
		MatOfFloat	descriptors
	)

Computes HOG descriptors of given image.

Parameters

img	Matrix of the type CV_8U containing an image where HOG features will be calculated.
descriptors	Matrix of the type CV_32F
winStride	Window stride. It must be a multiple of block stride.
padding	Padding
locations	Vector of Point

◆ computeGradient() [1/3]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.computeGradient	(	Mat	img,
		Mat	grad,
		Mat	angleOfs,
		Size	paddingTL,
		Size	paddingBR
	)

Computes gradients and quantized gradient orientations.

Parameters

img	Matrix contains the image to be computed
grad	Matrix of type CV_32FC2 contains computed gradients
angleOfs	Matrix of type CV_8UC2 contains quantized gradient orientations
paddingTL	Padding from top-left
paddingBR	Padding from bottom-right

◆ computeGradient() [2/3]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.computeGradient	(	Mat	img,
		Mat	grad,
		Mat	angleOfs,
		Size	paddingTL
	)

Computes gradients and quantized gradient orientations.

Parameters

img	Matrix contains the image to be computed
grad	Matrix of type CV_32FC2 contains computed gradients
angleOfs	Matrix of type CV_8UC2 contains quantized gradient orientations
paddingTL	Padding from top-left
paddingBR	Padding from bottom-right

◆ computeGradient() [3/3]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.computeGradient	(	Mat	img,
		Mat	grad,
		Mat	angleOfs
	)

Computes gradients and quantized gradient orientations.

Parameters

img	Matrix contains the image to be computed
grad	Matrix of type CV_32FC2 contains computed gradients
angleOfs	Matrix of type CV_8UC2 contains quantized gradient orientations
paddingTL	Padding from top-left
paddingBR	Padding from bottom-right

◆ detect() [1/5]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detect	(	Mat	img,
		MatOfPoint	foundLocations,
		MatOfDouble	weights,
		double	hitThreshold,
		Size	winStride,
		Size	padding,
		MatOfPoint	searchLocations
	)

Performs object detection without a multi-scale window.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of point where each point contains left-top corner point of detected object boundaries.
weights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
searchLocations	Vector of Point includes set of requested locations to be evaluated.

◆ detect() [2/5]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detect	(	Mat	img,
		MatOfPoint	foundLocations,
		MatOfDouble	weights,
		double	hitThreshold,
		Size	winStride,
		Size	padding
	)

Performs object detection without a multi-scale window.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of point where each point contains left-top corner point of detected object boundaries.
weights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
searchLocations	Vector of Point includes set of requested locations to be evaluated.

◆ detect() [3/5]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detect	(	Mat	img,
		MatOfPoint	foundLocations,
		MatOfDouble	weights,
		double	hitThreshold,
		Size	winStride
	)

Performs object detection without a multi-scale window.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of point where each point contains left-top corner point of detected object boundaries.
weights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
searchLocations	Vector of Point includes set of requested locations to be evaluated.

◆ detect() [4/5]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detect	(	Mat	img,
		MatOfPoint	foundLocations,
		MatOfDouble	weights,
		double	hitThreshold
	)

Performs object detection without a multi-scale window.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of point where each point contains left-top corner point of detected object boundaries.
weights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
searchLocations	Vector of Point includes set of requested locations to be evaluated.

◆ detect() [5/5]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detect	(	Mat	img,
		MatOfPoint	foundLocations,
		MatOfDouble	weights
	)

Performs object detection without a multi-scale window.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of point where each point contains left-top corner point of detected object boundaries.
weights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
searchLocations	Vector of Point includes set of requested locations to be evaluated.

◆ detectMultiScale() [1/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights,
		double	hitThreshold,
		Size	winStride,
		Size	padding,
		double	scale,
		double	groupThreshold,
		bool	useMeanshiftGrouping
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [2/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights,
		double	hitThreshold,
		Size	winStride,
		Size	padding,
		double	scale,
		double	groupThreshold
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [3/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights,
		double	hitThreshold,
		Size	winStride,
		Size	padding,
		double	scale
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [4/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights,
		double	hitThreshold,
		Size	winStride,
		Size	padding
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [5/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights,
		double	hitThreshold,
		Size	winStride
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [6/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights,
		double	hitThreshold
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [7/7]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.detectMultiScale	(	Mat	img,
		MatOfRect	foundLocations,
		MatOfDouble	foundWeights
	)

Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles.

Parameters

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
foundLocations	Vector of rectangles where each rectangle contains the detected object.
foundWeights	Vector that will contain confidence values for each detected object.
hitThreshold	Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified 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	Window stride. It must be a multiple of block stride.
padding	Padding
scale	Coefficient of the detection window increase.
groupThreshold	Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping.
useMeanshiftGrouping	indicates grouping algorithm

◆ Dispose()

override void OpenCVForUnity.ObjdetectModule.HOGDescriptor.Dispose ( bool disposing )

protectedvirtual

Reimplemented from OpenCVForUnity.DisposableOpenCVObject.

◆ get_blockSize()

Size OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_blockSize ( )

◆ get_blockStride()

Size OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_blockStride ( )

◆ get_cellSize()

Size OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_cellSize ( )

◆ get_derivAperture()

int OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_derivAperture ( )

◆ get_gammaCorrection()

bool OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_gammaCorrection ( )

◆ get_histogramNormType()

int OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_histogramNormType ( )

◆ get_L2HysThreshold()

double OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_L2HysThreshold ( )

◆ get_nbins()

int OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_nbins ( )

◆ get_nlevels()

int OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_nlevels ( )

◆ get_signedGradient()

bool OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_signedGradient ( )

◆ get_svmDetector()

MatOfFloat OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_svmDetector ( )

◆ get_winSigma()

double OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_winSigma ( )

◆ get_winSize()

Size OpenCVForUnity.ObjdetectModule.HOGDescriptor.get_winSize ( )

◆ getDaimlerPeopleDetector()

static MatOfFloat OpenCVForUnity.ObjdetectModule.HOGDescriptor.getDaimlerPeopleDetector ( )

static

Returns coefficients of the classifier trained for people detection (for 48x96 windows).

◆ getDefaultPeopleDetector()

static MatOfFloat OpenCVForUnity.ObjdetectModule.HOGDescriptor.getDefaultPeopleDetector ( )

static

Returns coefficients of the classifier trained for people detection (for 64x128 windows).

◆ getDescriptorSize()

long OpenCVForUnity.ObjdetectModule.HOGDescriptor.getDescriptorSize ( )

Returns the number of coefficients required for the classification.

◆ getNativeObjAddr()

IntPtr OpenCVForUnity.ObjdetectModule.HOGDescriptor.getNativeObjAddr ( )

◆ getWinSigma()

double OpenCVForUnity.ObjdetectModule.HOGDescriptor.getWinSigma ( )

Returns winSigma value.

◆ load() [1/2]

bool OpenCVForUnity.ObjdetectModule.HOGDescriptor.load	(	string	filename,
		string	objname
	)

loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file

Parameters

filename	Name of the file to read.
objname	The optional name of the node to read (if empty, the first top-level node will be used).

◆ load() [2/2]

bool OpenCVForUnity.ObjdetectModule.HOGDescriptor.load ( string filename )

loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file

Parameters

filename	Name of the file to read.
objname	The optional name of the node to read (if empty, the first top-level node will be used).

◆ save() [1/2]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.save	(	string	filename,
		string	objname
	)

saves HOGDescriptor parameters and coefficients for the linear SVM classifier to a file

Parameters

filename	File name
objname	Object name

◆ save() [2/2]

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.save ( string filename )

saves HOGDescriptor parameters and coefficients for the linear SVM classifier to a file

Parameters

filename	File name
objname	Object name

◆ setSVMDetector()

void OpenCVForUnity.ObjdetectModule.HOGDescriptor.setSVMDetector ( Mat svmdetector )

Sets coefficients for the linear SVM classifier.

Parameters

svmdetector coefficients for the linear SVM classifier.

Member Data Documentation

◆ DEFAULT_NLEVELS

const int OpenCVForUnity.ObjdetectModule.HOGDescriptor.DEFAULT_NLEVELS = 64

◆ DESCR_FORMAT_COL_BY_COL

const int OpenCVForUnity.ObjdetectModule.HOGDescriptor.DESCR_FORMAT_COL_BY_COL = 0

◆ DESCR_FORMAT_ROW_BY_ROW

const int OpenCVForUnity.ObjdetectModule.HOGDescriptor.DESCR_FORMAT_ROW_BY_ROW = 1

◆ L2Hys

const int OpenCVForUnity.ObjdetectModule.HOGDescriptor.L2Hys = 0

The documentation for this class was generated from the following file:

OpenCVForUnity/Assets/OpenCVForUnity/org/opencv/objdetect/HOGDescriptor.cs

Public Member Functions

Static Public Member Functions

Public Attributes

Protected Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ HOGDescriptor() [1/10]

◆ HOGDescriptor() [2/10]

◆ HOGDescriptor() [3/10]

◆ HOGDescriptor() [4/10]

◆ HOGDescriptor() [5/10]

◆ HOGDescriptor() [6/10]

◆ HOGDescriptor() [7/10]

◆ HOGDescriptor() [8/10]

◆ HOGDescriptor() [9/10]

◆ HOGDescriptor() [10/10]

Member Function Documentation

◆ __fromPtr__()

◆ checkDetectorSize()

◆ compute() [1/4]

◆ compute() [2/4]

◆ compute() [3/4]

◆ compute() [4/4]

◆ computeGradient() [1/3]

◆ computeGradient() [2/3]

◆ computeGradient() [3/3]

◆ detect() [1/5]

◆ detect() [2/5]

◆ detect() [3/5]

◆ detect() [4/5]

◆ detect() [5/5]

◆ detectMultiScale() [1/7]

◆ detectMultiScale() [2/7]

◆ detectMultiScale() [3/7]

◆ detectMultiScale() [4/7]

◆ detectMultiScale() [5/7]

◆ detectMultiScale() [6/7]

◆ detectMultiScale() [7/7]

◆ Dispose()

◆ get_blockSize()

◆ get_blockStride()

◆ get_cellSize()

◆ get_derivAperture()

◆ get_gammaCorrection()

◆ get_histogramNormType()

◆ get_L2HysThreshold()

◆ get_nbins()

◆ get_nlevels()

◆ get_signedGradient()

◆ get_svmDetector()

◆ get_winSigma()

◆ get_winSize()

◆ getDaimlerPeopleDetector()

◆ getDefaultPeopleDetector()

◆ getDescriptorSize()

◆ getNativeObjAddr()

◆ getWinSigma()

◆ load() [1/2]

◆ load() [2/2]

◆ save() [1/2]

◆ save() [2/2]

◆ setSVMDetector()

Member Data Documentation

◆ DEFAULT_NLEVELS

◆ DESCR_FORMAT_COL_BY_COL

◆ DESCR_FORMAT_ROW_BY_ROW

◆ L2Hys

◆ fromPtr()