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

#include <objdetect.hpp>

公開型
enum	HistogramNormType { L2Hys = 0 }

enum	{ DEFAULT_NLEVELS = 64 }

enum	DescriptorStorageFormat { DESCR_FORMAT_COL_BY_COL , DESCR_FORMAT_ROW_BY_ROW }

公開メンバ関数
CV_WRAP	HOGDescriptor ()
	Creates the HOG descriptor and detector with default params. [詳解]

CV_WRAP	HOGDescriptor (Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture=1, double _winSigma=-1, HOGDescriptor::HistogramNormType _histogramNormType=HOGDescriptor::L2Hys, double _L2HysThreshold=0.2, bool _gammaCorrection=false, int _nlevels=HOGDescriptor::DEFAULT_NLEVELS, bool _signedGradient=false)

CV_WRAP	HOGDescriptor (const String &filename)

	HOGDescriptor (const HOGDescriptor &d)

virtual	~HOGDescriptor ()
	Default destructor.

CV_WRAP size_t	getDescriptorSize () const
	Returns the number of coefficients required for the classification.

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

CV_WRAP double	getWinSigma () const
	Returns winSigma value

virtual CV_WRAP void	setSVMDetector (InputArray svmdetector)
	Sets coefficients for the linear SVM classifier. [詳解]

virtual bool	read (FileNode &fn)
	Reads HOGDescriptor parameters from a cv::FileNode. [詳解]

virtual void	write (FileStorage &fs, const String &objname) const
	Stores HOGDescriptor parameters in a cv::FileStorage. [詳解]

virtual CV_WRAP bool	load (const String &filename, const String &objname=String())
	loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file. [詳解]

virtual CV_WRAP void	save (const String &filename, const String &objname=String()) const
	saves HOGDescriptor parameters and coefficients for the linear SVM classifier to a file [詳解]

virtual void	copyTo (HOGDescriptor &c) const
	clones the HOGDescriptor [詳解]

virtual CV_WRAP void	compute (InputArray img, CV_OUT std::vector< float > &descriptors, Size winStride=Size(), Size padding=Size(), const std::vector< Point > &locations=std::vector< Point >()) const
	Computes HOG descriptors of given image. [詳解]

virtual CV_WRAP void	detect (InputArray img, CV_OUT std::vector< Point > &foundLocations, CV_OUT std::vector< double > &weights, double hitThreshold=0, Size winStride=Size(), Size padding=Size(), const std::vector< Point > &searchLocations=std::vector< Point >()) const
	Performs object detection without a multi-scale window. [詳解]

virtual void	detect (InputArray img, CV_OUT std::vector< Point > &foundLocations, double hitThreshold=0, Size winStride=Size(), Size padding=Size(), const std::vector< Point > &searchLocations=std::vector< Point >()) const
	Performs object detection without a multi-scale window. [詳解]

virtual CV_WRAP void	detectMultiScale (InputArray img, CV_OUT std::vector< Rect > &foundLocations, CV_OUT std::vector< double > &foundWeights, double hitThreshold=0, Size winStride=Size(), Size padding=Size(), double scale=1.05, double finalThreshold=2.0, bool useMeanshiftGrouping=false) const
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. [詳解]

virtual void	detectMultiScale (InputArray img, CV_OUT std::vector< Rect > &foundLocations, double hitThreshold=0, Size winStride=Size(), Size padding=Size(), double scale=1.05, double finalThreshold=2.0, bool useMeanshiftGrouping=false) const
	Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. [詳解]

virtual CV_WRAP void	computeGradient (InputArray img, InputOutputArray grad, InputOutputArray angleOfs, Size paddingTL=Size(), Size paddingBR=Size()) const
	Computes gradients and quantized gradient orientations. [詳解]

virtual void	detectROI (InputArray img, const std::vector< cv::Point > &locations, CV_OUT std::vector< cv::Point > &foundLocations, CV_OUT std::vector< double > &confidences, double hitThreshold=0, cv::Size winStride=Size(), cv::Size padding=Size()) const
	evaluate specified ROI and return confidence value for each location [詳解]

virtual void	detectMultiScaleROI (InputArray img, CV_OUT std::vector< cv::Rect > &foundLocations, std::vector< DetectionROI > &locations, double hitThreshold=0, int groupThreshold=0) const
	evaluate specified ROI and return confidence value for each location in multiple scales [詳解]

void	groupRectangles (std::vector< cv::Rect > &rectList, std::vector< double > &weights, int groupThreshold, double eps) const
	Groups the object candidate rectangles. [詳解]

静的公開メンバ関数
static CV_WRAP std::vector< float >	getDefaultPeopleDetector ()
	Returns coefficients of the classifier trained for people detection (for 64x128 windows).

static CV_WRAP std::vector< float >	getDaimlerPeopleDetector ()
	Returns coefficients of the classifier trained for people detection (for 48x96 windows).

公開変数類
CV_PROP Size	winSize
	Detection window size. Align to block size and block stride. Default value is Size(64,128).

CV_PROP Size	blockSize
	Block size in pixels. Align to cell size. Default value is Size(16,16).

CV_PROP Size	blockStride
	Block stride. It must be a multiple of cell size. Default value is Size(8,8).

CV_PROP Size	cellSize
	Cell size. Default value is Size(8,8).

CV_PROP int	nbins
	Number of bins used in the calculation of histogram of gradients. Default value is 9.

CV_PROP int	derivAperture
	not documented

CV_PROP double	winSigma
	Gaussian smoothing window parameter.

CV_PROP HOGDescriptor::HistogramNormType	histogramNormType
	histogramNormType

CV_PROP double	L2HysThreshold
	L2-Hys normalization method shrinkage.

CV_PROP bool	gammaCorrection
	Flag to specify whether the gamma correction preprocessing is required or not.

CV_PROP std::vector< float >	svmDetector
	coefficients for the linear SVM classifier.

UMat	oclSvmDetector
	coefficients for the linear SVM classifier used when OpenCL is enabled

float	free_coef
	not documented

CV_PROP int	nlevels
	Maximum number of detection window increases. Default value is 64

CV_PROP bool	signedGradient
	Indicates signed gradient will be used or not

詳解

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

列挙型メンバ詳解

◆ anonymous enum

anonymous enum

列挙値
DEFAULT_NLEVELS	Default nlevels value.

◆ HistogramNormType

enum cv::HOGDescriptor::HistogramNormType

列挙値
L2Hys	Default histogramNormType

構築子と解体子

◆ HOGDescriptor() [1/4]

CV_WRAP cv::HOGDescriptor::HOGDescriptor ( )

inline

Creates the HOG descriptor and detector with default params.

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

◆ HOGDescriptor() [2/4]

CV_WRAP cv::HOGDescriptor::HOGDescriptor	(	Size	_winSize,
		Size	_blockSize,
		Size	_blockStride,
		Size	_cellSize,
		int	_nbins,
		int	_derivAperture = `1`,
		double	_winSigma = `-1`,
		HOGDescriptor::HistogramNormType	_histogramNormType = `HOGDescriptor::L2Hys`,
		double	_L2HysThreshold = `0.2`,
		bool	_gammaCorrection = `false`,
		int	_nlevels = `HOGDescriptor::DEFAULT_NLEVELS`,
		bool	_signedGradient = `false`
	)

inline

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。

引数

_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() [3/4]

CV_WRAP cv::HOGDescriptor::HOGDescriptor ( const String & filename )

inline

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。

引数

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

◆ HOGDescriptor() [4/4]

cv::HOGDescriptor::HOGDescriptor ( const HOGDescriptor & d )

inline

これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。

引数

d	the HOGDescriptor which cloned to create a new one.

関数詳解

◆ compute()

virtual CV_WRAP void cv::HOGDescriptor::compute	(	InputArray	img,
		CV_OUT std::vector< float > &	descriptors,
		Size	winStride = `Size()`,
		Size	padding = `Size()`,
		const std::vector< Point > &	locations = `std::vector< Point >()`
	)		const

virtual

Computes HOG descriptors of given image.

引数

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()

virtual CV_WRAP void cv::HOGDescriptor::computeGradient	(	InputArray	img,
		InputOutputArray	grad,
		InputOutputArray	angleOfs,
		Size	paddingTL = `Size()`,
		Size	paddingBR = `Size()`
	)		const

virtual

Computes gradients and quantized gradient orientations.

引数

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

◆ copyTo()

virtual void cv::HOGDescriptor::copyTo ( HOGDescriptor & c ) const

virtual

clones the HOGDescriptor

引数

c	cloned HOGDescriptor

◆ detect() [1/2]

virtual CV_WRAP void cv::HOGDescriptor::detect	(	InputArray	img,
		CV_OUT std::vector< Point > &	foundLocations,
		CV_OUT std::vector< double > &	weights,
		double	hitThreshold = `0`,
		Size	winStride = `Size()`,
		Size	padding = `Size()`,
		const std::vector< Point > &	searchLocations = `std::vector< Point >()`
	)		const

virtual

Performs object detection without a multi-scale window.

引数

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() [2/2]

virtual void cv::HOGDescriptor::detect	(	InputArray	img,
		CV_OUT std::vector< Point > &	foundLocations,
		double	hitThreshold = `0`,
		Size	winStride = `Size()`,
		Size	padding = `Size()`,
		const std::vector< Point > &	searchLocations = `std::vector< Point >()`
	)		const

virtual

Performs object detection without a multi-scale window.

引数

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.
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 locations to search.

◆ detectMultiScale() [1/2]

virtual CV_WRAP void cv::HOGDescriptor::detectMultiScale	(	InputArray	img,
		CV_OUT std::vector< Rect > &	foundLocations,
		CV_OUT std::vector< double > &	foundWeights,
		double	hitThreshold = `0`,
		Size	winStride = `Size()`,
		Size	padding = `Size()`,
		double	scale = `1.05`,
		double	finalThreshold = `2.0`,
		bool	useMeanshiftGrouping = `false`
	)		const

virtual

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

引数

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.
finalThreshold	Final threshold
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScale() [2/2]

virtual void cv::HOGDescriptor::detectMultiScale	(	InputArray	img,
		CV_OUT std::vector< Rect > &	foundLocations,
		double	hitThreshold = `0`,
		Size	winStride = `Size()`,
		Size	padding = `Size()`,
		double	scale = `1.05`,
		double	finalThreshold = `2.0`,
		bool	useMeanshiftGrouping = `false`
	)		const

virtual

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

引数

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.
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.
finalThreshold	Final threshold
useMeanshiftGrouping	indicates grouping algorithm

◆ detectMultiScaleROI()

virtual void cv::HOGDescriptor::detectMultiScaleROI	(	InputArray	img,
		CV_OUT std::vector< cv::Rect > &	foundLocations,
		std::vector< DetectionROI > &	locations,
		double	hitThreshold = `0`,
		int	groupThreshold = `0`
	)		const

virtual

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

引数

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.
locations	Vector of DetectionROI
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.
groupThreshold	Minimum possible number of rectangles minus 1. The threshold is used in a group of rectangles to retain it.

◆ detectROI()

virtual void cv::HOGDescriptor::detectROI	(	InputArray	img,
		const std::vector< cv::Point > &	locations,
		CV_OUT std::vector< cv::Point > &	foundLocations,
		CV_OUT std::vector< double > &	confidences,
		double	hitThreshold = `0`,
		cv::Size	winStride = `Size()`,
		cv::Size	padding = `Size()`
	)		const

virtual

evaluate specified ROI and return confidence value for each location

引数

img	Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected.
locations	Vector of Point
foundLocations	Vector of Point where each Point is detected object's top-left point.
confidences	confidences
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	winStride
padding	padding

◆ groupRectangles()

void cv::HOGDescriptor::groupRectangles	(	std::vector< cv::Rect > &	rectList,
		std::vector< double > &	weights,
		int	groupThreshold,
		double	eps
	)		const

Groups the object candidate rectangles.

引数

rectList	Input/output vector of rectangles. Output vector includes retained and grouped rectangles. (The Python list is not modified in place.)
weights	Input/output vector of weights of rectangles. Output vector includes weights of retained and grouped rectangles. (The Python list is not modified in place.)
groupThreshold	Minimum possible number of rectangles minus 1. The threshold is used in a group of rectangles to retain it.
eps	Relative difference between sides of the rectangles to merge them into a group.

◆ load()

virtual CV_WRAP bool cv::HOGDescriptor::load	(	const String &	filename,
		const String &	objname = `String()`
	)

virtual

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

引数

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

◆ read()

virtual bool cv::HOGDescriptor::read ( FileNode & fn )

virtual

Reads HOGDescriptor parameters from a cv::FileNode.

引数

fn File node

◆ save()

virtual CV_WRAP void cv::HOGDescriptor::save	(	const String &	filename,
		const String &	objname = `String()`
	)		const

virtual

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

引数

filename	File name
objname	Object name

◆ setSVMDetector()

virtual CV_WRAP void cv::HOGDescriptor::setSVMDetector ( InputArray svmdetector )

virtual

Sets coefficients for the linear SVM classifier.

引数

svmdetector coefficients for the linear SVM classifier.

◆ write()

virtual void cv::HOGDescriptor::write	(	FileStorage &	fs,
		const String &	objname
	)		const

virtual

Stores HOGDescriptor parameters in a cv::FileStorage.

引数

fs	File storage
objname	Object name

この構造体詳解は次のファイルから抽出されました:

objdetect.hpp

公開型

公開メンバ関数

静的公開メンバ関数

公開変数類

詳解

列挙型メンバ詳解

◆ anonymous enum

◆ HistogramNormType

構築子と解体子

◆ HOGDescriptor() [1/4]

◆ HOGDescriptor() [2/4]

◆ HOGDescriptor() [3/4]

◆ HOGDescriptor() [4/4]

関数詳解

◆ compute()

◆ computeGradient()

◆ copyTo()

◆ detect() [1/2]

◆ detect() [2/2]

◆ detectMultiScale() [1/2]

◆ detectMultiScale() [2/2]

◆ detectMultiScaleROI()

◆ detectROI()

◆ groupRectangles()

◆ load()

◆ read()

◆ save()

◆ setSVMDetector()

◆ write()