cv::cuda::HOG Class Reference

The class implements Histogram of Oriented Gradients ([42]) object detector. More...

#include <opencv2/cudaobjdetect.hpp>

Inheritance diagram for cv::cuda::HOG:

Public Types
enum	{   DESCR_FORMAT_ROW_BY_ROW,   DESCR_FORMAT_COL_BY_COL }

Public Member Functions
virtual void	compute (InputArray img, OutputArray descriptors, Stream &stream=Stream::Null())=0
	Returns block descriptors computed for the whole image. More...
virtual void	detect (InputArray img, std::vector< Point > &found_locations, std::vector< double > *confidences=NULL)=0
	Performs object detection without a multi-scale window. More...
virtual void	detectMultiScale (InputArray img, std::vector< Rect > &found_locations, std::vector< double > *confidences=NULL)=0
	Performs object detection with a multi-scale window. More...
virtual size_t	getBlockHistogramSize () const =0
	Returns the block histogram size. More...
virtual Mat	getDefaultPeopleDetector () const =0
	Returns coefficients of the classifier trained for people detection. More...
virtual int	getDescriptorFormat () const =0
virtual size_t	getDescriptorSize () const =0
	Returns the number of coefficients required for the classification. More...
virtual bool	getGammaCorrection () const =0
virtual int	getGroupThreshold () const =0
virtual double	getHitThreshold () const =0
virtual double	getL2HysThreshold () const =0
virtual int	getNumLevels () const =0
virtual double	getScaleFactor () const =0
virtual double	getWinSigma () const =0
virtual Size	getWinStride () const =0
virtual void	setDescriptorFormat (int descr_format)=0
virtual void	setGammaCorrection (bool gamma_correction)=0
	Flag to specify whether the gamma correction preprocessing is required or not. More...
virtual void	setGroupThreshold (int group_threshold)=0
virtual void	setHitThreshold (double hit_threshold)=0
virtual void	setL2HysThreshold (double threshold_L2hys)=0
	L2-Hys normalization method shrinkage. More...
virtual void	setNumLevels (int nlevels)=0
	Maximum number of detection window increases. More...
virtual void	setScaleFactor (double scale0)=0
	Coefficient of the detection window increase. More...
virtual void	setSVMDetector (InputArray detector)=0
	Sets coefficients for the linear SVM classifier. More...
virtual void	setWinSigma (double win_sigma)=0
	Gaussian smoothing window parameter. More...
virtual void	setWinStride (Size win_stride)=0
	Window stride. It must be a multiple of block stride. More...
Public Member Functions inherited from cv::Algorithm
	Algorithm ()
virtual	~Algorithm ()
virtual void	clear ()
	Clears the algorithm state. More...
virtual bool	empty () const
	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...
virtual String	getDefaultName () const
virtual void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage. More...
virtual void	save (const String &filename) const
virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage. More...
void	write (const Ptr< FileStorage > &fs, const String &name=String()) const
	simplified API for language bindings This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...

Static Public Member Functions
static Ptr< HOG >	create (Size win_size=Size(64, 128), Size block_size=Size(16, 16), Size block_stride=Size(8, 8), Size cell_size=Size(8, 8), int nbins=9)
	Creates the HOG descriptor and detector. More...
Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file. More...
template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String. More...
template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node. More...

Additional Inherited Members
Protected Member Functions inherited from cv::Algorithm
void	writeFormat (FileStorage &fs) const

Detailed Description

The class implements Histogram of Oriented Gradients ([42]) object detector.

Note

• An example applying the HOG descriptor for people detection can be found at opencv_source_code/samples/cpp/peopledetect.cpp
• A CUDA example applying the HOG descriptor for people detection can be found at opencv_source_code/samples/gpu/hog.cpp
• (Python) An example applying the HOG descriptor for people detection can be found at opencv_source_code/samples/python/peopledetect.py

Member Enumeration Documentation

anonymous enum

anonymous enum

Enumerator
DESCR_FORMAT_ROW_BY_ROW
DESCR_FORMAT_COL_BY_COL

Member Function Documentation

compute()

virtual void cv::cuda::HOG::compute ( InputArray  img, OutputArray  descriptors, Stream &  stream = Stream::Null()  )

pure virtual

Returns block descriptors computed for the whole image.

Parameters

img	Source image. See cuda::HOGDescriptor::detect for type limitations.
descriptors	2D array of descriptors.
stream	CUDA stream.

create()

static Ptr<HOG> cv::cuda::HOG::create ( Size  win_size = Size(64, 128), Size  block_size = Size(16, 16), Size  block_stride = Size(8, 8), Size  cell_size = Size(8, 8), int  nbins = 9  )

static

Creates the HOG descriptor and detector.

Parameters

win_size	Detection window size. Align to block size and block stride.
block_size	Block size in pixels. Align to cell size. Only (16,16) is supported for now.
block_stride	Block stride. It must be a multiple of cell size.
cell_size	Cell size. Only (8, 8) is supported for now.
nbins	Number of bins. Only 9 bins per cell are supported for now.

detect()

virtual void cv::cuda::HOG::detect ( InputArray  img, std::vector< Point > &  found_locations, std::vector< double > *  confidences = NULL  )

pure virtual

Performs object detection without a multi-scale window.

Parameters

img	Source image. CV_8UC1 and CV_8UC4 types are supported for now.
found_locations	Left-top corner points of detected objects boundaries.
confidences	Optional output array for confidences.

detectMultiScale()

virtual void cv::cuda::HOG::detectMultiScale ( InputArray  img, std::vector< Rect > &  found_locations, std::vector< double > *  confidences = NULL  )

pure virtual

Performs object detection with a multi-scale window.

Parameters

img	Source image. See cuda::HOGDescriptor::detect for type limitations.
found_locations	Detected objects boundaries.
confidences	Optional output array for confidences.

getBlockHistogramSize()

virtual size_t cv::cuda::HOG::getBlockHistogramSize ( ) const

pure virtual

Returns the block histogram size.

getDefaultPeopleDetector()

virtual Mat cv::cuda::HOG::getDefaultPeopleDetector ( ) const

pure virtual

Returns coefficients of the classifier trained for people detection.

getDescriptorFormat()

virtual int cv::cuda::HOG::getDescriptorFormat ( ) const

pure virtual

getDescriptorSize()

virtual size_t cv::cuda::HOG::getDescriptorSize ( ) const

pure virtual

Returns the number of coefficients required for the classification.

getGammaCorrection()

virtual bool cv::cuda::HOG::getGammaCorrection ( ) const

pure virtual

getGroupThreshold()

virtual int cv::cuda::HOG::getGroupThreshold ( ) const

pure virtual

getHitThreshold()

virtual double cv::cuda::HOG::getHitThreshold ( ) const

pure virtual

getL2HysThreshold()

virtual double cv::cuda::HOG::getL2HysThreshold ( ) const

pure virtual

getNumLevels()

virtual int cv::cuda::HOG::getNumLevels ( ) const

pure virtual

getScaleFactor()

virtual double cv::cuda::HOG::getScaleFactor ( ) const

pure virtual

getWinSigma()

virtual double cv::cuda::HOG::getWinSigma ( ) const

pure virtual

getWinStride()

virtual Size cv::cuda::HOG::getWinStride ( ) const

pure virtual

setDescriptorFormat()

virtual void cv::cuda::HOG::setDescriptorFormat ( int  descr_format )

pure virtual

Descriptor storage format:

• DESCR_FORMAT_ROW_BY_ROW - Row-major order.
• DESCR_FORMAT_COL_BY_COL - Column-major order.

setGammaCorrection()

virtual void cv::cuda::HOG::setGammaCorrection ( bool  gamma_correction )

pure virtual

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

setGroupThreshold()

virtual void cv::cuda::HOG::setGroupThreshold ( int  group_threshold )

pure virtual

Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping. See groupRectangles.

setHitThreshold()

virtual void cv::cuda::HOG::setHitThreshold ( double  hit_threshold )

pure virtual

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.

setL2HysThreshold()

virtual void cv::cuda::HOG::setL2HysThreshold ( double  threshold_L2hys )

pure virtual

L2-Hys normalization method shrinkage.

setNumLevels()

virtual void cv::cuda::HOG::setNumLevels ( int  nlevels )

pure virtual

Maximum number of detection window increases.

setScaleFactor()

virtual void cv::cuda::HOG::setScaleFactor ( double  scale0 )

pure virtual

Coefficient of the detection window increase.

setSVMDetector()

virtual void cv::cuda::HOG::setSVMDetector ( InputArray  detector )

pure virtual

Sets coefficients for the linear SVM classifier.

setWinSigma()

virtual void cv::cuda::HOG::setWinSigma ( double  win_sigma )

pure virtual

Gaussian smoothing window parameter.

setWinStride()

virtual void cv::cuda::HOG::setWinStride ( Size  win_stride )

pure virtual

Window stride. It must be a multiple of block stride.

---

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

• opencv2/cudaobjdetect.hpp