HOG represents a class for computing the HOG descriptor described in Dalal, N. More...

#include <pcl/people/hog.h>

Public Member Functions
	HOG ()
	Constructor. More...

virtual	~HOG ()
	Destructor. More...

void	gradMag (float I, int h, int w, int d, float M, float *O) const
	Compute gradient magnitude and orientation at each location (uses sse). More...

void	gradHist (float M, float O, int h, int w, int bin_size, int n_orients, bool soft_bin, float *H) const
	Compute n_orients gradient histograms per bin_size x bin_size block of pixels. More...

void	normalization (float H, int h, int w, int bin_size, int n_orients, float clip, float G) const
	Normalize histogram of gradients. More...

void	compute (float I, int h, int w, int n_channels, int bin_size, int n_orients, bool soft_bin, float descriptor)
	Compute HOG descriptor. More...

void	compute (float I, float descriptor) const
	Compute HOG descriptor with default parameters. More...

Protected Attributes
int	h_
	image height (default = 128) More...

int	w_
	image width (default = 64) More...

int	n_channels_
	image number of channels (default = 3) More...

int	bin_size_
	spatial bin size (default = 8) More...

int	n_orients_
	number of orientation bins (default = 9) More...

bool	soft_bin_
	if true, each pixel can contribute to multiple spatial bins (using bilinear interpolation) (default = true) More...

float	clip_
	value at which to clip histogram bins (default = 0.2) More...

Detailed Description

HOG represents a class for computing the HOG descriptor described in Dalal, N.

and Triggs, B., "Histograms of oriented gradients for human detection", CVPR 2005.

Author: Matteo Munaro, Stefano Ghidoni, Stefano Michieletto

Definition at line 54 of file hog.h.

Constructor & Destructor Documentation

◆ HOG()

pcl::people::HOG::HOG ( )

Constructor.

◆ ~HOG()

virtual pcl::people::HOG::~HOG ( )

virtual

Destructor.

Member Function Documentation

◆ compute() [1/2]

void pcl::people::HOG::compute	(	float *	I,
		float *	descriptor
	)		const

Compute HOG descriptor with default parameters.

Parameters

[in]	I	Image as array of float between 0 and 1.
[out]	descriptor	HOG descriptor.

◆ compute() [2/2]

void pcl::people::HOG::compute	(	float *	I,
		int	h,
		int	w,
		int	n_channels,
		int	bin_size,
		int	n_orients,
		bool	soft_bin,
		float *	descriptor
	)

Compute HOG descriptor.

Parameters

[in]	I	Image as array of float between 0 and 1.
[in]	h	Image height.
[in]	w	Image width.
[in]	n_channels	Image number of channels.
[in]	bin_size	Spatial bin size.
[in]	n_orients	Number of orientation bins.
[in]	soft_bin	If true, each pixel can contribute to multiple spatial bins (using bilinear interpolation).
[out]	descriptor	HOG descriptor.

Referenced by pcl::people::PersonClassifier< PointT >::evaluate().

◆ gradHist()

void pcl::people::HOG::gradHist	(	float *	M,
		float *	O,
		int	h,
		int	w,
		int	bin_size,
		int	n_orients,
		bool	soft_bin,
		float *	H
	)		const

Compute n_orients gradient histograms per bin_size x bin_size block of pixels.

Parameters

[in]	M	Gradient magnitude for each image point.
[in]	O	Gradient orientation for each image point.
[in]	h	Image height.
[in]	w	Image width.
[in]	bin_size	Spatial bin size.
[in]	n_orients	Number of orientation bins.
[in]	soft_bin	If true, each pixel can contribute to multiple spatial bins (using bilinear interpolation).
[out]	H	Gradient histograms.

◆ gradMag()

void pcl::people::HOG::gradMag	(	float *	I,
		int	h,
		int	w,
		int	d,
		float *	M,
		float *	O
	)		const

Compute gradient magnitude and orientation at each location (uses sse).

Parameters

[in]	I	Image as array of float.
[in]	h	Image height.
[in]	w	Image width.
[in]	d	Image number of channels.
[out]	M	Gradient magnitude for each image point.
[out]	O	Gradient orientation for each image point.

◆ normalization()

void pcl::people::HOG::normalization	(	float *	H,
		int	h,
		int	w,
		int	bin_size,
		int	n_orients,
		float	clip,
		float *	G
	)		const

Normalize histogram of gradients.

Parameters

[in]	H	Gradient histograms.
[in]	h	Image height.
[in]	w	Image width.
[in]	bin_size	Spatial bin size.
[in]	n_orients	Number of orientation bins.
[in]	clip	Value at which to clip histogram bins.
[out]	G	Normalized gradient histograms.

Member Data Documentation

◆ bin_size_

int pcl::people::HOG::bin_size_

protected

spatial bin size (default = 8)

Definition at line 174 of file hog.h.

◆ clip_

float pcl::people::HOG::clip_

protected

value at which to clip histogram bins (default = 0.2)

Definition at line 183 of file hog.h.

◆ h_

int pcl::people::HOG::h_

protected

image height (default = 128)

Definition at line 165 of file hog.h.

◆ n_channels_

int pcl::people::HOG::n_channels_

protected

image number of channels (default = 3)

Definition at line 171 of file hog.h.

◆ n_orients_

int pcl::people::HOG::n_orients_

protected

number of orientation bins (default = 9)

Definition at line 177 of file hog.h.

◆ soft_bin_

bool pcl::people::HOG::soft_bin_

protected

if true, each pixel can contribute to multiple spatial bins (using bilinear interpolation) (default = true)

Definition at line 180 of file hog.h.

◆ w_

int pcl::people::HOG::w_

protected

image width (default = 64)

Definition at line 168 of file hog.h.

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

pcl/people/hog.h

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ HOG()

◆ ~HOG()

Member Function Documentation

◆ compute() [1/2]

◆ compute() [2/2]

◆ gradHist()

◆ gradMag()

◆ normalization()

Member Data Documentation

◆ bin_size_

◆ clip_

◆ h_

◆ n_channels_

◆ n_orients_

◆ soft_bin_

◆ w_