Modality based on max-RGB gradients. More...

#include <color_gradient_modality.h>

Inheritance diagram for pcl::ColorGradientModality< PointInT >:

Classes
struct	Candidate
	Candidate for a feature (used in feature extraction methods). More...
Public Types
enum	FeatureSelectionMethod { MASK_BORDER_HIGH_GRADIENTS, MASK_BORDER_EQUALLY, DISTANCE_MAGNITUDE_SCORE }
	Different methods for feature selection/extraction. More...
typedef pcl::PointCloud< PointInT >	PointCloudIn
Public Member Functions
	ColorGradientModality ()
	Constructor.
void	extractAllFeatures (const MaskMap &mask, size_t nr_features, size_t modalityIndex, std::vector< QuantizedMultiModFeature > &features) const
	Extracts all possible features from the modality within the specified mask.
void	extractFeatures (const MaskMap &mask, size_t nr_features, size_t modalityIndex, std::vector< QuantizedMultiModFeature > &features) const
	Extracts features from this modality within the specified mask.
pcl::PointCloud < pcl::GradientXY > &	getMaxColorGradients ()
	Returns a point cloud containing the max-RGB gradients.
QuantizedMap &	getQuantizedMap ()
	Returns a reference to the internally computed quantized map.
QuantizedMap &	getSpreadedQuantizedMap ()
	Returns a reference to the internally computed spreaded quantized map.
virtual void	processInputData ()
	Processes the input data (smoothing, computing gradients, quantizing, filtering, spreading).
virtual void	processInputDataFromFiltered ()
	Processes the input data assuming that everything up to filtering is already done/available (so only spreading is performed).
void	setFeatureSelectionMethod (const FeatureSelectionMethod method)
	Sets the feature selection method.
void	setGradientMagnitudeThreshold (const float threshold)
	Sets the threshold for the gradient magnitude which is used when quantizing the data. Gradients with a smaller magnitude are ignored.
void	setGradientMagnitudeThresholdForFeatureExtraction (const float threshold)
	Sets the threshold for the gradient magnitude which is used for feature extraction. Gradients with a smaller magnitude are ignored.
virtual void	setInputCloud (const typename PointCloudIn::ConstPtr &cloud)
	Provide a pointer to the input dataset (overwrites the PCLBase::setInputCloud method)
void	setSpreadingSize (const size_t spreading_size)
	Sets the spreading size for spreading the quantized data.
void	setVariableFeatureNr (const bool enabled)
	Sets whether variable feature numbers for feature extraction is enabled.
virtual	~ColorGradientModality ()
	Destructor.
Protected Member Functions
void	computeGaussianKernel (const size_t kernel_size, const float sigma, std::vector< float > &kernel_values)
	Computes the Gaussian kernel used for smoothing.
void	computeMaxColorGradients (const typename pcl::PointCloud< pcl::RGB >::ConstPtr &cloud)
	Computes the max-RGB gradients for the specified cloud.
void	computeMaxColorGradientsSobel (const typename pcl::PointCloud< pcl::RGB >::ConstPtr &cloud)
	Computes the max-RGB gradients for the specified cloud using sobel.
void	filterQuantizedColorGradients ()
	Filters the quantized gradients.
void	quantizeColorGradients ()
	Quantizes the color gradients.
Static Protected Member Functions
static void	erode (const pcl::MaskMap &mask_in, pcl::MaskMap &mask_out)
	Erodes a mask.
Private Attributes
pcl::PointCloud< pcl::GradientXY >	color_gradients_
	The point cloud which holds the max-RGB gradients.
FeatureSelectionMethod	feature_selection_method_
	Defines which feature selection method is used.
pcl::QuantizedMap	filtered_quantized_color_gradients_
	The map which holds the filtered quantized data.
float	gradient_magnitude_threshold_
	The threshold applied on the gradient magnitudes (for quantization).
float	gradient_magnitude_threshold_feature_extraction_
	The threshold applied on the gradient magnitudes for feature extraction.
pcl::QuantizedMap	quantized_color_gradients_
	The map which holds the quantized max-RGB gradients.
pcl::PointCloud< pcl::RGB >::Ptr	smoothed_input_
	Stores a smoothed verion of the input cloud.
pcl::QuantizedMap	spreaded_filtered_quantized_color_gradients_
	The map which holds the spreaded quantized data.
size_t	spreading_size_
	The spreading size.
bool	variable_feature_nr_
	Determines whether variable numbers of features are extracted or not.

Detailed Description

template<typename PointInT>
class pcl::ColorGradientModality< PointInT >

Modality based on max-RGB gradients.

Author:: Stefan Holzer

Definition at line 58 of file color_gradient_modality.h.

Member Typedef Documentation

template<typename PointInT>

typedef pcl::PointCloud<PointInT> pcl::ColorGradientModality< PointInT >::PointCloudIn

Definition at line 85 of file color_gradient_modality.h.

Member Enumeration Documentation

template<typename PointInT>

enum pcl::ColorGradientModality::FeatureSelectionMethod

Different methods for feature selection/extraction.

Enumerator:

MASK_BORDER_HIGH_GRADIENTS
MASK_BORDER_EQUALLY
DISTANCE_MAGNITUDE_SCORE

Definition at line 88 of file color_gradient_modality.h.

Constructor & Destructor Documentation

template<typename PointInT >

pcl::ColorGradientModality< PointInT >::ColorGradientModality ( )

Constructor.

Definition at line 277 of file color_gradient_modality.h.

template<typename PointInT >

pcl::ColorGradientModality< PointInT >::~ColorGradientModality ( ) [virtual]

Destructor.

Definition at line 294 of file color_gradient_modality.h.

Member Function Documentation

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::computeGaussianKernel	(	const size_t	kernel_size,
		const float	sigma,
		std::vector< float > &	kernel_values
	)		`[protected]`

Computes the Gaussian kernel used for smoothing.

Parameters:

[in]	kernel_size	the size of the Gaussian kernel.
[in]	sigma	the sigma.
[out]	kernel_values	the destination for the values of the kernel.

Definition at line 301 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::computeMaxColorGradients ( const typename pcl::PointCloud< pcl::RGB >::ConstPtr & cloud ) [protected]

Computes the max-RGB gradients for the specified cloud.

Parameters:

[in] cloud the cloud for which the gradients are computed.

Definition at line 755 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::computeMaxColorGradientsSobel ( const typename pcl::PointCloud< pcl::RGB >::ConstPtr & cloud ) [protected]

Computes the max-RGB gradients for the specified cloud using sobel.

Parameters:

[in] cloud the cloud for which the gradients are computed.

Definition at line 842 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::erode	(	const pcl::MaskMap &	mask_in,
		pcl::MaskMap &	mask_out
	)		`[static, protected]`

Erodes a mask.

Parameters:

[in]	mask_in	the mask which will be eroded.
[out]	mask_out	the destination for the eroded mask.

Definition at line 1097 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::extractAllFeatures	(	const MaskMap &	mask,
		size_t	nr_features,
		size_t	modalityIndex,
		std::vector< QuantizedMultiModFeature > &	features
	)		const `[virtual]`

Extracts all possible features from the modality within the specified mask.

Parameters:

[in]	mask	defines the areas where features are searched in.
[in]	nr_features	IGNORED (TODO: remove this parameter).
[in]	modality_index	the index which is stored in the extracted features.
[out]	features	the destination for the extracted features.

Implements pcl::QuantizableModality.

Definition at line 705 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::extractFeatures	(	const MaskMap &	mask,
		size_t	nr_features,
		size_t	modalityIndex,
		std::vector< QuantizedMultiModFeature > &	features
	)		const `[virtual]`

Extracts features from this modality within the specified mask.

Parameters:

[in]	mask	defines the areas where features are searched in.
[in]	nr_features	defines the number of features to be extracted (might be less if not sufficient information is present in the modality).
[in]	modality_index	the index which is stored in the extracted features.
[out]	features	the destination for the extracted features.

Implements pcl::QuantizableModality.

Definition at line 418 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::filterQuantizedColorGradients ( ) [protected]

Filters the quantized gradients.

Definition at line 1027 of file color_gradient_modality.h.

template<typename PointInT>

pcl::PointCloud<pcl::GradientXY>& pcl::ColorGradientModality< PointInT >::getMaxColorGradients ( ) [inline]

Returns a point cloud containing the max-RGB gradients.

Definition at line 161 of file color_gradient_modality.h.

template<typename PointInT>

QuantizedMap& pcl::ColorGradientModality< PointInT >::getQuantizedMap ( ) [inline, virtual]

Returns a reference to the internally computed quantized map.

Implements pcl::QuantizableModality.

Definition at line 147 of file color_gradient_modality.h.

template<typename PointInT>

QuantizedMap& pcl::ColorGradientModality< PointInT >::getSpreadedQuantizedMap ( ) [inline, virtual]

Returns a reference to the internally computed spreaded quantized map.

Implements pcl::QuantizableModality.

Definition at line 154 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::processInputData ( ) [virtual]

Processes the input data (smoothing, computing gradients, quantizing, filtering, spreading).

Definition at line 348 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::processInputDataFromFiltered ( ) [virtual]

Processes the input data assuming that everything up to filtering is already done/available (so only spreading is performed).

Definition at line 406 of file color_gradient_modality.h.

template<typename PointInT >

void pcl::ColorGradientModality< PointInT >::quantizeColorGradients ( ) [protected]

Quantizes the color gradients.

Definition at line 964 of file color_gradient_modality.h.

template<typename PointInT>

void pcl::ColorGradientModality< PointInT >::setFeatureSelectionMethod ( const FeatureSelectionMethod method ) [inline]

Sets the feature selection method.

Parameters:

[in] method the feature selection method.

Definition at line 124 of file color_gradient_modality.h.

template<typename PointInT>

void pcl::ColorGradientModality< PointInT >::setGradientMagnitudeThreshold ( const float threshold ) [inline]

Sets the threshold for the gradient magnitude which is used when quantizing the data. Gradients with a smaller magnitude are ignored.

Parameters:

[in] threshold the new gradient magnitude threshold.

Definition at line 105 of file color_gradient_modality.h.

template<typename PointInT>

void pcl::ColorGradientModality< PointInT >::setGradientMagnitudeThresholdForFeatureExtraction ( const float threshold ) [inline]

Sets the threshold for the gradient magnitude which is used for feature extraction. Gradients with a smaller magnitude are ignored.

Parameters:

[in] threshold the new gradient magnitude threshold.

Definition at line 115 of file color_gradient_modality.h.

template<typename PointInT>

virtual void pcl::ColorGradientModality< PointInT >::setInputCloud ( const typename PointCloudIn::ConstPtr & cloud ) [inline, virtual]

Provide a pointer to the input dataset (overwrites the PCLBase::setInputCloud method)

Parameters:

cloud the const boost shared pointer to a PointCloud message

Definition at line 191 of file color_gradient_modality.h.

template<typename PointInT>

void pcl::ColorGradientModality< PointInT >::setSpreadingSize ( const size_t spreading_size ) [inline]

Sets the spreading size for spreading the quantized data.

Definition at line 131 of file color_gradient_modality.h.

template<typename PointInT>

void pcl::ColorGradientModality< PointInT >::setVariableFeatureNr ( const bool enabled ) [inline]

Sets whether variable feature numbers for feature extraction is enabled.

Parameters:

[in] enabled enables/disables variable feature numbers for feature extraction.

Definition at line 140 of file color_gradient_modality.h.

Member Data Documentation

template<typename PointInT>

pcl::PointCloud<pcl::GradientXY> pcl::ColorGradientModality< PointInT >::color_gradients_ [private]

The point cloud which holds the max-RGB gradients.

Definition at line 258 of file color_gradient_modality.h.

template<typename PointInT>

FeatureSelectionMethod pcl::ColorGradientModality< PointInT >::feature_selection_method_ [private]

Defines which feature selection method is used.

Definition at line 250 of file color_gradient_modality.h.

template<typename PointInT>

pcl::QuantizedMap pcl::ColorGradientModality< PointInT >::filtered_quantized_color_gradients_ [private]

The map which holds the filtered quantized data.

Definition at line 266 of file color_gradient_modality.h.

template<typename PointInT>

float pcl::ColorGradientModality< PointInT >::gradient_magnitude_threshold_ [private]

The threshold applied on the gradient magnitudes (for quantization).

Definition at line 253 of file color_gradient_modality.h.

template<typename PointInT>

float pcl::ColorGradientModality< PointInT >::gradient_magnitude_threshold_feature_extraction_ [private]

The threshold applied on the gradient magnitudes for feature extraction.

Definition at line 255 of file color_gradient_modality.h.

template<typename PointInT>

pcl::QuantizedMap pcl::ColorGradientModality< PointInT >::quantized_color_gradients_ [private]

The map which holds the quantized max-RGB gradients.

Definition at line 264 of file color_gradient_modality.h.

template<typename PointInT>

pcl::PointCloud<pcl::RGB>::Ptr pcl::ColorGradientModality< PointInT >::smoothed_input_ [private]

Stores a smoothed verion of the input cloud.

Definition at line 247 of file color_gradient_modality.h.

template<typename PointInT>

pcl::QuantizedMap pcl::ColorGradientModality< PointInT >::spreaded_filtered_quantized_color_gradients_ [private]

The map which holds the spreaded quantized data.

Definition at line 268 of file color_gradient_modality.h.

template<typename PointInT>

size_t pcl::ColorGradientModality< PointInT >::spreading_size_ [private]

The spreading size.

Definition at line 261 of file color_gradient_modality.h.

template<typename PointInT>

bool pcl::ColorGradientModality< PointInT >::variable_feature_nr_ [private]

Determines whether variable numbers of features are extracted or not.

Definition at line 244 of file color_gradient_modality.h.

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

color_gradient_modality.h

Classes

Public Types

Public Member Functions

Protected Member Functions

Static Protected Member Functions

Private Attributes

Detailed Description

template<typename PointInT> class pcl::ColorGradientModality< PointInT >

Member Typedef Documentation

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation

template<typename PointInT>
class pcl::ColorGradientModality< PointInT >