pcl::segmentation::grabcut Namespace Reference

Classes
class	BoykovKolmogorov
	boost implementation of Boykov and Kolmogorov's maxflow algorithm doesn't support negative flows which makes it inappropriate for this conext. More...
struct	Color
	Structure to save RGB colors into floats. More...
struct	Gaussian
	Gaussian structure. More...
class	GaussianFitter
	Helper class that fits a single Gaussian to color samples. More...
class	GMM

Typedefs
typedef pcl::PointCloud< Color >	Image
	An Image is a point cloud of Color. More...

Enumerations
enum	TrimapValue { TrimapUnknown = -1, TrimapForeground, TrimapBackground }
	User supplied Trimap values. More...
enum	SegmentationValue { SegmentationForeground = 0, SegmentationBackground }
	Grabcut derived hard segementation values. More...

Functions
float	colorDistance (const Color &c1, const Color &c2)
	Compute squared distance between two colors. More...
PCL_EXPORTS void	buildGMMs (const Image &image, const std::vector< int > &indices, const std::vector< SegmentationValue > &hardSegmentation, std::vector< std::size_t > &components, GMM &background_GMM, GMM &foreground_GMM)
	Build the initial GMMs using the Orchard and Bouman color clustering algorithm. More...
PCL_EXPORTS void	learnGMMs (const Image &image, const std::vector< int > &indices, const std::vector< SegmentationValue > &hard_segmentation, std::vector< std::size_t > &components, GMM &background_GMM, GMM &foreground_GMM)
	Iteratively learn GMMs using GrabCut updating algorithm. More...

Typedef Documentation

typedef pcl::PointCloud<Color> pcl::segmentation::grabcut::Image

An Image is a point cloud of Color.

Definition at line 188 of file grabcut_segmentation.h.

Enumeration Type Documentation

enum pcl::segmentation::grabcut::SegmentationValue

Grabcut derived hard segementation values.

Enumerator
SegmentationForeground
SegmentationBackground

Definition at line 199 of file grabcut_segmentation.h.

enum pcl::segmentation::grabcut::TrimapValue

User supplied Trimap values.

Enumerator
TrimapUnknown
TrimapForeground
TrimapBackground

Definition at line 197 of file grabcut_segmentation.h.

Function Documentation

PCL_EXPORTS void pcl::segmentation::grabcut::buildGMMs	(	const Image &	image,
		const std::vector< int > &	indices,
		const std::vector< SegmentationValue > &	hardSegmentation,
		std::vector< std::size_t > &	components,
		GMM &	background_GMM,
		GMM &	foreground_GMM
	)

Build the initial GMMs using the Orchard and Bouman color clustering algorithm.

Referenced by pcl::GrabCut< PointT >::fitGMMs(), and pcl::segmentation::grabcut::GaussianFitter::setEpsilon().

float pcl::segmentation::grabcut::colorDistance	(	const Color &	c1,
		const Color &	c2
	)

Compute squared distance between two colors.

Parameters

[in]	c1	first color
[in]	c2	second color

Returns

the squared distance measure in RGB space

PCL_EXPORTS void pcl::segmentation::grabcut::learnGMMs	(	const Image &	image,
		const std::vector< int > &	indices,
		const std::vector< SegmentationValue > &	hard_segmentation,
		std::vector< std::size_t > &	components,
		GMM &	background_GMM,
		GMM &	foreground_GMM
	)

Iteratively learn GMMs using GrabCut updating algorithm.

Referenced by pcl::GrabCut< PointT >::refineOnce(), and pcl::segmentation::grabcut::GaussianFitter::setEpsilon().