cv::RgbdNormals Class Reference

#include <opencv2/3d/depth.hpp>

Collaboration diagram for cv::RgbdNormals:

Public Types
enum	RgbdNormalsMethod {   RGBD_NORMALS_METHOD_FALS = 0 ,   RGBD_NORMALS_METHOD_LINEMOD = 1 ,   RGBD_NORMALS_METHOD_SRI = 2 ,   RGBD_NORMALS_METHOD_CROSS_PRODUCT = 3 }

Public Member Functions
	RgbdNormals ()
virtual	~RgbdNormals ()
virtual void	apply (InputArray points, OutputArray normals) const =0
virtual void	cache () const =0
virtual int	getCols () const =0
virtual int	getDepth () const =0
virtual void	getK (OutputArray val) const =0
virtual RgbdNormals::RgbdNormalsMethod	getMethod () const =0
virtual int	getRows () const =0
virtual int	getWindowSize () const =0
virtual void	setCols (int val)=0
virtual void	setK (InputArray val)=0
virtual void	setRows (int val)=0
virtual void	setWindowSize (int val)=0

Static Public Member Functions
static Ptr< RgbdNormals >	create (int rows=0, int cols=0, int depth=0, InputArray K=noArray(), int window_size=5, float diff_threshold=50.f, RgbdNormals::RgbdNormalsMethod method=RgbdNormals::RgbdNormalsMethod::RGBD_NORMALS_METHOD_FALS)

Detailed Description

Object that can compute the normals in an image. It is an object as it can cache data for speed efficiency The implemented methods are either:

• FALS (the fastest) and SRI from Fast and Accurate Computation of Surface Normals from Range Images by H. Badino, D. Huber, Y. Park and T. Kanade
• the normals with bilateral filtering on a depth image from Gradient Response Maps for Real-Time Detection of Texture-Less Objects by S. Hinterstoisser, C. Cagniart, S. Ilic, P. Sturm, N. Navab, P. Fua, and V. Lepetit

Member Enumeration Documentation

RgbdNormalsMethod

enum cv::RgbdNormals::RgbdNormalsMethod

Enumerator
RGBD_NORMALS_METHOD_FALS
RGBD_NORMALS_METHOD_LINEMOD
RGBD_NORMALS_METHOD_SRI
RGBD_NORMALS_METHOD_CROSS_PRODUCT

Constructor & Destructor Documentation

RgbdNormals()

cv::RgbdNormals::RgbdNormals ( )

inline

~RgbdNormals()

virtual cv::RgbdNormals::~RgbdNormals ( )

inlinevirtual

Member Function Documentation

apply()

virtual void cv::RgbdNormals::apply ( InputArray  points, OutputArray  normals  ) const

pure virtual

Python:
	cv.RgbdNormals.apply(	points[, normals]	) ->	normals

Given a set of 3d points in a depth image, compute the normals at each point.

Parameters

points	a rows x cols x 3 matrix of CV_32F/CV64F or a rows x cols x 1 CV_U16S
normals	a rows x cols x 3 matrix

cache()

virtual void cv::RgbdNormals::cache ( ) const

pure virtual

Python:
	cv.RgbdNormals.cache(		) ->	None

Prepares cached data required for calculation If not called by user, called automatically at first calculation

create()

static Ptr< RgbdNormals > cv::RgbdNormals::create ( int  rows = 0, int  cols = 0, int  depth = 0, InputArray  K = noArray(), int  window_size = 5, float  diff_threshold = 50.f, RgbdNormals::RgbdNormalsMethod  method = RgbdNormals::RgbdNormalsMethod::RGBD_NORMALS_METHOD_FALS  )

static

Python:
	cv.RgbdNormals.create(	[, rows[, cols[, depth[, K[, window_size[, diff_threshold[, method]]]]]]]	) ->	retval
	cv.RgbdNormals_create(	[, rows[, cols[, depth[, K[, window_size[, diff_threshold[, method]]]]]]]	) ->	retval

Creates new RgbdNormals object

Parameters

rows	the number of rows of the depth image normals will be computed on
cols	the number of cols of the depth image normals will be computed on
depth	the depth of the normals (only CV_32F or CV_64F)
K	the calibration matrix to use
window_size	the window size to compute the normals: can only be 1,3,5 or 7
diff_threshold	threshold in depth difference, used in LINEMOD algirithm
method	one of the methods to use: RGBD_NORMALS_METHOD_SRI, RGBD_NORMALS_METHOD_FALS

Here is the call graph for this function:

getCols()

virtual int cv::RgbdNormals::getCols ( ) const

pure virtual

Python:
	cv.RgbdNormals.getCols(		) ->	retval

getDepth()

virtual int cv::RgbdNormals::getDepth ( ) const

pure virtual

Python:
	cv.RgbdNormals.getDepth(		) ->	retval

getK()

virtual void cv::RgbdNormals::getK ( OutputArray  val ) const

pure virtual

Python:
	cv.RgbdNormals.getK(	[, val]	) ->	val

getMethod()

virtual RgbdNormals::RgbdNormalsMethod cv::RgbdNormals::getMethod ( ) const

pure virtual

Python:
	cv.RgbdNormals.getMethod(		) ->	retval

getRows()

virtual int cv::RgbdNormals::getRows ( ) const

pure virtual

Python:
	cv.RgbdNormals.getRows(		) ->	retval

getWindowSize()

virtual int cv::RgbdNormals::getWindowSize ( ) const

pure virtual

Python:
	cv.RgbdNormals.getWindowSize(		) ->	retval

setCols()

virtual void cv::RgbdNormals::setCols ( int  val )

pure virtual

Python:
	cv.RgbdNormals.setCols(	val	) ->	None

setK()

virtual void cv::RgbdNormals::setK ( InputArray  val )

pure virtual

Python:
	cv.RgbdNormals.setK(	val	) ->	None

setRows()

virtual void cv::RgbdNormals::setRows ( int  val )

pure virtual

Python:
	cv.RgbdNormals.setRows(	val	) ->	None

setWindowSize()

virtual void cv::RgbdNormals::setWindowSize ( int  val )

pure virtual

Python:
	cv.RgbdNormals.setWindowSize(	val	) ->	None

---

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

• opencv2/3d/depth.hpp