#include <bgsub_state.h>

Inheritance diagram for bgsub_state< observation_type >:

Public Member Functions
	bgsub_state (const options &opts, const calibration &_calib, const bool _for_show=true)
double	predict (const observation_type &observation, const double variance_scale=1.0)
bgsub_state &	operator= (bgsub_state &new_state)
bool	load (const std::string filename)
bool	load (std::ifstream &file)

Detailed Description

template<class observation_type>
class bgsub_state< observation_type >

An implementation of the projected prior constrained by an observed silhouete. If you use this class we recommend citing

 @inproceedings{hauberg:emmcvpr11,
  author    = {S{\o}ren Hauberg and Kim Steenstrup Pedersen},
  booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition},
  editor    = {Yuri Boykov and others},
  pages     = {},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  title     = {{Data-Driven Importance Distributions for Articulated Tracking}},
  year      = {2011}
 }

Constructor & Destructor Documentation

template<class observation_type >

bgsub_state< observation_type >::bgsub_state	(	const options &	opts,
		const calibration &	_calib,
		const bool	_for_show = `true`
	)			`[inline]`

Member Function Documentation

template<class observation_type >

bool bgsub_state< observation_type >::load ( const std::string filename ) [inline]

Load pose parameters from a file.

Parameters:

[in] filename The name of the file containing the pose paramters.

Returns:: TRUE on succes.

Reimplemented from skeleton_state< observation_type >.

template<class observation_type >

bool bgsub_state< observation_type >::load ( std::ifstream & file ) [inline]

Load pose parameters from a stream. This is useful for batch loads.

Parameters:

[in] file A stream representing the open file.

Returns:: TRUE on succes.

Reimplemented from skeleton_state< observation_type >.

template<class observation_type >

bgsub_state& bgsub_state< observation_type >::operator= ( bgsub_state< observation_type > & new_state ) [inline]

template<class observation_type >

double bgsub_state< observation_type >::predict	(	const observation_type &	observation,
		const double	variance_scale = `1.0`
	)			`[inline, virtual]`

The importance distribution of the tracker.

Parameters:

`[in]`	observation	The current observation.
`[in]`	variance_scale	A scale factor for the default variance. This is used for annealed filters.

Returns:: The correction factor for the importance distribution (most often 1).

Implements state< observation_type >.

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

/home/hauberg/Dokumenter/Capture/humim-tracker-0.1/src/bgsub_state.h

bgsub_state< observation_type > Class Template Reference

Public Member Functions

Detailed Description

template<class observation_type> class bgsub_state< observation_type >

Constructor & Destructor Documentation

Member Function Documentation

template<class observation_type>
class bgsub_state< observation_type >