Public Types | Public Member Functions

brownian_stick_state< observation_type > Class Template Reference

#include <brownian_stick_state.h>

Inheritance diagram for brownian_stick_state< observation_type >:
angle_state< observation_type > skeleton_state< observation_type > state< observation_type >

List of all members.

Public Types

typedef
boost::numeric::ublas::diagonal_matrix
< double > 		diagonal_matrix_type

Public Member Functions

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

Detailed Description

template<class observation_type>
class brownian_stick_state< observation_type >

An implementation of the spatial Brownian motion prior for object interaction. If you use this class we recommend citing 

 @article{hauberg:imavis11,
  title = {{Natural Metrics and Least-Committed Priors for Articulated Tracking}},
  author = {S{\o}ren Hauberg and Stefan Sommer and Kim Steenstrup Pedersen},
  journal = {Image and Vision Computing},
  publisher = {Elsevier},
  year = {2011},
 }

Member Typedef Documentation

template<class observation_type >
typedef boost::numeric::ublas::diagonal_matrix<double> brownian_stick_state< observation_type >::diagonal_matrix_type

Constructor & Destructor Documentation

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

Member Function Documentation

template<class observation_type >
bool brownian_stick_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 angle_state< observation_type >.

template<class observation_type >
bool brownian_stick_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 angle_state< observation_type >.

template<class observation_type >
brownian_stick_state& brownian_stick_state< observation_type >::operator= ( brownian_stick_state< observation_type > &  new_state  )  [inline]
template<class observation_type >
double brownian_stick_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).

Reimplemented from angle_state< observation_type >.

The documentation for this class was generated from the following file:
Generated on Thu Dec 1 2011 12:54:11 for HUMIM Tracker by  doxygen 1.7.1