Public Member Functions | Protected Attributes | Static Protected Attributes

stick_state< observation_type > Class Template Reference

#include <stick_state.h>

Inheritance diagram for stick_state< observation_type >:
skeleton_state< observation_type > state< observation_type >

List of all members.

Public Member Functions

 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)
stick_state & operator= (stick_state &new_state)
bool load (const std::string filename)
bool load (std::ifstream &file)

Protected Attributes

std::vector< double > lambda
const double pred_noise

Static Protected Attributes

static const double p_letgo = 0.05
static const double T_E = 1.0
static const double sigma = 0.0001

Detailed Description

template<class observation_type>
class stick_state< observation_type >

An implementation projected prior constrained by 3D information about a stick that the user is interacting with. If you use this class we recommend citing 

 @inproceedings{hauberg_accv2010,
  author = {S{\o}ren Hauberg and Kim S. Pedersen},
  title = {{Stick It! Articulated Tracking using Spatial Rigid Object Priors}},
  booktitle = {ACCV 2010},
  year = {2010},
  pages = {},
  publisher = {Springer-Verlag},
 }

Constructor & Destructor Documentation

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

Member Function Documentation

template<class observation_type>
bool 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 skeleton_state< observation_type >.

template<class observation_type>
bool 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 skeleton_state< observation_type >.

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

Implements state< observation_type >.

Member Data Documentation

template<class observation_type>
std::vector<double> stick_state< observation_type >::lambda [protected]
template<class observation_type>
const double stick_state< observation_type >::p_letgo = 0.05 [static, protected]
template<class observation_type>
const double stick_state< observation_type >::pred_noise [protected]
template<class observation_type>
const double stick_state< observation_type >::sigma = 0.0001 [static, protected]
template<class observation_type>
const double stick_state< observation_type >::T_E = 1.0 [static, protected]
The documentation for this class was generated from the following file:
Generated on Thu Dec 1 2011 12:54:43 for HUMIM Tracker by  doxygen 1.7.1