Public Member Functions | Protected Member Functions | Protected Attributes

pik_state< observation_type > Class Template Reference

#include <pik_state.h>

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

List of all members.

Public Member Functions

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

Protected Member Functions

void set_end_effectors (const std::vector< vector3 > &data)
void get_end_effectors (std::vector< vector3 > &data)

Protected Attributes

size_t num_end_effectors
std::vector< vector3 > prev_end_effectors
std::vector< vector3 > curr_end_effectors

Detailed Description

template<class observation_type>
class pik_state< observation_type >

An implementation of the Probabilistic Inverse Kinematics prior. If you use this class we recommend citing 

 @article {hauberg:ijcv11,
  author = {S{\o}ren Hauberg and Kim Steenstrup Pedersen},
  title = {{Predicting Articulated Human Motion from Spatial Processes}},
  journal = {International Journal of Computer Vision},
  publisher = {Springer},
  pages = {317--334},
  volume = {94},
  issue = {3},
  year = {2011}
 }

Constructor & Destructor Documentation

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

Member Function Documentation

template<class observation_type >
void pik_state< observation_type >::get_end_effectors ( std::vector< vector3 > &  data  )  [inline, protected]
template<class observation_type >
void pik_state< observation_type >::linear_motion (  )  [inline]
template<class observation_type >
bool pik_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 pik_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 >
pik_state& pik_state< observation_type >::operator= ( pik_state< observation_type > &  new_state  )  [inline]
template<class observation_type >
void pik_state< observation_type >::pelvic_lift (  )  [inline]
template<class observation_type >
double pik_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 >.

template<class observation_type >
void pik_state< observation_type >::set_end_effectors ( const std::vector< vector3 > &  data  )  [inline, protected]

Member Data Documentation

template<class observation_type >
std::vector<vector3> pik_state< observation_type >::curr_end_effectors [protected]
template<class observation_type >
size_t pik_state< observation_type >::num_end_effectors [protected]
template<class observation_type >
std::vector<vector3> pik_state< observation_type >::prev_end_effectors [protected]
The documentation for this class was generated from the following file:
Generated on Thu Dec 1 2011 12:54:35 for HUMIM Tracker by  doxygen 1.7.1