My Project
Public Member Functions | List of all members
UnscentedProcess Class Referenceabstract

Process model for an unscented kalman filter. More...

#include <UnscentedKalman.h>

Public Member Functions

virtual void f (cv::Mat &state)=0
 process model: state+1 = f(state) More...
 
virtual cv::Mat getProcessNoise ()=0
 Returns the process noise covariance. More...
 

Detailed Description

Process model for an unscented kalman filter.

Implementing class needs to allocate a noise matrix of correct size.

Definition at line 230 of file UnscentedKalman.h.

Member Function Documentation

◆ f()

virtual void f ( cv::Mat &  state)
pure virtual

process model: state+1 = f(state)

Model the process by computing an estimate how the process changes when one timestep is taken.

Parameters
statestate_n size vector; The current state in input and the next state estimate in output.

◆ getProcessNoise()

virtual cv::Mat getProcessNoise ( )
pure virtual

Returns the process noise covariance.

The returned matrix will be added to the current state covariance matrix, increasing the uncertainty of the current state. The matrix should reflect all unknown factors of the process which are not taken into account by the state estimation method f.

Returns
state_n by state_n size matrix; or NULL for no additional noise.

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