cv::KalmanFilter Class Reference

Kalman filter class. More...

#include "tracking.hpp"

Collaboration diagram for cv::KalmanFilter:

Public Member Functions
	KalmanFilter ()
	The constructors. More...
	KalmanFilter (int dynamParams, int measureParams, int controlParams=0, int type=CV_32F)
	This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...
const Mat &	correct (const Mat &measurement)
	Updates the predicted state from the measurement. More...
void	init (int dynamParams, int measureParams, int controlParams=0, int type=CV_32F)
	Re-initializes Kalman filter. More...
const Mat &	predict (const Mat &control=Mat())
	Computes a predicted state. More...

Public Attributes
Mat	controlMatrix
	control matrix (B) (not used if there is no control) More...
Mat	errorCovPost
	posteriori error estimate covariance matrix (P(k)): P(k)=(I-K(k)*H)*P'(k) More...
Mat	errorCovPre
	priori error estimate covariance matrix (P'(k)): P'(k)=A*P(k-1)*At + Q)*/ More...
Mat	gain
	Kalman gain matrix (K(k)): K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R) More...
Mat	measurementMatrix
	measurement matrix (H) More...
Mat	measurementNoiseCov
	measurement noise covariance matrix (R) More...
Mat	processNoiseCov
	process noise covariance matrix (Q) More...
Mat	statePost
	corrected state (x(k)): x(k)=x'(k)+K(k)*(z(k)-H*x'(k)) More...
Mat	statePre
	predicted state (x'(k)): x(k)=A*x(k-1)+B*u(k) More...
Mat	temp1
Mat	temp2
Mat	temp3
Mat	temp4
Mat	temp5
Mat	transitionMatrix
	state transition matrix (A) More...

Detailed Description

Kalman filter class.

The class implements a standard Kalman filter http://en.wikipedia.org/wiki/Kalman_filter, [90] . However, you can modify transitionMatrix, controlMatrix, and measurementMatrix to get an extended Kalman filter functionality. See the OpenCV sample kalman.cpp.

Note

• An example using the standard Kalman filter can be found at opencv_source_code/samples/cpp/kalman.cpp

Constructor & Destructor Documentation

cv::KalmanFilter::KalmanFilter

(

)

The constructors.

Note

In C API when CvKalman* kalmanFilter structure is not needed anymore, it should be released with cvReleaseKalman(&kalmanFilter)

cv::KalmanFilter::KalmanFilter	(	int	dynamParams,
		int	measureParams,
		int	controlParams = 0,
		int	type = CV_32F
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

dynamParams	Dimensionality of the state.
measureParams	Dimensionality of the measurement.
controlParams	Dimensionality of the control vector.
type	Type of the created matrices that should be CV_32F or CV_64F.

Member Function Documentation

const Mat& cv::KalmanFilter::correct

(

const Mat &

measurement

)

Updates the predicted state from the measurement.

Parameters

measurement

The measured system parameters

void cv::KalmanFilter::init	(	int	dynamParams,
		int	measureParams,
		int	controlParams = 0,
		int	type = CV_32F
	)

Re-initializes Kalman filter.

The previous content is destroyed.

Parameters

dynamParams	Dimensionality of the state.
measureParams	Dimensionality of the measurement.
controlParams	Dimensionality of the control vector.
type	Type of the created matrices that should be CV_32F or CV_64F.

const Mat& cv::KalmanFilter::predict

(

const Mat &

control = Mat()

)

Computes a predicted state.

Parameters

control

The optional input control

Member Data Documentation

Mat cv::KalmanFilter::controlMatrix

control matrix (B) (not used if there is no control)

Mat cv::KalmanFilter::errorCovPost

posteriori error estimate covariance matrix (P(k)): P(k)=(I-K(k)*H)*P'(k)

Mat cv::KalmanFilter::errorCovPre

priori error estimate covariance matrix (P'(k)): P'(k)=A*P(k-1)*At + Q)*/

Mat cv::KalmanFilter::gain

Kalman gain matrix (K(k)): K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)

Mat cv::KalmanFilter::measurementMatrix

measurement matrix (H)

Mat cv::KalmanFilter::measurementNoiseCov

measurement noise covariance matrix (R)

Mat cv::KalmanFilter::processNoiseCov

process noise covariance matrix (Q)

Mat cv::KalmanFilter::statePost

corrected state (x(k)): x(k)=x'(k)+K(k)*(z(k)-H*x'(k))

Mat cv::KalmanFilter::statePre

predicted state (x'(k)): x(k)=A*x(k-1)+B*u(k)

Mat cv::KalmanFilter::temp1

Mat cv::KalmanFilter::temp2

Mat cv::KalmanFilter::temp3

Mat cv::KalmanFilter::temp4

Mat cv::KalmanFilter::temp5

Mat cv::KalmanFilter::transitionMatrix

state transition matrix (A)

---

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

• video/include/opencv2/video/tracking.hpp