How can I decompose covariance in kalman filter? The covariance is too large to calculate quickly.
Dear Yuli,
The attached file gives a summary on how to decompose covariance into Kalman filter.
Hoping this will be helpful,
Rafik
You can use Sequential Kalman Filtering Technique.
Detail can be found in following reference:
Optimal State Estimation, Kalman, H,, and Nonlinear Approaches by Dan Simon
Alternate Kalman filter formulations (Chapter-6)
I don't know what exactly your issue it, but to avoid numerical problems associated with positive definitness of the covariacne matrix, Cholesky decompsition may be used.
As addition to the previous advice I can recommend Bierman Factorization, which is very popular in practical applications of Kalman Filtering in the INS/GPS Integrated Systems. You can find all details in the book: G.J. Bierman. Factorization Methods for Discrete Sequential Estimation. Academic Press, 1977.-241p.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Computer Graphics and Animation
- 3D