Abstract | ||
---|---|---|
We address the image formation of a dynamic object from projections by formulating it as a state estimation problem. The problem is solved with the ensemble Kalman filter (EnKF), a Monte Carlo algorithm that is computationally tractable when the state dimension is large. In this paper, we first rigorously address the convergence of the EnKF. Then, the effectiveness of the EnKF is demonstrated in a numerical experiment where a highly variable object is reconstructed from its projections, an imaging modality not yet explored with the EnKF. The results show that the EnKF can yield estimates of almost equal quality as the optimal Kalman filter but at a fraction of the computational effort. Further experiments explore the rate of convergence of the EnKF, its performance relative to an idealized particle filter, and implications of modeling the system dynamics as a random walk. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/TIP.2009.2017996 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Tomography,State estimation,Biomedical imaging,Sea measurements,Convergence,Image reconstruction,Particle filters,Statistics,Random processes,Remote sensing | Convergence (routing),Particle filter,Rate of convergence,Artificial intelligence,Ensemble Kalman filter,Iterative reconstruction,Mathematical optimization,Monte Carlo method,Monte Carlo algorithm,Pattern recognition,Algorithm,Kalman filter,Mathematics | Journal |
Volume | Issue | ISSN |
18 | 7 | 1057-7149 |
Citations | PageRank | References |
3 | 0.57 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mark D. Butala | 1 | 24 | 4.80 |
Richard A. Frazin | 2 | 15 | 2.43 |
Yuguo Chen | 3 | 187 | 11.67 |
Farzad Kamalabadi | 4 | 98 | 17.82 |