Title | ||
---|---|---|
R-adaptive kalman filtering approach to estimate head orientation for driving simulator |
Abstract | ||
---|---|---|
Kalman filters are used to overcome system latency by predicting head orientation using AC magnetic tracker. To achieve optimum performance from the Kalman filter, the process and measurement covariance must be accurately set to tune the filter in the intelligent environment, i.e. driver assistive service. This paper discusses two adaptive Kalman filters, one using the well known fading memory algorithm and a new approach that adaptively tunes the filter to improve output signal quality. The two filters are tested in a head orientation prediction, and their performance is compared to a non-adaptive Kalman filter. The test results indicate that the adaptive tuning algorithm significantly reduces output noise in realtime head orientation for feasible applications of a driving simulator |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ITSC.2006.1706850 | ITSC |
Keywords | Field | DocType |
kalman filters,driver information systems,knowledge based systems,object recognition,pose estimation,ac magnetic tracker,r-adaptive kalman filtering,driver assistive service,driving simulator,fading memory algorithm,head orientation estimate,intelligent environment,kalman filter | Alpha beta filter,Driving simulator,Control theory,Computer science,Pose,Artificial intelligence,Adaptive filter,Invariant extended Kalman filter,Computer vision,Extended Kalman filter,Fast Kalman filter,Simulation,Kalman filter | Conference |
ISBN | Citations | PageRank |
1-4244-0094-5 | 3 | 0.50 |
References | Authors | |
5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Himberg, H. | 1 | 3 | 0.50 |
Yuichi Motai | 2 | 230 | 24.68 |
Barrios, C. | 3 | 38 | 3.29 |