Tracking and data association
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
Multisensor state estimation is an important issue in multisensor data fusion. In order to solve the centralized multisensor state estimation problem of a non-Gaussian nonlinear system, the paper proposes a new multisensor sequential particle filter (MSPF). First, the general theoretical model of a centralized multisensor particle filter is obtained. Then, a sequential resampling method is proposed according to the characteristics of a centralized multisensor system. Last, a Monte Carlo simulation is used to analyze the performance of the method. The results of the simulation show that the new method can greatly improve the state estimation precision of a multisensor system. Moreover, it will gain more accuracy in estimation with an increase in sensor numbers.