Adaptive sensor selection for target tracking using particle filter

This study presents a novel particle filtering approach for multiple sensor target tracking. In contrast to the standard form, each particle only uses the measurements received by a single selected sensor to estimate the mean and covariance of the target state. In order to do so, sensor selections are sampled using a particle filter and the hidden states are marginalised over. Finite number of sensors allows the exact calculation of the normalisation constant, thus the sampling can be done from the optimal importance distribution. In addition, an extension to the multiple sensor case of the probabilistic data association approach is also provided when clutter or false alarm is considered. Simulation examples that involve tracking a bearings-only target are provided to demonstrate the effectiveness of the proposed algorithms in critical situations where the single-sensor observability is lacking.