Decentralised particle filtering for multiple target tracking in wireless sensor networks

This paper presents algorithms for consistent joint localisation and tracking of multiple targets in wireless sensor networks under the decentralised data fusion (DDF) paradigm where particle representations of the state posteriors are communicated. This work differs from previous work as more generalised methods have been developed to account for correlated estimation errors that arise due to common past information between two discrete particle sets. The particle sets are converted to continuous distributions for communication and inter-nodal fusion. Common past information is then removed by a division operation of two estimates so that only new information is updated at the node. In previous work, the continuous distribution used was limited to a Gaussian kernel function. This new method is compared to the optimal centralised solution where each node sends all observation information to a central fusion node when received. Results presented include a real-time application of the DDF operation of division on data logged from field trials.