Multiple resolvable group target estimation using graph theory and the multi-Bernoulli filter

This paper considers multiple resolvable group target estimation under clutter environment. We first build the structure for the resolvable group targets using graph theory. Then, the group estimation involves two stages of the target state estimation and group state (group size, shape, etc) estimation. In the first stage, based on the given group dynamic models, we derive the target estimated state set and the number of targets by using the multi-Bernoulli filter under the assumption of independence of all targets. In the second stage, we combine the graph theory with the group targets and build the adjacency matrix of the estimated state set. We thus get the number of the subgroups, the group state, the group sizes and its structures. Finally, a linear and a non-linear examples are given to verify the proposed algorithm, respectively.