Application of particle swarm optimization in multi-sensor multi-target tracking

For the multi-sensor multi-target data association problem, a novel particle swarm optimization (PSO) algorithm based S-dimensional (S-D) assignment method is proposed in this paper. By a combinational optimal way, it could find the minimum objective cost to be the best solution. Furthermore, the best solution could be searched soon through reducing the search region. The reason is that the validity of the candidate measurements is considered in particle swarm initialization, cross-over rules, and mutation rules. The PSO using different rules and GA are simulated for data association in the presence of fault alarms, and missed detections. The comparison testifies the proposed approach is effective.