Abstract:

In order to rapidly realize the association of multi-target data,a hybrid swarm intelligent algorithm is proposed by combining the ant colony optimization ( ACO) algorithm with the particle swarm optimization ( PSO) algorithm. In the algorithm,first,a combinatorial optimization model for the multi-target data association is constructed by using the tracking gate to confirm the effective measurements of targets and by using the likelihood function of the filter innovation to describe the association relation between the measurements and the targets. Then,the PSO algorithm based on the cross and mutation rules is used to obtain the suboptimal solution to the constructed model,and according to the suboptimal solution,the location and pheromone of each ant are initialized. Finally,the ACO algorithm is employed to make a fine searching in the solutions to target functions,so as to obtain a better solution. Simulated results indicate that the proposed algorithm can effectively improve the accuracy and convergence speed of the data association.

Key words: data association, multi-target tracking, ant colony optimization, particle swarm optimization