基于蚁群-遗传算法的改进多目标数据关联方法
袁东辉;刘大有;申世群
【期刊名称】《通信学报》 【年(卷),期】2011(032)006
【摘要】An AC-GADA (ant colony-genetic algorithm data association) algorithm was proposed to deal with the data association problem for multi-target tracking. This algorithm designed difference pheromone for each ant and improved global pheromone increment model, and combined crossover and mutation strategy with fitness of population model in order to improve rate of convergence and avoid the appearance of local extremum. The comparison with ACDA (ant colony data association) and JPAD (joint pobabilistic data association) proved its efficiency and superiority.%将蚁群算法与遗传算法相结合,提出一种快速实现多目标数据关联的AC-GADA(ant colony-genetic algorithm data association)算法,该算法利用种群个体携带信息素,并改进了全局信息素扩散模型,同时为了提高算法的收敛速度并且避免局部极值的出现,引入了交叉变异策略和种群适应度模型,通过大量的实验数据证明,该算法在获得较高关联准确率的同时可以有效地提高关联速度. 【总页数】7页(17-23)
【关键词】数据关联;多目标;蚁群算法;遗传算法 【作者】袁东辉;刘大有;申世群
【作者单位】吉林大学知识工程与符号计算教育部重点实验室,吉林长春
基于蚁群-遗传算法的改进多目标数据关联方法
