动态目标搜索中自适应参数差分进化算法仿真

Simulation of Adaptive Parameter Differential Evolution Algorithm in Dynamic Target Search

为了准确、高效地完成动态目标的搜索,需要对动态目标搜索方法进行研究。采用当前方法对动态目标进行搜索时,不能有效的去除运动过程中动态目标背景存在的噪声,且搜索动态目标所用的时间较长,存在搜索效率低和准确率低的问题。在自适应参数差分进化算法的基础上提出一种动态目标搜索方法,根据动态目标运动矢量计算子图像块的最小平均绝对差值,对动态目标背景进行补偿。采用自适应参数差分进化算法初始化种群、设置参数,根据调整后的变异率和交叉率对种群进行变异操作和交叉操作,最后对种群进行选择操作,通过设置终止条件输出得到动态目标的搜索结果,完成动态目标的搜索。仿真结果表明,所提方法的搜索效率高、准确率高。

In order to accurately and efficiently complete the search of dynamic target, it is necessary to research the dynamic target search method. Based on the adaptive parameter differential evolution algorithm, this article puts forward a method to search dynamic target. According to the dynamic target motion vector, we calculated the minimum mean absolute difference of sub-image block and compensated the dynamic target background. Then, we used adaptive parameter differential evolution algorithm to initialize the population and set parameters. According to the adjusted mutation rate and crossover rate, we performed mutation operation and cross operation on population. Finally, we selected the population and obtained the search result of dynamic target by setting the end condition output. Thus , we completed the dynamic target search. Simulation results show that the proposed method has high search efficiency and accuracy.