说明：  在目标跟踪领域, 粒子滤波技术有处理非线性非高斯问题的优势, 但是标准粒子滤波在利用重采样方法解决退化现象时, 会产生粒子贫化问题, 导致滤波精度不稳定. 针对这种问题, 本文算法采用了差分进化蝙蝠算法对粒子滤波进行改进. 本文算法将粒子表征为蝙蝠个体, 蝙蝠种群通过调节频率、响度、脉冲发射率, 伴随当前最优蝙蝠个体在目标图像区域进行搜索, 并且可以动态决策是采用全局搜索还是进行局部搜索, 从而提高粒子整体的质量和合理的分布; 引进的差分进化策略可以增强蝙蝠个体跳出局部最优的能力. 为了验证本文算法的优化性能, 将本文算法和标准粒子滤波算法进行性能分析对比. 实验结果表明本文算法滤波性能优于标准粒子滤波算法.
(In the field of target tracking, particle filter has the advantage of dealing with nonlinear non Gaussian problems. However, when the standard particle filter uses resampling to solve the degradation, particle dilution will occur, which leads to unstable filtering accuracy, In this paper, the particle filter is improved by using the differential evolutionary bat algorithm. In this paper, the particle is represented as bat individual. The bat population can search in the target image region by adjusting the frequency, loudness and pulse emission rate. The dynamic decision can be made by global search or local search, In order to verify the optimization performance of the algorithm, the performance of this algorithm and the standard particle filter algorithm are compared. The experimental results show that the performance of the algorithm is better than the standard particle filter algorithm)