基于改进布谷鸟粒子滤波算法的WSN目标跟踪

WSN Target Tracking Based on Improved Cuckoo Particle Filter Algorithm

摘要:

为了解决粒子滤波(PF)的无线传感器目标跟踪中样本贫化导致的精度较低的问题,提出了改进布谷鸟粒子滤波的WSN目标跟踪方法。通过改进布谷鸟算法的滤波算法取代粒子滤波重采样过程,主要通过改进布谷鸟算法中的搜索步长值 和发现外来鸟卵的物种的概率 的自适应调节,同时在步长更新方程中实时引入函数值的变化趋势,引导粒子整体上向较高的随机区域移动, 有效调整全局探索和局部探索适应能力、改善粒子贫化和局部极值问题,增加粒子群多样化从而提高跟踪性能。实验结果表明,改进布谷鸟粒子滤波算法重采样方法可以防止粒子的退化,增加粒子的多样性,减少跟踪误差,可以减少算法的运行时间,实时追踪性能大幅提高。与CS-PF算法和PF算法相比较,ICS-PF 算法的计算时间是最短的,ICS-PF算法的位置和速度的平均平方根误差最小(位置0.0306、0.0213、速度0.0253、0.0102),PF算法的跟踪精度是最低的,而ICS-PF跟踪精度较高,ICS-PF算法被证明具有良好的跟踪性能。

Abstract:

In order to solve the problem of low precision caused by sample dilution in wireless sensor target tracking based on particle filter (PF), a WSN target tracking method based on improved cuckoo particle filter is proposed. The filter algorithm of the improved cuckoo algorithm replaces the particle filter resampling process, mainly through the adaptive adjustment of the search step value and the probability of discovering exotic bird eggs in the cuckoo algorithm, and meanwhile, the change trend of function value is introduced into the step update equation in real time. It can guide particles to move to a higher random region on the whole, effectively adjust the adaptability of global exploration and local exploration, improve particle dilution and local extreme value problems, and increase the diversity of particle swarm to improve tracking performance. The experimental results show that the improved resampling method of cuckoo particle filter algorithm can prevent the degradation of particles, increase the diversity of particles, reduce the tracking error, reduce the running time of the algorithm, and greatly improve the real-time tracking performance. Compared with CS-PF algorithm and PF algorithm, The ICS-PF algorithm has the shortest calculation time, the ICS-PF algorithm has the smallest mean square root error of position and velocity (position 0.0306, 0.0213, speed 0.0253, 0.0102), and the PF algorithm has the lowest tracking accuracy. The Tracking accuracy of ICS-PF is higher, and the Algorithm has been proved to have good tracking performance.