改进集合平方根滤波的目标跟踪算法

Improved Set Square Root Filtering Algorithm for Target Tracking

目标跟踪算法的目的是在部分含噪声的可用观测值中估计目标的位置,最大的难点是测量源的不确定和剔除杂波的干扰。针对高斯噪声下的线性动态系统,论文采用非最优的粒子滤波器,通过一个连续的蒙特卡洛方法实现随机滤波出了在集合平方根的滤波框架中采用基于样本的联合概率数据关联技术的目标跟踪算法。实验通过将其跟踪性能与常规的自举和辅助自举粒子滤波器的比较,证明该方法跟踪更加准确高效。

The purpose of the target tracking algorithm is to estimate the position of the target in the available observations with noise. The biggest difficuhy is the uncertainty of the measurement source and the interference of the clutter. According to the linear dynamic system under Gaussian noise, this paper uses a non-optimal particle filter to achieve a randomized filtering of the target of joint probability data association based on the sample in the filter frame of the set square root by a continuous Monte Carlo method Tracking algorithm. Experiments show that the method is more accurate and efficient by comparing the tracking performance with the conventional bootstrap and auxiliary- bootstrap filter.