基于两级采样的粒子滤波检测前跟踪算法

Particle filter track-before-detect algorithm based on two-hierarchy sampling

针对粒子滤波检测前跟踪算法中高维状态采样效率低的问题,提出了一种基于两级采样的粒子滤波检测前跟踪算法。根据状态向量中各分量对量测有无直接影响,把粒子的高维状态采样转换为两个序列低维采样,提高了粒子采样效率,进而可获得更高的检测概率和估计精度。仿真结果验证了算法的有效性。

A particle filter track-before-detect （TBD） algorithm based on two-hierarchy sampling is proposed to deal with low sampling efficiency in high dimension state space. According to each component＇s impacting on measurement directly or not, the higher-dimension state sampling process is converted to two successive lower dimension state sampling processes. This algorithm improves the efficiency of state sampling for particles, and a better detection and tracking performance is obtained. Simulation results show the effectiveness of the proposed algorithm.