摘要
针对多传感器多目标跟踪,提出一种基于数据压缩的多传感器概率假设密度(PHD)滤波算法,解决串行多传感器PHD(SMSPHD)滤波计算量过大的问题。算法首先利用数据压缩将多传感器量测数据转换成等效的单传感器量测数据,然后在此基础上进行PHD滤波。仿真结果表明,该算法可以实现对多目标的有效跟踪;此外,随传感器数目的增加,该算法增加的计算量约为SMSPHD滤波算法增加的4.3%。
For multi-sensor multi-target tracking, a novel multi-sensor probability hypothesis density （PHD） filter based on data compression was proposed to solve the computation load of the serial multi-sensor PHD （SMSPHD） filter. With the proposed method, firstly, the multi-sensor measurements were equivalently converted to those from a single sensor by using data compres- sion, then, the PHD filter was executed. The simulation results demonstrate that the proposed method can realize the tracking of multiple targets effectively. Moreover, as the increasing of the number of sensors, the added computational complexity of the proposed method is about 4.3% of that of the SMSPHD.
出处
《弹箭与制导学报》
CSCD
北大核心
2011年第2期161-164,共4页
Journal of Projectiles,Rockets,Missiles and Guidance
基金
国家自然科学基金(60972159
61032001
61002006)
航空科学基金资助
关键词
数据压缩
概率假设密度
多传感器
多目标跟踪
data compressing
probability hypothesis density
multi-sensor
multi-target tracking
