论文部分内容阅读
提出一种新的多目标跟踪算法:核粒子概率假设密度滤波算法(KP-PHDF)。算法的创新点在概率假设密度滤波算法(PHDF)的目标状态提取步骤,以粒子概率假设密度滤波算法为框架,并运用结合了mean-shift算法的核密度估计(KDE)理论进行概率假设密度(PHD)分布的二次估计、提取PHD峰值位置作为目标状态估计值。分析与多目标跟踪(MTT)仿真的结果表明,与现有序列蒙特卡罗概率假设密度滤波算法(SMC-PHDF)相比,在相同仿真条件下新算法的估计精度提高30.5%。
A new multi-target tracking algorithm is proposed: kernel particle probability hypothesis density filtering algorithm (KP-PHDF). Algorithm innovation point In the probability hypothesis density filtering algorithm (PHDF) target state extraction steps, the particle probability hypothesis density filtering algorithm as a framework and the use of mean-shift algorithm based on the kernel density estimation (KDE) theory of probability hypothesis density ( PHD) distribution of the second estimate, PHD peak position extracted as the target state estimates. The results of analysis and multi-target tracking (MTT) simulation show that compared with the existing sequential Monte Carlo probability hypothesis density filter algorithm (SMC-PHDF), the accuracy of the new algorithm is improved by 30.5% under the same simulation conditions.