摘要
针对可变数目多目标视频跟踪,粒子滤波不能持续维持目标的多模态分布问题,本文提出一种混合粒子概率假设密度(PHD)滤波的多目标视频跟踪算法.该算法首先用K-means算法对粒子进行空间分布聚类,给各粒子群附加身份标签,使各粒子群分别对应混合粒子滤波的各分量,采用相互独立的各分量粒子滤波跟踪各目标,这样提高了目标状态估计的准确性,也能有效维持各目标的多模态分布.实验结果表明,该算法能有效处理新目标出现、合并、分离等多目标跟踪问题.
Aiming at the problem that particle filter is poor at consistently maintaining the muhi-modality of the target distributions for multi-targets in a variable number of visual tracking, a multi-target visual tracking approach based on mixture particle probability hypothesis density （PHD） filter is proposed. The particles are clustered by the K-means algorithm, the classified particles are labeled and the particle filters are separately used for each classified particles. It improves the accuracy of target states estimation and effectively maintains the multi-modal distribution of the various objectives. The experimental results show that the proposed approach is an effective solution to the appearance, merger, separation and other multi-target tracking problems for the new target.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2013年第9期885-890,共6页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.61170126)
江苏省科技支撑项目(No.BE2011156)
江苏省自然科学基金项目(No.BK2011521)资助
关键词
混合粒子滤波器
概率假设密度
多目标跟踪
多模态分布
Mixture Particle Filter, Probability Hypothesis Density, Multi-Target Tracking, Muhi-Modal Distribution
