PCL环境下粒子滤波目标跟踪算法研究

发布时间：2018-01-05 04:01

  本文关键词：PCL环境下粒子滤波目标跟踪算法研究　出处：《计算机工程》2017年09期 　论文类型：期刊论文

  更多相关文章： 点云库 目标跟踪 粒子滤波 距离阈值 小区域阈值

【摘要】：在实时三维目标跟踪系统中,KL距离自适应粒子滤波算法中距离阈值、小区域阈值以及其他参数的选取往往根据经验设置,如果参数设置不合适会降低跟踪精度和实时性。为此,设计一种3D点云目标跟踪系统。分析距离阈值和小区域阈值等参数对跟踪性能的影响,并给出自适应粒子滤波中参数与跟踪目标模型的关系。实验结果表明,与PCL_Tracking算法相比,该系统提高了三维目标跟踪系统的准确性和实时性。
[Abstract]:In the real-time 3D target tracking system, the range threshold, small region threshold and other parameters are often set according to the experience in the KL distance adaptive particle filter algorithm. If the parameters are not set properly, the tracking accuracy and real-time will be reduced. Therefore, a 3D point cloud target tracking system is designed. The influence of distance threshold and small region threshold on tracking performance is analyzed. The relationship between the parameters of the adaptive particle filter and the target tracking model is given. The experimental results show that the proposed algorithm is compared with the PCL_Tracking algorithm. This system improves the accuracy and real-time of three-dimensional target tracking system.
【作者单位】： 武汉科技大学冶金自动化与检测技术教育部工程研究中心;
【基金】：国家自然科学基金(61175094,61673304)
【分类号】：TN713;TP391.41
【正文快照】： 中文引用格式:康雅文,闵华松,陈鸣宇,等.PCL环境下粒子滤波目标跟踪算法研究[J].计算机工程,2017,43(9):304-309.英文引用格式:KANG Yawen,MIN Huasong,CHEN Mingyu,et al.Research on Target Tracking Algorithm for ParticleFiltering Under PCL Environment[J].Computer En，

本文编号：1381439