东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2010, Vol. 31 ›› Issue (3): 334-337.DOI: -

• 论著 • 上一篇    下一篇

一种适用于建筑灾难救援系统的目标跟踪方法

贾子熙;吴成东;张云洲;黄月;   

  1. 东北大学信息科学与工程学院;
  • 收稿日期:2013-06-20 修回日期:2013-06-20 发布日期:2013-06-20
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(60874103)

A target tracking method of rescue system for buildings during disaster

Jia, Zi-Xi (1); Wu, Cheng-Dong (1); Zhang, Yun-Zhou (1); Huang, Yue (1)   

  1. (1) School of Information Science and Engineering, Northeastern University, Shenyang 110004, China
  • Received:2013-06-20 Revised:2013-06-20 Published:2013-06-20
  • Contact: Jia, Z.-X.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

715

摘要： 在目标跟踪研究中,大量的实验证明粒子滤波算法对于运动轨迹变化复杂的运动目标跟踪效果不理想.基于变率粒子滤波算法(VRPF),以大型建筑灾难救援系统为研究背景,应用无线传感器网络技术,提出了一种自适应变率粒子滤波算法(AVRPF).该算法通过比较某时刻粒子值与测量值的关系自适应地调节采样周期,以提高对复杂运动目标的跟踪精度,尤其当运动轨迹出现大幅度变化时.仿真实验证明了该算法的有效性和实用性.

关键词: 无线传感器网络, 变率粒子滤波, 自适应, 跟踪

Abstract: In the research on target tracking, lots of experimental results illustrated that the particle filter algorithm is imperfect to the moving target of which the trajectory changes complexly. The AVRPF (adaptive variable rate particle filter) algorithm is proposed instead of VRPF (variable rate particle filter) algorithm in regard to the rescue system for large-scale building during disaster, with the wireless sensor network technology applied to the system. The AVRPF can adaptively adjust the sampling period by comparing the relationships between the particle value and measured value at a certain moment to improve the tracking accuracy for complex moving target, especially the moving trajectory changes dramatically. The simulation results showed that the tracking algorithm is effective and practical.

中图分类号: