期刊文献+

基于粒子滤波和检测信息的多传感器融合跟踪 被引量:4

Multi-sensor Fusion Tracking Based on Particle Filterin g and Detection Information
下载PDF
导出
摘要 从概率角度审视低检测率、低信噪比下的多传感器融合算法.首先建立传感器检测概率模型,然后计算传感器检测响应、量测信息的融合似然度,在贝叶斯框架下建立一种非线性目标基于粒子滤波器的多传感器多源信息融合算法,该算法融合了传感器的量测信息和检测响应,提高了跟踪精度蒙特卡洛仿真结果表明了算法的有效性. A multi-sensor fusion algorithm under low detect io n probability and low signal-to-noise ratio environment is discussed in this paper. First, detection probability of sensor is modeled. Then, mixed likelihood of detection response and measurement information is calculated. A nonlinear ta rget multi-sensor multi-resource fusion algorithm based on particle filter is established within Bayesian framework. The proposed algorithm utilizes detection responses and measurement information of sensors, and the tracking accuracy is enhanced. The effectiveness of the proposed method is shown by Monte Carlo simul ation results.
出处 《信息与控制》 CSCD 北大核心 2005年第3期356-359,共4页 Information and Control
基金 国家自然科学基金资助项目(60404011 60372085)
关键词 粒子滤波器 多传感器 信息融合 检测和跟踪 目标跟踪 particle filter multi-sensor information fusion detecting and tracking target tracking
  • 相关文献

参考文献4

  • 1Bar-Shalom Y, Li X R. Multi-target Multi-sensor Tracking: Principles and Techniques [M]. Storrs,, CT: YBS Publishing, 1995.
  • 2Gordon N J, Salmond D J, Smith A F M. Novel approach to nonlinear/non-Gaussian Bayesian state estimation [J]. IEE Proceedings on Radar and Signal Processing, 1993,140 (2) : 107 - 113.
  • 3Doucet A, de Freitas J F G, Gorden N J. Sequential Monte Carlo Methods in Practice [ M]. New York: Springer-Verlag, 2001.
  • 4Lawrence D S, Carl A B, Thomas L C. Bayesian Multiple Target Tracking [M]. Boston London: Artech House, 1999.

同被引文献43

引证文献4

二级引证文献16

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部