| 量测不确定下多传感器自适应粒子滤波算法 |
| |
| 引用本文： | 胡振涛 潘泉 金勇 张帆. 量测不确定下多传感器自适应粒子滤波算法[J]. 控制与决策, 2012, 27(4): 547-550 |
| |
| 作者姓名： | 胡振涛 潘泉 金勇 张帆 |
| |
| 作者单位： | 河南大学图像处理与模式识别研究所;西北工业大学自动化学院 |
| |
| 基金项目： | 国家自然科学基金项目(60972119,61170243);河南省创新人才培养计划(114100510001) |
| |
| 摘 要： | 针对量测不确定条件下多传感器量测数据的有效利用问题,提出一种多传感器自适应粒子滤波算法.利用随机采样策略和量测模型转移概率实现当前时刻多传感器量测集合的采样,通过粒子滤波中重采样步骤完成估计状态和量测集合的更新,进而依据重采样后单个传感器量测数目在传感器量测集合中的比重实现当前时刻传感器量测的确认.该算法通过有效量测的合理选择,改善了扰动对滤波精度和计算量的不利影响.理论分析和仿真实验均验证了所提出算法的有效性.
|
| 关 键 词： | 非线性滤波 多传感器 信息融合 粒子滤波 量测不确定 |
| 收稿时间： | 2010-11-02 |
| 修稿时间： | 2011-05-09 |
Multi-sensor adaptive particle filter in measurement uncertainty |
| |
| HU Zhen-tao PAN Quan JIN Yong ZHANG Fan. Multi-sensor adaptive particle filter in measurement uncertainty[J]. Control and Decision, 2012, 27(4): 547-550 |
| |
| Authors: | HU Zhen-tao PAN Quan JIN Yong ZHANG Fan |
| |
| Affiliation: | 1(1.Institute of Image Processing and Pattern Recognition,He’nan University,Kaifeng 475001,China;2.College of Automation,Northwestern Polytechnical University,Xi’an 710072,China.) |
| |
| Abstract: | Aiming at the effective utilization of multi-sensor measurement in measurement uncertainty,a multi-sensor adaptive particle filter algorithm is proposed.In the algorithm,multi-sensor measurement set is sampled by the random sampling strategy and measurement model transition probability.Then state estimation and the update of multi-sensor measurement set are realized by re-sampling in particle filter.Finally,the current moment measurement is validated according to the proportion of measurement number of single sensor in multi-sensor measurement set after re-sampling.The adverse influence of interference to the computational complexity is by reasonably selecting effective measurement.The theoretical analysis and experimental results show the efficiency of the proposed algorithm. |
| |
| Keywords: | nonlinear filter multi-sensor information fusion particle filter measurement uncertainty |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《控制与决策》浏览原始摘要信息 |
|
点击此处可从《控制与决策》下载全文 |
