作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (08): 1-3. doi: 10.3969/j.issn.1000-3428.2012.08.001

• 博士论文 •    下一篇

基于近邻量测认知信息的多传感器融合估计

张 鹏 1,张建业 2,王占磊 1,谢文俊 1   

  1. (1. 空军工程大学工程学院,西安 710038;2. 空军工程大学科研部,西安 710051)
  • 收稿日期:2011-09-02 出版日期:2012-04-20 发布日期:2012-04-20
  • 作者简介:张 鹏(1979-),男,讲师、博士,主研方向:信息融合与挖掘;张建业,副教授、博士;王占磊,硕士研究生;谢文俊,副教授、博士研究生
  • 基金资助:
    国家自然科学基金资助项目(61074007);陕西省自然科 学基金资助项目(2009JM8002-7)

Multi-sensor Fusion Estimation Based on Adjacent Measurement Cognitive Information

ZHANG Peng 1, ZHANG Jian-ye 2, WANG Zhan-lei 1, XIE Wen-jun 1   

  1. (1. Engineering Institute, Air Force Engineering University, Xi’an 710038, China; 2. Department of Science, Air Force Engineering University, Xi’an 710051, China)
  • Received:2011-09-02 Online:2012-04-20 Published:2012-04-20

摘要: 在构建传感器模糊量测认知偏差的基础上,提出一种新的多传感器融合估计方法。运用相邻量测样本均值和协方差度量传感器可靠性,确保融合权重分配的客观性和灵敏性。实验结果表明,与基于均值融合算法和支持度融合算法相比,使用该方法得到的融合权值分配方式更加合理,可进一步提高估计精度。

关键词: 多传感器融合, 一致性序列, 量测认知偏差, 近邻信息, 可靠性度量, 权重分配

Abstract: On the basis of constructing the fuzzy measurement cognitive bias, a novel independent quota fusion algorithm for the multi-sensor data is proposed. And the given sensor’s reliability can be obtained by using mean value and covariance value of the adjacent information, which can ensure the objectivity and sensitivity for the fusion weight assignment. Experimental result shows that compared with the mean and support degree based data fusion techniques, the more reasonable fusion weight assignment can improve the fusion precision further by the proposed method.

Key words: multi-sensor fusion, consensus sequence, measurement cognitive bias, adjacent information, reliability measurement, weight assignment

中图分类号: