基于关系矩阵的多传感器数据融合方法

A Relation Matrix Method for Multisensor Data Fusion

以置信距离测度作为数据融合的融合度,先计算出置信距离矩阵,然后分析了计算关系矩阵和确定最佳融合数的几种不同方法,通过分析和算例可以看出,应用椭圆曲线表示的支持程度有助于提高融合结果;并讲述了极值原理法、极大似然法、Bayes法和综合支持程度等数据融合方法,算例表明,这几种融合方法都十分有效,在实际应用中应根据具体情况选择不同的融合方法。

In this paper, the confidence distance measure is used to be fusion measure of data fusion. Several method of calculate relation matrix though confidence distance matrix is given. The analysis and the fusion results from the example show using the ellipse curve relation matrix can improve the precise of the result. Finally, the fused results of example are given by maximum principle and maximum likelihood method and Bayes theory and fuzzy index. The fused results shows these methods are very effective and could be used accord case.