加权凸集投影法在分布式目标定位中的应用

Application of Weighted Projections onto Convex Sets in Distributed Source Localization

针对基于能量的分布式目标定位算法——加权凸集投影法(POCS)精度不高、稳定性差的不足,提出一种加权POCS算法。在已有圆的方差基础上,推导出直线的方差,并建立POCS迭代步长与圆和直线方差的关系式,实现加权的迭代。通过控制到不同圆和直线的步长,减少噪声对定位的影响。实验证明,提出的加权POCS算法比普通POCS算法具有更高的精度和稳定性。

This paper proposes a distributed object oriented algorithm based on energy weighted Projections onto Convex Sets（POCS） to solve the problem that POCS is not accurate and stable. Based on the variance of circle, the variance of line is derived, and a relationship equation between the variance and the pace of POCS is set up to realize weighted POCS. To control paces to different circles and lines, the influence of noise is reduced. It is proved that weighted POCS is more accurate and stable.