极限分割估计矩形的Bounding-Box定位算法

Bounding-Box localization algorithm based on limit partition of estimated rectangle

针对无线传感器网络中Bounding-Box算法定位精度低的问题,在Bounding-Box算法的基础上提出一种极限分割估计矩形的方法来改进定位算法,分割后的估计矩形产生一个待选质心,当满足分割条件时,对估计矩形继续分割,并不断产生待选质心,当满足终止分割条件时,将上一次分割得到的待选质心坐标作为未知节点的最终位置,通过极限分割的方法可以修正未知节点的定位误差。仿真结果表明,在无需增加额外通信开销的情况下,改进的算法在一定程度上降低了算法的平均相对定位误差。

Aiming to the problem of low positioning accuracy,in Wireless Sensor Network(WSN),for traditional Bounding-Box algorithm,the method of limit partition is proposed on the basis of Bounding-Box algorithm to improve the localizationalgorithm.The estimated rectangle produces a desired centroid after partition.While satisfying the conditions of partition,continue partitioning and producing a new desired centroid.If the termination condition is satisfied,the centroid coordinatesof the last partition are chosen as the final position of the unknown node.The simulation results suggest that,incase of no additional communication overhead,the improved algorithm reduces the average relative positioning error ofthe algorithm to a certain extent.