分布式无线传感网络的协作目标跟踪策略

基于图像序列的目标跟踪是目标跟踪的重要研究问题之一.由于受图像解析度和跟踪范围限制,单视角跟踪准确性和鲁棒性不足.本文提出了分布式无线传感网络测量环境下的多视角协作融合跟踪方法,并引入了渐进分布式数据融合,采用基于能耗参数和信息有效性参数的综合优化函数动态选择融合节点,规划融合过程,平衡融合精度与网络能耗.通过目标跟踪准确性、网络能耗及传输延时对比实验表明:基于渐进分布式数据融合的协作信号处理方法提高了分布式多视角跟踪的准确性与实时性,减少了网络拥塞,降低了通讯能耗及延时.

Collaborative Target Tracking Strategy in Distributed Wireless Sensor Networks

Target tracking in complex situations is challenging,especially in visual tracking,which is always performed in single-view system.Because of the conflict between resolution and tracking range,however,single-view tracking is not robust and accurate.This paper presents a distributed multi-view tracking system using collaborative signal processing(CSP) in distributed wireless sensor networks(DWSNs),and introduces a progressive distributed data fusion mechanism.This mechanism dynamically chooses the optimal sensor nodes and schedules the fusion process with several measures of energy consumption and information utility.Finally,an indoor target tracking experiment is illustrated,and then tracking performance,execution time and energy consumption of progressive distributed data fusion based CSP are compared with centralized data fusion based CSP.Experimental results demonstrate that the distributed multi-view tracking system using progressive distributed data fusion based CSP in DWSNs can track the 3-D positions of targets quickly and accurately,and decrease the congestion,energy consumption and time latency in communication.