自适应采样间隔的无线传感器网络多目标跟踪算法

发布时间：2019-05-11 20:17

【摘要】：多目标跟踪是无线传感器网络当前研究的热点问题。针对多目标跟踪存在耗能较大,跟踪丢失等问题,提出了一种自适应采样间隔的多目标跟踪算法。采用跟踪目标的定位元数据来对目标的运动模式进行建模。基于扩展的卡尔曼滤波器来预测跟踪目标状态,采用预测目标定位的概率密度函数构建跟踪簇。通过定义跟踪目标中心,基于马氏距离来量化主节点MN的选举过程。通过跟踪目标重要性和其与MN之间的距离来量化目标的影响强度,并以此构建自适应采样间隔的多目标跟踪算法。基于MATLAB进行了仿真实验,实验结果显示,本文设计的跟踪算法能准确预测目标的运动轨迹,能随着运动目标的状态实时采用自适应的采样间隔。通过数据分析得知,本文提出的算法能在实现WSN网络节能的基础上提高跟踪精度。
[Abstract]:Multi-target tracking is a hot issue in wireless sensor networks. In order to solve the problems of high energy consumption and tracking loss in multi-target tracking, an adaptive sampling interval multi-target tracking algorithm is proposed. The positioning metadata of tracking target is used to model the motion mode of the target. Based on the extended Kalman filter to predict the state of the tracking target, the probability density function of predicting the target location is used to construct the tracking cluster. By defining the tracking target center, the election process of the main node MN is quantified based on Mahalanobis distance. The influence intensity of the target is quantified by tracking the importance of the target and the distance between it and MN, and a multi-target tracking algorithm with adaptive sampling interval is constructed. The simulation results based on MATLAB show that the tracking algorithm designed in this paper can accurately predict the trajectory of the target and can adopt adaptive sampling interval in real time with the state of the moving target. Through data analysis, it is found that the algorithm proposed in this paper can improve the tracking accuracy on the basis of energy saving of WSN network.
【作者单位】：河南科技学院信息工程学院;武汉理工大学信息工程学院;
【基金】：国家自然科学基金资助项目(31371525) 河南省教育厅科学技术研究重点资助项目(14A520067) 河南省教育厅人文社会科学研究资助项目(2014-gh-245) 河南省信息技术教育研究重点资助项目(ITE12037) 2014年度新乡市科技发展计划资助项目(14GY23) 2014年度河南科技学院教育教学改革研究重点资助项目(2014PUZD08)
【分类号】：TP212.9;TN929.5

【参考文献】