基于数据挖掘的交通监控信息融合技术研究

Research on traffic monitoring information fusion technology based on data mining

为了降低交通监控系统中单一传感器的误报率和漏报率,提出基于数据挖掘的交通监控信息融合技术。在监控环境中安装并配准视觉交通监控设备,通过对交通监控系统的视频摄像等多视角传感器的数据挖掘与集成,提取监控目标的信息特征。以提取的特征结果为基础,通过目标匹配及相同目标数据融合两个步骤得出交通监控的信息融合结果。经过对比实验得出结论:与传统信息融合技术相比,将设计的交通监控信息融合技术应用到监控系统中有效地降低了误报率和漏报率。

A traffic monitoring information fusion technology based on data mining is proposed to reduce the false alarm rate and missing alarm rate of the single sensor in the traffic monitoring system.The visual traffic monitoring equipment is installed and registered in the monitoring environment,and then the information features of monitored targets are extracted by data mining and integration of the multi⁃perspective sensors like video and camera shooting in the traffic monitoring system.On the basis of the extracted feature results,the information fusion results of traffic monitoring are obtained by the two steps of target matching and data fusion of the same targets.It can be concluded from the contrastive experiments that the application of the proposed traffic monitoring information fusion technology to the monitoring system can effectively reduce the false alarm rate and missing alarm rate in comparison with the traditional information fusion technology.