【作者】 李治江； 於志文； 王辉； 耿会东；

【Author】 Zhijiang Li + , Zhiwen Yu, Hui Wang, Huidong Geng School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China

【机构】 西北工业大学计算机学院；

【摘要】 现有GPS轨迹分析主要面向个人活动情况分析、基于历史轨迹的朋友推荐与位置推荐,对于用户群体特征的分析很少涉及。本文完成了个人轨迹建模、群体轨迹分析与基于网络地图服务的可视化,并且提出了针对GPS设备在较小尺度下数据误差较大的数据过滤方法。通过在此基础上采集校园数据,实现了校园人流位置查询的原型系统Campus Stream Visualization,提供了个人轨迹分析、群体轨迹可视化、位置人流监测的功能。更多还原

【Abstract】 The existing research for GPS trajectories is mainly focused on activity classification, friends and locations recommendation based on individual location history. However, so far, investigation on group features is rarely involved. This paper’s work includes individual trajectories modeling, group features investigation and data visualization based on web map. It also proposes a method of GPS data filtering in small-scale areas. With these methods and GPS data collected in campus, a prototype system named "Campus Stream Visualization" is developed to visualize pedestrian stream and location flow. It provides individual trajectories analysis, group trajectories visualization and location flow monitoring.更多还原