面向地理信息大数据的时空事件关系可视化分析框架

Visualized analysis framework on big geo-information data oriented spatio-temporal events

不同类型的地理信息大数据蕴含了丰富的时空关系,反映个体或者群体时空事件之间的变化模式,在资源、环境、交通等领域的智慧应用中起到关键性作用。然而,地理信息大数据拥有的多尺度和多语义特性,在挖掘地理信息大数据的时空关系时会存在许多困难。如何有效地构建多尺度多语义时空关系,并直观地表达这些时空关系是一个重大挑战。本文设计了一种时空事件关系可视化分析框架,通过定义事件间时空关系的描述,设计了一种多视图协同的可视化分析方法,结合时空关系的可视化协同交互,实现地理信息大数据时空事件可视分析。基于时空轨迹数据,通过试验说明该方法可以探寻时空事件及背景间的时空关系,实现时空事件的交互可视分析。

Rich spatio-temporal relations are hidden in types of big geo-data,which represent the evolution of individual or collective spatio-temporal events and play a decisive role in intelligent applications such as natural resources,environments,transportation and other fields.However,there are many difficulties in digging the spatio-temporal relationship,due to the large number of attributes embedded in multi-scale and multi-semantic big geo-data.It is a technical challenge to effectively construct multi-scale and multi semantic spatio-temporal and as well as to visualize the relations.In this paper,we design an analysis framework to visualize the spatiotemporal relations among spatio-temporal events.we design a multi-view collaboration to visualize the spatio-temporal relations among events by describing a general definition for spatio-temporal relations in spatio-temporal events.A visual interface is presented for users to interactively select or filter spatial and temporal extents to guide the knowledge discovery process.Followed by experimental application on spatio-temporal trajectory data shows that this method can explore the spatio-temporal relationship between spatiotemporal events and context,and realize the interactive visual analysis of spatio-temporal events.