A Graph-Based Visual Query Method for Massive Human Trajectory Data

Abstract

With the advance of location acquisition technologies nowadays, the human trajectory data, such as vehicles, phones and bicycles, is growing vastly and extending our imagination of new users. These trajectories have shown great values in supporting situation-aware exploration and prediction of human mobility, discovering movement patterns and monitoring the traffic situations. Query is an essential task for trajectory exploration. To do this, users should input spatial, temporal and other types of query conditionals to obtain a group of filtered trajectories. However, current visual query methods for urban data suffer from two main problems. First, it is a challenge for users without background knowledge to specify query conditions, such as selecting a popular entertainment area on the map as spatial condition. Second, there still needs a way to fuse the multi-source, heterogeneous, and large-scale urban data to partition the urban area, extract their semantic information, and provide intuitive, efficient trajectory queries. In this paper, we propose CBRG(cellular-based region growing) algorithm to make a preliminary region partition which tends to be a certain collection of similar regions. Then, we generate a semantic node for graph and provide a set of feasible clues and signs to explore and mine data from the aspects of spatio-temporal characteristics, inherent coupling of data, and human mobility. It is worth mentioning that our methodology is also universal for other heterogeneous data with spatio-temporal characteristics. INDEX TERMS Functional zones construction, human trajectory data, visual query, visual analysis.

Directional-Layered Space-Time Densities: A New Spatiotemporal Trajectory Aggregation and Geographic Visualization Approach

“…For small-scale movement data, the STP-based representation can be used directly in movement data visualization, from which we can obtain meaningful information [10], [11]. As mentioned above, with increasingly large movement datasets becoming available, this type of display can easily become cluttered and illegible, making it impossible to identify useful information from the map [12]. Therefore, certain forms of trajectory data generalization/aggregation are necessary for reliable pattern recognition [1], [13], [14].…”