Multi-scale window specification over streaming trajectories

Abstract

Enormous amounts of positional information are collected by monitoring applications in domains such as fleet management, cargo transport, wildlife protection, etc. With the advent of modern location-based services, processing such data mostly focuses on providing real-time response to a variety of user requests in continuous and scalable fashion. An important class of such queries concerns evolving trajectories that continuously trace the streaming locations of moving objects, like GPS-equipped vehicles, commodities with RFID's, people with smartphones etc. In this work, we propose an advanced windowing operator that enables online, incremental examination of recent motion paths at multiple resolutions for numerous point entities. When applied against incoming positions, this window can abstract trajectories at coarser representations towards the past, while retaining progressively finer features closer to the present. We explain the semantics of such multi-scale sliding windows through parameterized functions that reflect the sequential nature of trajectories and can effectively capture their spatiotemporal properties. Such window specification goes beyond its usual role for non-blocking processing of multiple concurrent queries. Actually, it can offer concrete subsequences from each trajectory, thus preserving continuity in time and contiguity in space along the respective segments. Further, we suggest language extensions in order to express characteristic spatiotemporal queries using windows. Finally, we discuss algorithms for nested maintenance of multi-scale windows and evaluate their efficiency against streaming positional data, offering empirical evidence of their benefits to online trajectory processing.