PROJECT TITLE :

Searching Trajectories by Regions of Interest - 2017

ABSTRACT:

With the increasing availability of moving-object tracking knowledge, trajectory search is increasingly necessary. We have a tendency to propose and investigate a novel question type named trajectory search by regions of interest (TSR question). Given an argument set of trajectories, a TSR query takes a group of regions of interest as a parameter and returns the trajectory in the argument set with the best spatial-density correlation to the question regions. This sort of query is useful in many in style applications such as trip coming up with and recommendation, and site based mostly services in general. TSR query processing faces 3 challenges: how to model the spatial-density correlation between question regions and data trajectories, the way to effectively prune the search area, and how to effectively schedule multiple thus-referred to as question sources. To tackle these challenges, a series of latest metrics are defined to model spatial-density correlations. An efficient trajectory search algorithm is developed that exploits higher and lower bounds to prune the search space and that adopts a query-source choice strategy, as well as integrates a heuristic search strategy primarily based on priority ranking to schedule multiple question sources. The performance of TSR query processing is studied in in depth experiments based mostly on real and synthetic spatial information.