Retrieving k-Nearest Neighboring Trajectories by a Set of Point Locations
- Cite this paper as:
- Tang LA., Zheng Y., Xie X., Yuan J., Yu X., Han J. (2011) Retrieving k-Nearest Neighboring Trajectories by a Set of Point Locations. In: Pfoser D. et al. (eds) Advances in Spatial and Temporal Databases. SSTD 2011. Lecture Notes in Computer Science, vol 6849. Springer, Berlin, Heidelberg
The advance of object tracking technologies leads to huge volumes of spatio-temporal data accumulated in the form of location trajectories. Such data bring us new opportunities and challenges in efficient trajectory retrieval. In this paper, we study a new type of query that finds the kNearestNeighboringTrajectories (k-NNT) with the minimum aggregated distance to a set of query points. Such queries, though have a broad range of applications like trip planning and moving object study, cannot be handled by traditional k-NN query processing techniques that only find the neighboring points of an object. To facilitate scalable, flexible and effective query execution, we propose a k-NN trajectory retrieval algorithm using a candidate-generation-and-verification strategy. The algorithm utilizes a data structure called globalheap to retrieve candidate trajectories near each individual query point. Then, at the verification step, it refines these trajectory candidates by a lower-bound computed based on the global heap. The global heap guarantees the candidate’s completeness (i.e., all the k-NNTs are included), and reduces the computational overhead of candidate verification. In addition, we propose a qualifierexpectation measure that ranks partial-matching candidate trajectories to accelerate query processing in the cases of non-uniform trajectory distributions or outlier query locations. Extensive experiments on both real and synthetic trajectory datasets demonstrate the feasibility and effectiveness of proposed methods.
Unable to display preview. Download preview PDF.