Similarity Search Algorithm for Efficient Sub-trajectory Matching in Moving Databases

Similarity measure scheme on moving objects has become a topic of increasing in the area of moving databases. In this paper, we propose a new similarity search algorithm for efficient sub-trajectory matching. For measuring similarity between two sub-trajectories, we propose a new v(variable)-warping distance algorithm which enhances the existing time warping distance algorithm by permitting up to v replications for an arbitrary motion of a query trajectory. Our v-warping distance algorithm provides an approximate matching between two trajectories as well as an exact matching between them. Based on our vwarping distance algorithm, we also present a similarity measure scheme for the single trajectory in moving databases. Finally, we show that our scheme based on the v-warping distance achieves much better performance than other conventional schemes, such as Li's one (no-warping) and Shan's one (infinitewarping) in terms of precision and recall measures.