A Spatio-Temporal Representation Scheme for Content- and Semantic-Based Video Retrieval on Moving Objects’ Trajectories

Abstract

In this paper, we propose a new spatio-temporal representation scheme which can effectively model moving objects’ trajectories in video data and propose a new signature-based access method which can support efficient retrieval on the user query based on the moving objects’ trajectories. The proposed spatio-temporal representation scheme supports content-based retrieval based on moving objects’ trajectories and supports semantics-based retrieval based on concepts which are acquired through the location information of moving objects. Compared with the sequential search, our signature-based access method can improve retrieval performance by reducing the significant number of disk accesses since it can access only candidate signatures by doing filtering through the signature file. Finally, we show from our experimental result that our scheme is superior to the Li’s scheme and the Shan’s one in terms of both retrieval effectiveness and efficiency.