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

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.

Authors and Affiliations

1. Dept. of Computer Engineering, Research Center of Industrial Technology, Engineering Research Institute, Chonbuk National University, Chonju, Chonbuk, 561-756, South Korea

   Choon-Bo Shim & Jae-Woo Chang

Editors and Affiliations

1. Information School, Renmin University of China, Beijing, 100872, China

   Xiaofeng Meng

2. Department of Computer Science, University of California, Santa Barbara, CA, 93106-5110, USA

   Jianwen Su  & Yujun Wang  & 

Reprints and permissions

© 2002 Springer-Verlag Berlin Heidelberg

Policies and ethics