抄録
This paper proposes a retrieval mechanism for a peta-byte video archive equipped with a large-scale, automatic, tape-feed robot. The mechanism has a multiple video digest display system with a user-friendly interface and a scene-detection-based index allowing users to efficiently access the detailed video information. An effective integrated system for managing different types of servers that are set up to maximize the performance of such a large-scale archive is also discussed. Our verification tests show the effectiveness and the feasibility of the proposed solution.
