A VIDEO RETRIEVAL AND SEQUENCING SYSTEM

Video is an effective medium for capturing the events in the real worl d around us, and a vast amount of video materials exists, covering a w ide range of applications. However, widespread use of video in compute r applications is often impeded by the lack of effective tools to mana ge video information systematically. This article discusses the design and implementation of a frame-based video retrieval and sequencing sy stem (VRSS). The system is designed to support the entire process of v ideo information management: segmenting, indexing, retrieving, and seq uencing of Video data. A semiautomatic tool is developed to divide vid eo sequences into meaningful shots. Each video shot is logged using te xt descriptions, audio dialogue, and cinematic attributes. A two-layer ed, concept-based model is used as the basis for accurately retrieving relevant video shots based on users' free-text queries. A cinematic, rule-based, virtual editing tool is also developed to sequence the vid eo shots retrieved for presentation within a specified time constraint . The system has been tested on a video documentary on the NUS (Nation al University of Singapore) engineering faculty. The results of video retrieval experiments are encouraging.