7 A MULTI-MODEL FRAMEWORK FOR VIDEO INFORMATION SYSTEMS Uma Srinivasan, Craig Lindley, and Bill Simpson-Young CSIRO Mathematical and Information Sciences North Ryde, NSW, Australia Abstract : In order to develop Video Information Systems (VIS) such as digital video libraries, video-on-demand systems and video synthesis applications, we need to understand the semantics of video data, and have appropriate schemes to store, retrieve and present this data. In this paper, we have presented an integrated multi- model framework for designing VIS application that accommodates semantic representation and supports a variety of forms of content-based retrieval. The framework includes a functional component to represent video and audio analysis functions, a hypermedia component for video delivery and presentation and a data management component to manage multi-modal queries for continuous media A metamodel is described for representing video semantic at severallevelss. Finally we have described a case study - the FRAMES project - which utilises the multimodel framework to develop specific VIS applications. 7.1 INTRODUCTION Video information systems (VIS) such as digital video libraries, video-on- demand systems, and video synthesis applications introduce new challenges in the management of large collections of digital video and audio data with associated texts, images, and other objects. In order to manage digital videos, we need to understand the semantics of video data, and have appropriate schemes to store, retrieve and present it. Researchers have studied video data hum different perspectives. The pattern recognition community has largely concentrated on image data in video and has come up with algorithms that can detect patterns in the data at the visual level (Aigrain et ai, 1996). The database community has focussed on logical structures that facilitate indexing of video sequences for retrieval purposes. In order to manage large 85