Video Navigator automates video archiving and retrieval
Much of the broadcasting and multimedia content is based on archived film and video material. Searching for the most striking video sequence, is both difficult and time consuming, and is greatly dependent on the archiving of material. Project VICAR (Video Indexing, Classification, Indexing and Retrieval) developed a software tool, Video Navigator, which partly automates the annotation work, currently performed manually. Each single shot of the video is analyzed, and representative frames are assigned a composite index containing information on color, brightness, camera movement, etc. Beyond that, the frames are classified into user-specific classes, such as VIPs, settings and objects. The user retains full control of the process and can modify or complement an annotation at any time. The archived material can be searched with queries based on text, or on a visual example, using either still or moving images. The sample image is indexed and classified and the archive is scanned for shots with matching characteristics. The results are displayed on-screen and are readily available for a new montage, or even a refined search. The novel indexing concept makes it easy to locate and retrieve videos. The Video Navigator software was mainly developed to improve the level of automation in the professional video archive market, providing a comprehensive set of video indexing and searching tools. Nevertheless, its application is not restricted to massive archives. It can also be used to organize smaller archives, or even by individuals to structure their own video footage. Useful links: http://www.nb.no/fiat/2000-01/vicar2000.html
