Lessons learned from building a terabyte digital video library

The Informedia Project at Carnegie Mellon University has created a terabyte digital video library in which automatically derived descriptors for the video are used for indexing, segmenting and accessing the library contents. Begun in 1994, the project presented numerous challenges for library creation and deployment, valuable information covered in this article. The authors, developers of the project at Carnegie Mellon University, addressed these challenges by: automatically extracting information from digitized video; creating interfaces that allowed users to search for and retrieve videos based on extracted information; and validating the system through user testbeds. Through speech, image, and natural language processing, the Informedia Project has demonstrated that previously inaccessible data can be derived automatically and used to describe and index video segments.