Computer Laboratory

Technical reports

Video-augmented environments

James Quentin Stafford-Fraser

April 1997, 91 pages

This technical report is based on a dissertation submitted February 1996 by the author for the degree of Doctor of Philosophy to the University of Cambridge, Gonville & Caius College.


In the future, the computer will be thought of more as an assistant than as a tool, and users will increasingly expect machines to make decisions on their behalf. As with a human assistant, a machine’s ability to make informed choices will often depend on the extent of its knowledge of activities in the world around it. Equipping personal computers with a large number of sensors for monitoring their environment is, however, expensive and inconvenient, and a preferable solution would involve a small number of input devices with a broad scope of application. Video cameras are ideally suited to many realworld monitoring applications for this reason. In addition, recent reductions in the manufacturing costs of simple cameras will soon make their widespread deployment in the home and office economically viable. The use of video as an input device also allows the creation of new types of user-interface, more suitable in some circumstances than those afforded by the conventional keyboard and mouse.

This thesis examines some examples of these ‘Video-Augmented Environments’ and related work, and then describes two applications in detail. The first, a ‘software cameraman’, uses the analysis of one video stream to control the display of another. The second, ‘BrightBoard’, allows a user to control a computer by making marks on a conventional whiteboard, thus ‘augmenting’ the board with many of the facilities common to electronic documents, including the ability to fax, save, print and email the image of the board. The techniques which were found to be useful in the construction of these applications are common to many systems which monitor real-world video, and so they were combined in a toolkit called ‘Vicar’. This provides an architecture for ‘video plumbing’, which allows standard videoprocessing components to be connected together under the control of a scripting language. It is a single application which can be programmed to create a variety of simple Video-Augmented Environments, such as those described above, without the need for any recompilation, and so should simplify the construction of such applications in the future. Finally, opportunities for further exploration on this theme are discussed.

Full text

PDF (2.4 MB)

BibTeX record

  author =	 {Stafford-Fraser, James Quentin},
  title = 	 {{Video-augmented environments}},
  year = 	 1997,
  month = 	 apr,
  url = 	 {},
  institution =  {University of Cambridge, Computer Laboratory},
  number = 	 {UCAM-CL-TR-419}