Amit Chakraborty

Authoring and viewing video documents using an SGML structure

In recent years, videos have become immensely popular. They are being generated at an enormous rate everyday. To be able to use this information in a meaningful way in conjunction with all the other media types, i.e. text, images, audio, etc., it is important to segment and structure the video and to create appropriate links between objects in different sections of a video and pertinent information in other media forms. This enables the users to view relevant information from a video sequence regarding a particular object within the context of a much larger multimedia document. We describe a novel system for structuring video based on their content and creating and navigating links between objects of interest in the video and related information elsewhere.

Video structuring for multimedia applications

In recent years, videos have become immensely popular. They are being generated at an enormous rate everyday by a variety of sources such as defense/civilian satellites, scientific experiments, biomedical imaging, industrial inspections, home entertainment systems, etc. This large amount of video data makes it a tedious and hard job to browse and annotate them by just fast forward and rewind. Organizing this information into well structured databases is of crucial importance in order to be able to use these videos in a meaningful way. The user can then readily retrieve those sections of the video that he/she is interested in without having to go through all the videos involved. In this paper we use an integrated method that uses several metrics computed from the video frames, which includes interframe difference, histogram difference between frames and the time derivative of the intensity variance, and then use probabilistic reasoning to break the video into shots. Our novel method works very well for videos with a mixture of abrupt and gradual scene changes.