This paper presents a novel framework for video management called Video Enrichment. It is based on the description of objects that are extracted from the video image sequences and allows a semantical interpretation of the video contents, that is important to solve the problems inherent to content retrieval. The proposed technologies extract the objects by segmenting regions of the images, analyze the behavior of the objects and generate descriptions based on that behavior. Descriptions obtained through this analysis of the image sequences are stored using keywords and a pre-defined syntax based on a priori knowledge of a given domain. They can be searched and query results can be shown not only by retrieving the original sequence, but also by displaying a view from a different perspective, with the movements of the objects summarized for a short interval. This enhanced visualization makes possible for the user to explore new interests. In this way, the Video Enrichment framework provides tools for video management by repeatedly querying, searching, viewing and refining images sequences in the video database.
By: Tomio Echigo, Masato Kurokawa, Alberto Tomita, Hisashi Miyamori, and Shun-ichi Iisaku
Published in: RT0338 in 2002
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .