Browse Prior Art Database

Multi-search of video segments indexed by time-aligned annotations of video content

IP.com Disclosure Number: IPCOM000013063D
Original Publication Date: 2000-Mar-01
Included in the Prior Art Database: 2003-Jun-12
Document File: 12 page(s) / 86K

Publishing Venue

IBM

Abstract

This paper describes an approach to the design and implementation of a video content man- agement system that enables the efficient indexing and storing, and searching and browsing of video segments defined by annotation of video content attributes. The annotation values rep- resent the durations of independently indexed and potentially overlapping attributes of the video content, such as camera motion, shot distance and face count, and associated informa- tion, such as spoken words in the soundtrack. These values define segments of video of any granularity from entire programs down to arbitrarily short segments. Boolean searches on these multiple indexed criteria can be performed, and temporal intervals corresponding to video segments can be computed that reflect the union and intersection of search results meeting these Boolean conditions. We propose a relational database-based model for storing indexed attributes which is flexible and because it does not index or store any fixed temporal segmentation of the video. Rather annotation values can be stored in any way appropriate for an open-ended set of annotation methods representing attributes of video content. The system is part of a project to exploit a set of automatic annotation methods for the visual attributes of video content, and to develop a component of a complete studio for broadcasting digital HDTV (High Definition Television). KEYWORDS :

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 10% of the total text.

Page 1 of 12

  Multi-search of video segments indexed by time-aligned annotations of video content

This paper describes an approach to the design and implementation of a video content man- agement system that enables the efficient indexing and storing, and searching and browsing of video segments defined by annotation of video content attributes. The annotation values rep- resent the durations of independently indexed and potentially overlapping attributes of the video content, such as camera motion, shot distance and face count, and associated informa- tion, such as spoken words in the soundtrack. These values define segments of video of any granularity from entire programs down to arbitrarily short segments. Boolean searches on these multiple indexed criteria can be performed, and temporal intervals corresponding to video segments can be computed that reflect the union and intersection of search results meeting these Boolean conditions. We propose a relational database-based model for storing indexed attributes which is flexible and because it does not index or store any fixed temporal

segmentation of the video. Rather annotation values can be stored in any way appropriate for an open-ended set of annotation methods representing attributes of video content. The system is part of a project to exploit a set of automatic annotation methods for the visual attributes of video content, and to develop a component of a complete studio for broadcasting digital

HDTV (High Definition Television).

KEYWORDS :

Media Content Management, Video Database, Query System

INTRODUCTION

Digital video asset management systems are becoming more pervasive as analog video tape archives are being converted to digital format, and new videos are produced in digital format. Key video management tasks are ingest, annotation or indexing, database modeling, search and browsing of stored content. Commercial systems are beginning to develop technological solutions for these video management tasks. A key challenge is annotation: developing search indices of descriptors for video content. Aguierre-Smith and Davenport put the challenge this way: "[The organization of a] video database system is a challenging information management problem because the way that a particular sequence of images is described effects Ýhow¨ a maker will retrieve it and incorporate it into a movie" Ý1¨.

However, the nature/type of metadata being stored is changing rapidly. Historically, "card catalog" metadata were associated with a video, such as title and production date. Such metadata attributes are descriptions of the video as a whole. Video asset management systems being developed in research projects and in some commercial systems (examples include ISLIP
[2], based on InforMedia research prototype Ý3¨ AVID Ý4¨, VIRAGE Ý5¨, EXCALIBUR Ý6¨ are beginning to go beyond limited sets of metadata attributes and index video content on a Video segment granularity (time unit) considerably less than traditional pr...