ShotWeave: A shot clustering technique for story browsing for large video databases
Date
2001
Authors
Zhou, Junyu
Major Professor
Advisor
Tavanapong, Wallapak
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Automatic video segmentation is the first and necessary step for organizing a long video file into several smaller units for subsequent browsing and retrieval. The smallest basic unit is shot--a contiguous sequence of frames recorded from a single camera operation. Since users of a video database management system are more likely to recall important events or stories rather than a particular frame or shot, relevant shots are typically grouped into a high-level unit called scene that is more meaningful to viewers. This thesis presents ShotWeave, a novel technique for clustering relevant shots into a scene for narrative films. Each scene is part of a story. Browsing through these scenes unfolds the entire story of the film, allowing the users to locate their desire video segments quickly and efficiently. The crux of ShotWeave is the use of similarity measures of carefully selected regions of representative frames of shots in the clustering process. These regions capture essential information needed to maintain viewers' thought in presence of shot breaks as intended by common continuity-editing techniques used in film literature. The experimental results show that ShotWeave performs well, and is more robust than two recent shot clustering techniques on full-length films consisting of a wide range of camera motions and a complex composition of related shots.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
thesis