Skip to main navigation Skip to search Skip to main content

Video trails: Representing and visualizing structure in video sequences

  • University of Maryland, College Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The problem of determining the physical and semantic structure of an extended video sequence is essential for providing appropriate processing, indexing and retrieval capabilities for video databases. In this paper, we describe a novel technique which reduces a sequence of MPEG encoded video frames to a trail of points in a low dimensional space. In the space, we can cluster frames, analyze transitions between clusters and compute properties of the resulting trail. By classifying portions of the trail as either stationary or transitional, we are able to detect gradual edits between shots. Furthermore, tracking the interaction of clusters over time, we lay the groundwork for the complete analysis and representation of the video's physical and semantic structure.

Original languageEnglish
Title of host publicationProceedings of the 5th ACM International Conference on Multimedia, MULTIMEDIA 1997
PublisherAssociation for Computing Machinery, Inc
Pages335-346
Number of pages12
ISBN (Electronic)0897919912, 9780897919913
DOIs
StatePublished - Nov 1 1997
Event5th ACM International Conference on Multimedia, MULTIMEDIA 1997 - Seattle, United States
Duration: Nov 9 1997Nov 13 1997

Publication series

NameProceedings of the 5th ACM International Conference on Multimedia, MULTIMEDIA 1997

Conference

Conference5th ACM International Conference on Multimedia, MULTIMEDIA 1997
Country/TerritoryUnited States
CitySeattle
Period11/9/9711/13/97

Fingerprint

Dive into the research topics of 'Video trails: Representing and visualizing structure in video sequences'. Together they form a unique fingerprint.

Cite this