• Home
  1. Home
  2. Video segmentation and camera motion characterization using compressed data
Proceedings chapter
OA Policy
English

Video segmentation and camera motion characterization using compressed data

Contributors

Milanese, Ruggero; Deguillaume, Frédéric; Jacot-Descombes, Alain

Presented at

Dallas TX

Published in

C.-C. J. Kuo and Shih Fu Chang and Venkat N. Gudivada (Ed.), Multimedia Storage and Archiving Systems II

Collection

  • SPIE Proceedings; 3229

Publication date

1997

Abstract

We address the problem of automatically extracting visual indexes from videos, in order to provide sophisticated access methods to the contents of a video server. We focus on two tasks, namely the decomposition of a video clip into uniform segments (shots) and the characterization of each shot by camera motion parameters. For the first task we use a Bayesian classification approach to detecting scene cuts by analyzing motion vectors. For the second task a least-squares fitting procedure determines the pan/tilt/zoom camera parameters. In order to guarantee the highest processing speed, all techniques process and analyze directly MPEG-1 motion vectors, without need for video decompression. Experimental results are reported for a database of news video clips.

Keywords

  • Dvp, cbir
  • Shot detection
  • Camera motion
  • Video archival
  • Content-based retrievnal
  • Bayesian classification
  • MPEG

UNIGE affiliation entities

UNIGE research groups

Citation (ISO format)

MILANESE, Ruggero, DEGUILLAUME, Frédéric, JACOT-DESCOMBES, Alain. Video segmentation and camera motion characterization using compressed data. In: Multimedia Storage and Archiving Systems II. C.-C. J. Kuo and Shih Fu Chang and Venkat N. Gudivada (Ed.). Dallas TX. [s.l.] : [s.n.], 1997. (SPIE Proceedings)

Main files (1)

Proceedings chapter (Published version)

Identifiers

  • PID : unige:47833

Additional URL for this publication

http://vision.unige.ch/publications/postscript/97/MilaneseDeguillaumeJacot-Descombes_msasII.ps.gz
550views
343downloads

Technical informations

Creation

06/03/2015 17:12:17

First validation

06/03/2015 17:12:17

Update

14/03/2023 22:59:24

Status update

14/03/2023 22:59:23

Last indexation

30/10/2024 23:21:35
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated