Proceedings chapter
Open access

Video segmentation and camera motion characterization using compressed data

Published inMultimedia Storage and Archiving Systems II, Editors C.-C. J. Kuo and Shih Fu Chang and Venkat N. Gudivada
Presented at Dallas TX
  • SPIE Proceedings; 3229
Publication date1997

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.

  • Dvp, cbir
  • Shot detection
  • Camera motion
  • Video archival
  • Content-based retrievnal
  • Bayesian classification
  • MPEG
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. Dallas TX. [s.l.] : [s.n.], 1997. (SPIE Proceedings)
Main files (1)
Proceedings chapter (Published version)
  • PID : unige:47833

Technical informations

Creation06/03/2015 17:12:17
First validation06/03/2015 17:12:17
Update time14/03/2023 22:59:24
Status update14/03/2023 22:59:23
Last indexation29/08/2023 15:12:35
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack