The COST292 experimental framework for rushes summarization task in TRECVID 2008

  • Authors:

  • S. U. Naci;Uros Damnjanovic;Boris Mansencal;Jenny Benois-Pineau;Christian Kaes;Marzia Corvaglia;Eliana Rossi;Naiara Aginako

  • Affiliations:

  • Delft University of Technology, Delft, Netherlands;Queen Mary University London, London, England, UK;LABRI UMR CNRS/University of Bordeaux, Talence, France;LABRI UMR CNRS/University of Bordeaux, Talence, France, France;LABRI UMR CNRS/University of Bordeaux, Talence, France;University of Brescia, Brescia, Italy;LABRI UMR CNRS/University of Bordeaux, Talence, France and University of Brescia, Italy;VicomTech, San Sebastian, Spain

  • Venue:
  • TVS '08 Proceedings of the 2nd ACM TRECVid Video Summarization Workshop
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, the method used for Rushes Summarization task by the COST 292 consortium is reported. The approach proposed this year differs significantly from the one proposed in the previous years because of the introduction of new processing steps, like repetition detection in scenes. The method starts with junk frames removal and follows with clustering and scene detection; then for each scene, repetitions are detected in order to extract once the real scene; the following step consists in face detections (faces are considered semantically relevant) and in pan, tilt and zoom detections (other camera motions are usually related to technical operations in the backstage); finally the summary is extracted.