Video rushes summarization by adaptive acceleration and stacking of shots

  • Authors:
  • Marcin Detyniecki;Christophe Marsala

  • Affiliations:
  • UPMC - CNRS - LIP6, Paris, France;UPMC - LIP6, Paris, France

  • Venue:
  • Proceedings of the international workshop on TRECVID video summarization
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

When witnessing the great increase of video data available, it becomes clear that summarization is one of the great challenges ahead. One particular problem is the summarization of video rushes. In this paper we present a straightforward approach that addresses this specific challenge. It combines two complementary actions: shot selection by stacking and adaptive acceleration of the playback. This simple approach provides excellent results, compared at TRECVid 2007. In particular, it offers easy to understand summaries that keep most of the original information, that meet the target compression rate, that have average scores of redundancy perception and that show playing times (by the judges) almost equal to the summaries duration.