Metrics for shot boundary detection in digital video sequences

  • Authors:
  • Ralph M. Ford;Craig Robson;Daniel Temple;Michael Gerlach

  • Affiliations:
  • Pennsylvania State Univ., Erie;Pennsylvania State Univ., Erie;Pennsylvania State Univ., Erie;Pennsylvania State Univ., Erie

  • Venue:
  • Multimedia Systems
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

The detection of shot boundaries in video sequences is an important task for generating indexed videodatabases. This paper provides a comprehensive quantitative comparison of the metrics that have been applied toshot boundary detection. In addition, several standardizedstatistical tests that have not been applied to this problem,as well as three new metrics, are considered. A mathematicalframework for quantitatively comparing metrics is supplied.Experimental results based on a video database containing39,000 frames are included.