On the advantages of the use of bitstream extraction for video summary generation

  • Authors:
  • Luis Herranz;José M. Martínez

  • Affiliations:
  • Video Processing and Understanding Lab, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Madrid, Spain;Video Processing and Understanding Lab, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Madrid, Spain

  • Venue:
  • MMM'10 Proceedings of the 16th international conference on Advances in Multimedia Modeling
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Video summaries are compact representations used in search and video retrieval. As content itself, summaries are stored and distributed using a suitable video coding format, such as H.264/AVC. The generation of the bitstream of the summary usually consist of the decoding of the input bitstream and the encoding of the selected frames (i.e. transcoding). This approach can be computationally very demanding and unsuitable if the summary must be generated on demand with low delay. This paper analyzes the advantages of an alternative approach using bitstream extraction instead of transcoding. Experimental results show that the bitstream can be generated much faster than with transcoding and without any loss of quality.