Automatic MPEG-4 sprite coding--Comparison of integrated object segmentation algorithms

  • Authors:
  • Alexander Glantz;Andreas Krutz;Thomas Sikora;Paulo Nunes;Fernando Pereira

  • Affiliations:
  • Technische Universität Berlin, Communication Systems Group, Berlin, Germany;Technische Universität Berlin, Communication Systems Group, Berlin, Germany;Technische Universität Berlin, Communication Systems Group, Berlin, Germany;Instituto Superior de Ciências do Trabalho e da Empresa, Instituto de Telecommunicações, Lisbon, Portugal;Instituto Superior Técnico, Instituto de Telecommunicações, Lisbon, Portugal

  • Venue:
  • Multimedia Tools and Applications
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Sprite coding, as standardized in MPEG-4 Visual, can result in superior performance compared to common hybrid video codecs. We consider sprite coding, which significantly increases the objective as well as the subjective quality of coded video content. The main challenge of this approach is the segmentation of the foreground objects in a preprocessing step. We evaluate automatic object segmentation methods based on global motion estimation and background sprite generation. The objects are coded using the MPEG-4 Visual Main Profile and compared with the Advanced Simple Profile.