Design and analysis of Multi-Hypothesis Motion Compensated Prediction (MHMCP) codec for error resilient visual communications

Wei Ying Kung, Chang Su Kim, C. C.Jay Kuo

Research output: Contribution to journalConference articlepeer-review

Abstract

A multi-hypothesis motion compensated prediction (MHMCP) scheme, which predicts a block from a weighted superposition of more than one reference blocks in the frame buffer, is proposed and analyzed for error resilient visual communication in this research. By combining these reference blocks effectively, MHMCP can enhance the error resilient capability of compressed video as well as achieve a coding gain. In particular, we investigate the error propagation effect in the MHMCP coder and analyze the rate-distortion performance in terms of the hypothesis number and hypothesis coefficients. It is shown that MHMCP suppresses the short-term effect of error propagation more effectively than the intra refreshing scheme. Simulation results are given to confirm the analysis. Finally, several design principles for the MHMCP coder are derived based on the analytical and experimental results.

Original languageEnglish
Article number11
Pages (from-to)78-89
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume5600
DOIs
Publication statusPublished - 2004
Externally publishedYes
EventMultimedia Systems and Applications VII - Philadelphia, PA, United States
Duration: 2004 Oct 252004 Oct 27

Keywords

  • And error resilient video coding
  • Error propagation
  • MHMCP
  • Multi-hypothesis motion compensated prediction

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Design and analysis of Multi-Hypothesis Motion Compensated Prediction (MHMCP) codec for error resilient visual communications'. Together they form a unique fingerprint.

Cite this