Bandwidth-constrained motion estimation for real-time mobile video application

Jui Hung Hsieh*, Tian-Sheuan Chang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper addresses the memory bandwidth problem of motion estimation in resource limited mobile video applications by an integrated bandwidth rate distortion optimization framework. The simulation result shows up to 86% bandwidth saving while keeps equivalent rate-distortion (R-D) performance and meets real time target compared with H.264 reference software for low motion CIF size video. For high motion sequence, the result shows our algorithm could better allocate the available bandwidth for high motion macroblock without violating the real time constraint when search range is set to 16.

Original languageEnglish
Title of host publication17th DSP 2011 International Conference on Digital Signal Processing, Proceedings
DOIs
StatePublished - 29 Sep 2011
Event17th International Conference on Digital Signal Processing, DSP 2011 - Corfu, Greece
Duration: 6 Jul 20118 Jul 2011

Publication series

Name17th DSP 2011 International Conference on Digital Signal Processing, Proceedings

Conference

Conference17th International Conference on Digital Signal Processing, DSP 2011
CountryGreece
CityCorfu
Period6/07/118/07/11

Keywords

  • H.264/AVC
  • Memory bandwidth
  • Motion estimation
  • Video coding

Fingerprint Dive into the research topics of 'Bandwidth-constrained motion estimation for real-time mobile video application'. Together they form a unique fingerprint.

Cite this