[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1109/AHS.2007.103guideproceedingsArticle/Chapter ViewAbstractPublication PagesConference Proceedingsacm-pubtype
Article

Systolic Array Based Architecture for Variable Block-Size Motion Estimation

Published: 05 August 2007 Publication History

Abstract

A new Systolic Array based architecture is introduced for Variable block-size motion estimation (VBSME). This comprises a 2D array structure for SAD value computation combined with a parallel adder tree and a SAD comparator unit. Parallel raster scan is applied leading to high processor utilization. The exhibits much simpler control and lower hardware cost compared with previous circuits and can handle flexible search ranges without any increase in silicon area. Resulting computational rates are suitable for high end video processing applications. This architecture can also be simply configured as other video compression standards usage. Silicon design studies, based on a 0.13 m CMOS technology, indicate that circuits based on this approach are suitable for SDTV applications with search ranges of up to 32~32 and for HDTV applications with a search range of at least 16~16, with increased ranges achievable using lower dimension technologies.

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings
AHS '07: Proceedings of the Second NASA/ESA Conference on Adaptive Hardware and Systems
August 2007
736 pages
ISBN:076952866X

Publisher

IEEE Computer Society

United States

Publication History

Published: 05 August 2007

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 0
    Total Downloads
  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 01 Jan 2025

Other Metrics

Citations

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media