Energy-Efficient Architectures for Multiview Video Coding

  • Bruno Zatt
  • Muhammad Shafique
  • Sergio Bampi
  • Jörg Henkel
Chapter

Abstract

Although the fast ME/DE provides significant complexity reduction, a high-throughput hardware architecture is required for real-time ME/DE in MVC. Without a dedicated hardware, ME/DE for MVC in real-time mobile application is unfeasible. Therefore, in addition to our fast ME/DE algorithm we propose a novel motion and disparity estimation hardware architecture designed to provide real-time MVC encoding for up to four views HD1080p (1920 × 1080) based on the proposed fast ME/DE algorithm. Firstly, we are going to start presenting a high-level architectural template description. The architectural template, presented in Sect. 5.1, will give the required basis for a better understanding of the proposed architecture.

Keywords

Dispatch 

References

  1. Chen C-Y et al (2006) Level C+ data reuse scheme for motion estimation with corresponding coding orders. IEEE Trans Circuits Syst Video Technol 16:553–558CrossRefGoogle Scholar
  2. Chen T-C et al (2007a) Fast algorithm and architecture design of low-power integer motion estimation for H.264/AVC. IEEE Trans Circuits Syst Video Technol 17:568–577CrossRefGoogle Scholar
  3. Chen T-C et al (2007b) Fast algorithm and architecture design of low-power integer motion estimation for H.264/AVC. [s.l.]. IEEE Trans Circuits Syst Video Technol 17: 568–577CrossRefGoogle Scholar
  4. Ding L-F et al (2010a) A 212 MPixels/s 4096 2160p multiview video encoder chip for 3D/Quad full HDTV applications. IEEE J Solid-State Circuits 45:46–58CrossRefGoogle Scholar
  5. Ghanbari M (1990) The cross-search algorithm for motion estimation. IEEE Trans Commun 38:950–953CrossRefGoogle Scholar
  6. JVT (2009a) JMVC 6.0 [garcon.ient.rwthaachen.de]Google Scholar
  7. Marlow S, Ng J, McArdle C (1997) Efficient motion estimation using multiple log searching and adaptive search windows. In: International conference on image processing and its applications, pp 214–218Google Scholar
  8. Saponara S, Fanucci L (2004a) Data-adaptive motion estimation algorithm and VLSI architecture design for low-power video systems. IEE Comput Digit Tech 151:51–59CrossRefGoogle Scholar
  9. Tsai C-Y et al (2007) Low power cache algorithm and architecture design for fast motion estimation in H.264/AVC encoder system. In: International conference on acoustics speech and signal processing (ICASSP), pp II-97–II-100Google Scholar
  10. Tsung P-K et al (2009) Cache-based integer motion/disparity estimation for quad-HD H.264/AVC and HD multiview video coding. In: International conference on acoustics, speech and signal processing, IEEE, Taipei, pp 2013–2016Google Scholar
  11. Yang J (2009) Multiview video coding based on rectified epipolar lines. In: International conference on information, communication and signal processing, pp 1–5Google Scholar
  12. Zatt B et al (2011c) Multi-level pipelined parallel hardware architecture for high throughput motion and disparity estimation in multiview video coding. In: IEEE/ACM 14th design automation and test in europe conference (DATE’11), vol 14, pp 1448–1453Google Scholar
  13. Zatt B et al (2011d) Run-time adaptive energy-aware motion and disparity estimation in multiview video coding. In: ACM/IEEE/EDA 48th design automation conference (DAC’11), pp 1026–1031Google Scholar
  14. Zhang K et al (2005) SRAM design on 65-nm CMOS technology with dynamic sleep transistor for leakage reduction. IEEE J Solid-State Circuits: 895–901Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Bruno Zatt
    • 1
    • 2
  • Muhammad Shafique
    • 3
  • Sergio Bampi
    • 2
  • Jörg Henkel
    • 1
  1. 1.Department of Computer ScienceKarlsruhe Institute of TechnologyKarlsruheGermany
  2. 2.Institute of Informatics Federal University of Rio Grande do Sul (UFRGS)Porto AlegreBrazil
  3. 3.Karlsruhe Institute of TechnologyKarlsruheGermany

Personalised recommendations