• DocumentCode
    2920709
  • Title

    Hardware architecture for fast Intra mode and direction prediction in real-time MPEG-2 to H.264/AVC transcoder

  • Author

    Elarabi, Tarek A. ; Ayoubi, Randa ; Mahmoud, Hanan ; Bayoumi, Magdy

  • Author_Institution
    CACS, Univ. of Louisiana at Lafayette, Lafayette, LA, USA
  • fYear
    2012
  • fDate
    25-28 June 2012
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    In this article, we propose a hardware architecture for our fast Intra mode and direction prediction algorithm to accelerate the MPEG-2 to H.264/AVC transcoding devices. In order to eliminate the redundant operations in the transcoder, our implemented algorithm uses the DCT coefficients from the MPEG-2 decoder to predict the Intra mode and reconstruction direction for the H.264/AVC encoder. In addition, the Intra prediction process in the H.264/AVC part of the transcoder has been dramatically accelerated by using our full-search elimination technique. The empirical results show 92% reduction in the transcoding time while reducing the PSNR for less than 3.5%. The proposed architecture has achieved an operating frequency of 323MHz at a power consumption of 112 mW when implemented on Virtex-5 FPGA Development Board.
  • Keywords
    data compression; discrete cosine transforms; field programmable gate arrays; media streaming; power consumption; transcoding; video coding; DCT coefficients; H.264-AVC transcoding device; PSNR; Virtex-5 FPGA development board; direction prediction algorithm; fast Intra mode; frequency 323 MHz; full-search elimination technique; hardware architecture; power 112 mW; real-time MPEG-2 decoder; Computer architecture; Decoding; Discrete cosine transforms; Prediction algorithms; Streaming media; Transcoding; Transform coding; FPGA; H.264/AVC; Intra; MBEG-2; Transcoder; Video;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    World of Wireless, Mobile and Multimedia Networks (WoWMoM), 2012 IEEE International Symposium on a
  • Conference_Location
    San Francisco, CA
  • Print_ISBN
    978-1-4673-1238-7
  • Electronic_ISBN
    978-1-4673-1237-0
  • Type

    conf

  • DOI
    10.1109/WoWMoM.2012.6263798
  • Filename
    6263798