• DocumentCode
    2741950
  • Title

    Design and Optimization of H.264 Video Encoder on DSP Platform

  • Author

    Li Ke ; Jia Kebin ; Xie Jing ; Wang Yan

  • Author_Institution
    Beijing Univ. of Technol., Beijing
  • fYear
    2007
  • fDate
    5-7 Sept. 2007
  • Firstpage
    541
  • Lastpage
    541
  • Abstract
    With the rapid development of microprocessor, embedded multimedia products are gradually becoming the mainstream in the market. However, the high coding efficiency enabled by the H.264 video compression standard comes with substantially greater algorithmic complexity as compared to that of existing standards. And this additional complexity results in many difficulties in the implementation and optimization tasks. This paper firstly analyses the block size prediction algorithms of intra & inter frame, and then improves it through autocorrelation and combining sum of absolute difference (SAD) and analysis of texture difference respectively. The experimental results indicated that the new algorithms achieved significant improvement as compared to the original encoder. Finally, some optimization techniques about H.264 on TMS320DM642 DSP platform, which can effectively enhance the video coding speed, are proposed.
  • Keywords
    digital signal processing chips; optimisation; video coding; DSP; H.264 video encoder; TMS320DM642; autocorrelation; block size prediction algorithms; high coding efficiency; inter frame; intra frame; microprocessor; multimedia products; optimization techniques; sum of absolute difference; texture difference analysis; video compression standard; Algorithm design and analysis; Autocorrelation; Consumer electronics; Design optimization; Digital signal processing; Educational institutions; Histograms; ISO standards; Prediction algorithms; Video coding;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Innovative Computing, Information and Control, 2007. ICICIC '07. Second International Conference on
  • Conference_Location
    Kumamoto
  • Print_ISBN
    0-7695-2882-1
  • Type

    conf

  • DOI
    10.1109/ICICIC.2007.247
  • Filename
    4428183