• DocumentCode
    1838519
  • Title

    Multi-core Video Analytics Engine (MVE) for security and surveillance applications

  • Author

    Rekeczky, C. ; Zarandy, A. ; Foldesy, P.

  • Author_Institution
    Eutecus Inc., Berkeley, CA, USA
  • fYear
    2010
  • fDate
    3-5 Feb. 2010
  • Firstpage
    1
  • Lastpage
    1
  • Abstract
    The Multi-core Video Analytics Engine (MVE??) is an easily configurable, compact, high-performance processing architecture that can be used to implement complete video analytics solutions in a single FPGA embedded in intelligent surveillance cameras. With the steadily growing demand for increased processing power at lower costs for video analytics systems, especially intelligent cameras with embedded Digital Signal Processors (DSPs), traditional -software-only approaches are breaking down under the heavy burden of sheer computational complexity. MVE addresses this problem right at the heart, combining an inherently parallel multi-core processing architecture with embedded complex video analytics algorithms in a configurable SoC (System-on-Chip) solution. This initial commercial implementation of MVE is on the Xilinx Spartan-3A DSP 3400A FPGA chip. MVE is based on Eutecus´ Cellular Multi-core Video Analytics (C-MVA??) processor - containing specialized image processing IP cores - which has been developed based on substantial research into cellular architectures that mimics the processing found in human vision. The performance of the MVE?? will be demonstrated in both indoor and outdoor security and surveillance applications.
  • Keywords
    field programmable gate arrays; image sensors; multiprocessing systems; parallel architectures; system-on-chip; video signal processing; video surveillance; Eutecus cellular multicore video analytics processor; FPGA; MVE; Xilinx Spartan-3A DSP 3400A FPGA chip; computational complexity; configurable SoC; embedded complex video analytics algorithms; embedded digital signal processors; human vision; image processing; indoor security; intelligent surveillance cameras; multicore video analytics engine; outdoor security; parallel multicore processing architecture; system-on-chip; Computational intelligence; Costs; Digital cameras; Engines; Field programmable gate arrays; Intelligent systems; Security; Signal analysis; Smart cameras; Surveillance;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cellular Nanoscale Networks and Their Applications (CNNA), 2010 12th International Workshop on
  • Conference_Location
    Berkeley, CA
  • Print_ISBN
    978-1-4244-6679-5
  • Type

    conf

  • DOI
    10.1109/CNNA.2010.5430331
  • Filename
    5430331