Discrete wavelet transform on dynamically reconfigurable hardware.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

    44 Downloads (Pure)

    Abstract

    The increasing amount of data produced in satellites poses a problem for the limited data rate of its downlink. This discrepancy is solved by introducing more and more processing power on-board to compress data to a satisfiable rate. Currently, this processing power is often provided by custom-off-the-shelf hardware. These architectures introduce problems when they are scaled up. To deal with the ever increasing data rate of the newest sensors and still be within the same power and thermal constraints, new architectures are being examined. In this paper we will describe one of these new architectures, the Montium tile processor, and we show how a well-known algorithm, the CCSDS 9/7 integer discrete wavelet transform (DWT), can be mapped to this architecture. Furthermore, some improvements are discussed that can make the Montium and reconfigurable architectures in general, an even better platform to support algorithms like the DWT.
    Original languageUndefined
    Title of host publicationOn-Board Payload Data Compression Workshop 2008
    Place of PublicationNoordwijk
    PublisherESA conference bureau
    Pages-
    Number of pages6
    ISBN (Print)not assigned
    Publication statusPublished - 27 Jun 2008

    Publication series

    Name
    PublisherESA conference bureau
    Number2

    Keywords

    • METIS-254883
    • EWI-13198
    • IR-64914

    Cite this

    Walters, K. H. G., Smit, G. J. M., & Gerez, S. H. (2008). Discrete wavelet transform on dynamically reconfigurable hardware. In On-Board Payload Data Compression Workshop 2008 (pp. -). Noordwijk: ESA conference bureau.