RT Journal Article
T1 An extremely pipelined FPGA implementation of a lossy hyperspectral image compression algorithm
A1 González, Carlos
A1 Bascones García, Daniel
A1 Mozos Muñoz, Daniel
AB Segmented and pipelined execution has been a staple of computing for the past decades. Operations over different values can be carried out at the same time speeding up computations. Hyperspectral image compression sequentially processes samples, exploiting local redundancies to generate a predictable data stream that can be compressed. In this paper, we take advantage of a Low Complexity Predictive Lossy Compression algorithm which can be executed over an extremely long pipeline of hundreds of stages. We can avoid most stalls and maintain throughput close to the theoretical maximum. The different steps operate over integers with simple arithmetic operations, so they are specially well-suited for our FPGA implementation. Results on a Virtex-7 show a maximum frequency of over 300Mhz for a throughput of over 290MB/s, with a space-qualified Virtex5 reaching 258MHz, being 5 times as fast as the previous FPGA designs. This shows that a modular pipelined approach is beneficial for these kinds of compression algorithms.
PB IEEE
SN 0196-2892
YR 2020
FD 2020
LK https://hdl.handle.net/20.500.14352/98415
UL https://hdl.handle.net/20.500.14352/98415
LA eng
NO D. Báscones, C. González and D. Mozos, "An Extremely Pipelined FPGA Implementation of a Lossy Hyperspectral Image Compression Algorithm," in IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 10, pp. 7435-7447, Oct. 2020, doi: 10.1109/TGRS.2020.2982586.
NO Ministerio de Economía y Competitividad (España)
DS Docta Complutense
RD 8 abr 2025