A Low-Cost Hardware Accelerator for CCSDS 123 Predictor in FPGA
Lucas M. V. Pereira, Douglas A. Santos, Cesar Albenes Zeferino, Douglas R. Melo · 2019
Hyperspectral images are a widely used remote sensing technique. These images are three-dimensional data structures, where the x and y axes contain spatial information and the z-axis contains spectral information or image bands. Usually, these bands can reach the order of hundreds, generating a considerable amount of information. Due to storage limitations and communication bandwidth, the use of compression techniques becomes essential. For spatial applications, a standard commonly used in the literature is CCSDS 123, developed by the Consultative Committee for Space Data Systems, which describes the algorithm for lossless compression of hyperspectral images. In this context, we implemented the prediction stage of the CCSDS 123 algorithm in the Xilinx Zynq-7000 FPGA. The developed processor provides a good trade-off to meet real-time requirements at low-cost.