GPU implementation of a lossy compression algorithm for hyperspectral images

Abstract

In this paper, a lossy compression algorithm for onboard hyperspectral image compression is implemented on a GPU. The strategy followed for parallelizing the algorithm is presented, as well as the experimental results obtained when executing it on the GPU. Furthermore, we present the speedups that can be gained by the GPU implementation with respect to the CPU implementation, which demonstrate that the computational power of the GPUs is effective in obtaining compression results in short execution times.