Paper
20 September 2011 Heterogeneous computing system with GPU-based IDWT and CPU-based SPIHT and Reed-Solomon decoding for satellite image decompression
Changhe Song, Yunsong Li, Bormin Huang
Author Affiliations +
Abstract
The discrete wavelet transform (DWT)-based Set Partitioning in Hierarchical Trees (SPIHT) algorithm is widely used in many image compression systems. In order to perform real-time Reed-Solomon channel decoding and SPIHT+DWT source decoding on a massive bit stream of compressed images continuously down-linked from the satellite, we propose a novel graphic processing unit (GPU)-accelerated decoding system. In this system the GPU is used to compute the time-consuming inverse DWT, while multiple CPU threads are run in parallel for the remaining part of the system. Both CPU and GPU parts were carefully designed to have approximately the same processing speed to obtain the maximum throughput via a novel pipeline structure for processing continuous satellite images. Through the pipelined CPU and GPU heterogeneous computing, the entire decoding system approaches a speedup of 84x as compared to its single-threaded CPU counterpart.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Changhe Song, Yunsong Li, and Bormin Huang "Heterogeneous computing system with GPU-based IDWT and CPU-based SPIHT and Reed-Solomon decoding for satellite image decompression", Proc. SPIE 8157, Satellite Data Compression, Communications, and Processing VII, 815710 (20 September 2011); https://doi.org/10.1117/12.895421
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Remote sensing

Computing systems

Discrete wavelet transforms

Satellites

Satellite imaging

Image processing

Earth observing sensors

Back to Top