Real-Time Image Compression using SIMD architectures

摘要

Today, in the digitized satellite image domain, the needs for high dimension images increase considerably. To transmit or to stock such images (more than 6000 by 6000 pixels), we need to reduce their data volume and so we have to use image compression technics. In most cases, these operations have to be processed in Real-Time. The large amount of computations required by classical image compression algorithms prohibits the use of common sequential processors.rnTo solve this problem, CEA in collaboration with CNES has tried to define the best suited architecture for the image compression. In order to achieve this aim, we developed and evaluated a new parallel image compression algorithm for general purpose parallel computers using data-parallelism.rnThe purpose of this paper is to present this new parallel image compression algorithm. We present implementation results on several parallel computers. We also examine load balancing and data mapping problems. We end by defining optimal characteristics of the parallel machine for Real-Time image compression.