基于OpenMP的压缩感知多描述并行处理算法  

Multiple description of compressed sensing parallel processing algorithm based on OpenMP

作　　者：巫小婷[1] 邓家先[1] 任玉莉[1] 杨扬[1] 

机构地区：[1]海南大学信息科学技术学院,海口570228

出　　处：《计算机应用研究》2013年第4期1278-1280,共3页Application Research of Computers

摘　　要：针对压缩感知算法重建时间长、图像重建质量不高等不足,在认真分析压缩感知算法的基础上,提出一种压缩感知多描述并行算法。为了提高系统运行速度和重建图像质量,将经过稀疏变换后的系数进行交织抽取,分成多个子图像,再利用OpenMP将子图像分配到各线程中并行实现分块压缩感知。实验结果表明,随着抽取数的增加,图像的重建质量呈上升趋势,在32-抽取时图像的重建质量比单抽取的高出了7.24 dB;随着线程数的增加,程序的执行效率不断提高,最高可达单线程的7.35倍,有效地解决了压缩感知算法重建时间长以及图像重建质量差的问题。Concerning the long time running for reconstruction and the poor quality of reconstruction image in compressed sensing,this paper proposed a multiple description of compressed sensing parallel processing algorithm on the basis of a careful analysis.In order to improve the speed and the quality of reconstruction image,divided the coefficients after sparse transform into several sub-images using interleaving extraction.And then assigned these sub-images to each thread to using OpenMP.The experimental results show that the quality of reconstruction image is rising with the increase of the extraction number,compare with the single extraction,the PSNR in 32-extraction is higher 7.24 dB.Moreover the executed efficiency continues to increase with the increase of the number of threads,it＇s up to 7.35 times compare with the single-thread.It solved the problems of long time running and poor quality of reconstruction image effectively by the proposed algorithm.

关 键 词：压缩感知 多描述 OPENMP 并行 交织抽取 加速比 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP391.4[自动化与计算机技术—计算机科学与技术]