基于CUDA架构并行设计图像去噪算法
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Parallel design of image denoising algorithm based on CUDA
  • 作者:霍迎秋 ; 陈春荣 ; 王雨菲 ; 尹加
  • 英文作者:HUO Yingqiu;CHEN Chunrong;WANG Yufei;YIN Jia;School of Information Engineering,Northwest A&F University;
  • 关键词:CUDA ; 图像去噪 ; K-SVD ; 图形处理器 ; 并行优化 ; 矩阵拉伸
  • 英文关键词:CUDA;;image denoising;;K-SVD;;graphic processing unit;;parallel optimization;;matrix stretching
  • 中文刊名:XDDJ
  • 英文刊名:Modern Electronics Technique
  • 机构:西北农林科技大学信息工程学院;
  • 出版日期:2018-11-12 14:03
  • 出版单位:现代电子技术
  • 年:2018
  • 期:v.41;No.525
  • 基金:陕西省农业科技创新与攻关项目(2015NY049);; 陕西省自然科学基金面上项目(2015JM3110);; 大学生科技创新项目:基于CUDA的并行K-SVD图像去噪算法研究~~
  • 语种:中文;
  • 页:XDDJ201822014
  • 页数:6
  • CN:22
  • ISSN:61-1224/TN
  • 分类号:61-66
摘要
针对图像去噪算法中由于数据量大、计算复杂度高导致的实时性低的问题,通过对经典K-SVD图像去噪算法的并行性进行研究分析,设计基于CUDA架构的并行K-SVD图像去噪算法。该算法主要对去噪算法中矩阵拉伸、快速OMP和SVD等部分进行并行设计,采用"共享内存""归并求和"等策略进行优化。实验结果表明,基于CUDA架构的并行算法比串行算法速度有了显著提高,最高加速比为12倍,极大提高了图像去噪算法的处理速度。
        In allusion to the low real-time performance caused by mass data quantity and high calculation complexity in the image denoising algorithm,a parallel K-SVD image denoising algorithm based on computer unified device architecture(CUDA)is designed by means of parallelism research analysis of the typical K-SVD image denoising algorithm. In the algorithm,the parallel design of matrix stretching,fast OMP,SVD and other parts in the denoising algorithm is conducted. Strategies like memory sharing and summation by merging are adopted for optimization. The experimental results show that the parallel algorithm based on CUDA has a significant higher speed than the serial algorithm and a speed-up ratio as high as 12,which greatly improves the processing speed of the image denoising algorithm.
引文
[1]赵育良,许兆林.基于图像处理技术的航空相机镜头焦面自准直定位研究[J].应用光学,2012,33(2):288-292.ZHAO Yuliang,XU Zhaolin. Autocollimation location system of aerial camera lens′focus plane based on image processing technology[J]. Journal of applied optics,2012,33(2):288-292.
    [2]孙世杰,张凯,孙力,等.基于图像处理的航空仪表自动判读系统设计[J].科学技术与工程,2011,11(6):1260-1263.SUN Shijie,ZHANG Kai,SUN Li,et al. Automatic interpretation of aviation instrument based on image processing[J]. Science technology and engineering,2011,11(6):1260-1263.
    [3]赵志彬,刘晶红.基于图像处理的航空成像设备自动调焦设计[J].液晶与显示,2010,25(6):863-868.ZHAO Zhibin,LIU Jinghong. Auto-focusing method for airborne image equipment based on image processing[J]. Chinese journal of liquid crystals and displays,2010,25(6):863-868.
    [4]郝景宏,姜袁,梅世强,等.基于CT图像处理技术的混凝土损伤演化研究[J].人民长江,2010,41(17):79-83.HAO Jinghong,JIANG Yuan,MEI Shiqiang,et al. Study on damage development of concrete based on CT image processing[J]. Yangtze River,2010,41(17):79-83.
    [5]田威,党发宁,陈厚群.基于CT图像处理技术的混凝土细观破裂分形分析[J].应用基础与工程科学学报,2012,20(3):424-431.TIAN Wei,DANG Faning,CHEN Houqun. Fractal analysis on meso-fracture of concrete based on the technique of CT image processing[J]. Journal of basic science and engineering,2012,20(3):424-431.
    [6]刘奇,李昌聪,黄韫栀,等.对接管焊缝的双壁双投影工业X射线图像处理研究[J].四川大学学报(工程科学版),2015,47(2):89-94.LIU Qi,LI Changcong,HUANG Yunzhi,et al. Image processing research on double-walled double-imaging industrial X-ray radiographs of butt weld[J]. Journal of Sichuan University(Engineering science edition),2015,47(2):89-94.
    [7]丁继生,卫伟,杨依忠,等.一种基于FPGA的开关中值滤波算法研究[J].合肥工业大学学报(自然科学版),2016,39(4):490-493.DING Jisheng,WEI Wei,YANG Yizhong,et al. Research on switching median filtering algorithm based on FPGA[J]. Journal of Hefei University of Technology,2016,39(4):490-493.
    [8]汪祖辉,孙刘杰,邵雪,等.一种结合小波变换和维纳滤波的图像去噪算法[J].包装工程,2016,37(13):173-178.WANG Zuhui,SUN Liujie,SHAO Xue,et al. An image denoising algorithm combined with wavelet transform and Wiener filtering[J]. Packaging engineering,2016,37(13):173-178.
    [9]张小波.基于维纳滤波的图像去噪算法研究[D].西安:西安电子科技大学,2014.ZHANG Xiaobo. Research of image denoising algorithms based on Wiener filter[D]. Xi’an:Xidian University,2014.
    [10]焦莉娟,王文剑.一种快速的K-SVD图像去噪方法[J].小型微型计算机系统,2016,37(7):1608-1612.JIAO Lijuan,WANG Wenjian. Speeded-up K-SVD image denoising algorithm[J]. Journal of Chinese computer systems,2016,37(7):1608-1612.
    [11] AHARON M,ELAD M,BRUCKSTEIN A. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE transactions on signal processing,2006,54(11):4311-4322.
    [12] ELAD M,AHARON M. Image denoising via sparse and redundant representations over learned dictionaries[J]. IEEE transactions on image processing,2006,15(12):3736-3745.
    [13]张海军,陈圣波,张旭晴,等.基于GPU的遥感图像快速去噪处理[J].城市勘测,2010(2):96-98.ZHANG Haijun, CHEN Shengbo, ZHANG Xuqing, et al.GPU-based denoising to remotely sensing images[J]. Urban geotechnical investigation&surveying,2010(2):96-98.
    [14] PARK J Y,CHUNG K S. Parallel LDPC decoding using CUDA and OpenMP[J]. EURASIP journal on wireless communications and networking,2011(1):172-179.
    [15] MROZEK D,BROZEK M,MALYSIAK-MROZEK B. Parallel implementation of 3D protein structure similarity searches using a GPU and the CUDA[J]. Journal of molecular modeling,2014,20(2):2067.
    [16]霍迎秋,秦仁波,邢彩燕,等.基于CUDA的并行K-means聚类图像分割算法优化[J].农业机械学报,2014,45(11):47-53.HUO Yingqiu,QIN Renbo,XING Caiyan,et al. CUDAbased parallel K-means clustering algorithm[J]. Transactions of the Chinese Society of Agricultural Machinery,2014,45(11):47-53.
    [17]张晓阳.基于K-SVD和残差比的稀疏表示图像去噪研究[D].重庆:重庆大学,2012.ZHANG Xiaoyang. Image denoising via sparse and redundant representations over K-SVD algorithm and residual ratio iteration termination[D]. Chongqing:Chongqing University,2012.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700