[1]肖 汉,郭宝云*,李彩林,等.基于OpenCL的图像灰度化并行算法研究[J].江西师范大学学报(自然科学版),2020,(05):462-471.[doi:10.16357/j.cnki.issn1000-5862.2020.05.03]
 XIAO Han,GUO Baoyun*,LI Cailin,et al.The Study on Image Gray-Scale Parallel Algorithm Based on OpenCL[J].Journal of Jiangxi Normal University:Natural Science Edition,2020,(05):462-471.[doi:10.16357/j.cnki.issn1000-5862.2020.05.03]
点击复制

基于OpenCL的图像灰度化并行算法研究()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2020年05期
页码:
462-471
栏目:
信息科学与技术
出版日期:
2020-10-20

文章信息/Info

Title:
The Study on Image Gray-Scale Parallel Algorithm Based on OpenCL
文章编号:
1000-5862(2020)05-0462-10
作者:
肖 汉12郭宝云3*李彩林3肖诗洋4
1.郑州师范学院信息科学与技术学院,河南 郑州 450044; 2.郑州大学信息工程学院,河南 郑州 450001; 3.山东理工大学建筑工程学院,山东 淄博 255000; 4.东北林业大学土木工程学院,黑龙江 哈尔滨 150040
Author(s):
XIAO Han12GUO Baoyun3*LI Cailin3XIAO Shiyang4
1.School of Information Science and Technology,Zhengzhou Normal University,Zhengzhou Henan 450044,China; 2.School of Information Engineering,Zhengzhou University,Zhengzhou Henan 450001,China; 3.School of Civil and Architectural Engineering,Shandong University of Technology,Zibo Shandong 255000,China; 4.School of Civil Engineering,Northeast Forestry University,Harbin Heilongjiang 150040,China
关键词:
图像灰度化 加权平均 图形处理器 开放式计算语言 并行算法
Keywords:
image gray-scale weighted average Graphic Processing Unit(GPU) Open Computing Language(OpenCL) parallel algorithm
分类号:
TP 311
DOI:
10.16357/j.cnki.issn1000-5862.2020.05.03
文献标志码:
A
摘要:
随着图像数据量的增加,传统单核处理器或多处理器结构的计算方式已无法满足图像灰度化实时处理需求.该文利用图像处理器(GPU)在异构并行计算的优势,提出了基于开放式计算语言(OpenCL)的图像灰度化并行算法.通过分析加权平均图像灰度化数据处理的并行性,对任务进行了层次化分解,设计了2级并行的并行算法并映射到“CPU+GPU”异构计算平台上.实验结果显示:图像灰度化并行算法在OpenCL架构下NVIDIA GPU计算平台上相比串行算法、多核CPU并行算法和CUDA并行算法的性能分别获得了27.04倍、4.96倍和1.21倍的加速比.该文提出的并行优化方法的有效性和性能可移植性得到了验证.
Abstract:
With the increase of image data amount,the computing model of the traditional single-core processor or multi-processor structure can't meet the real-time processing requirements of image gray-scale.In this paper,the parallel algorithm of image gray-scale based on Open Computing Language(OpenCL)is proposed by using the advantages of Graphic Processing Unit(GPU)in heterogeneous parallel computing.By analyzing the parallelism of weighted average image gray-scale algorithm data processing,the task is decomposed hierarchically.Two levels parallel algorithm is designed and mapped onto the CPU+GPU heterogeneous computing platform.The experimental results show that compared with the performance of the serial algorithm,multi-core CPU parallel algorithm and parallel algorithm based on Compute Unified Device Architecture(CUDA),the image gray-scale parallel algorithm obtains 27.04 times,4.96 times and 1.21 times speedup in the NVIDIA GPU computing platform under the OpenCL architecture respectively.The validity and performance portability of the proposed parallel optimization method are verified.

参考文献/References:

[1] Schindler S,Bruchmann M,Bublatzky F,et al.Modulation of face- and emotion-selective ERPs by the three most common types of face image manipulations[J].Social Cognitive and Affective Neuroscience,2019,14(5):493-503.
[2] Li Dahua,Zhao Hui,Zhao Xiangfei,et al.Cucumber detection based on texture and color in greenhouse[J].International Journal of Pattern Recognition and Artificial Intelligence,2017,31(8):1-17.
[3] Howard S R,Shrestha M,Schramme J,et al.Honeybees prefer novel insect-pollinated flower shapes over bird-pollinated flower shapes[J].Current Zoology,2019,65(4):457-465.
[4] Gotz M,Cavallaro G,Geraud T,et al.Parallel computation of component trees on distributed memory machines[J].IEEE Transactions on Parallel and Distributed Systems,2018,29(11):2582-2598.
[5] Rostami M J,Shahba A,Saryazdi S,et al.A novel parallel image encryption with chaotic windows based on logistic map[J].Computers and Electrical Engineering,2017,62(8):384-400.
[6] Luo Gaofeng,Zhou Rigui,Liu Xingao,et al.Fuzzy matching based on gray-scale difference for quantum images[J].International Journal of Theoretical Physics,2018,57(8):2447-2460.
[7] Dhivya R,Prakash R.Edge detection of satellite image using fuzzy logic[J].Cluster Computing:The Journal of Networks Software Tools and Applications,2019,22(5):11891-11898.
[8] Sreenilayam Sithara P,Panarin Yuri P,Vij Jagdish K,et al.Spontaneous helix formation in non-chiral bent-core liquid crystals with fast linear electro-optic effect[J].Nature Communications,2016,7(5):S1-S11.
[9] Lowes S,Leaver A,Cox K,et al.Evolving imaging techniques for staging axillary lymph nodes in breast cancer[J].Clinical Radiology,2018,73(4):396-409.
[10] Jahid Tarik,Karmouni Hicham,Hmimid Abdeslam,et al.Fast computation of Charlier moments and its inverses using Clenshaw's recurrence formula for image analysis[J].Multimedia Tools and Applications,2019,78(9):12183-12201.
[11] Liu Zhao,Jing Hui,Han Xue,et al.Shear wave elastography combined with the thyroid imaging reporting and data system for malignancy risk stratification in thyroid nodules[J].Oncotarget,2017,8(26):43406-43416.
[12] Yadav,Gyan Singh,Ojha,Aparajita.Secure data hiding scheme using shape generation algorithm:a key based approach[J].Multimedia Tools and Applications,2018,77(13):16319-16345.
[13] Jin Changzhu,Nam Kweon-Ho,Paeng Dong-Guk.Asymmetric pulsation of rat carotid artery bifurcation in three-dimension observed by ultrasound imaging[J].International Journal of Cardiovascular Imaging,2016,32(10):1499-1508.
[14] Nafchi H Z,Shahkolaei A,Hedjam R,et al.CorrC2G:color to gray conversion by correlation[J].IEEE Signal Processing Letters,2017,24(11):1651-1655.
[15] Viswanathan S,Divakaran G,Soman K P.Exploring the significance of using perceptually relevant image decolorization method for scene classification[J].Journal of Electronic Imaging,2017,26(6):21-31.
[16] Rostami M J,Shahba A,Saryazdi S,et al.A novel parallel image encryption with chaotic windows based on logistic map[J].Computers and Electrical Engineering,2017,62(8):384-400.
[17] 崔宣,丁杨,高文,等.快速并行细化算法在焊缝识别中的实现[J].西华大学学报:自然科学版,2014,33(6):11-15.
[18] Tan Fenglin,Li Yanxiong,Guan Mingyu.Automatic windowing for highly dynamic industrial X-ray image based on short-term energy of gray histogram[J].Journal of Nondestructive Evaluation,2017,36(3):539-552.
[19] 杨洪余,李成明,王小平,等.CPU/GPU异构环境下图像协同并行处理模型[J].集成技术,2017,6(5):8-18.
[20] Saleem S,Bais A,Sablatnig R,et al.Feature points for multisensor images[J].Computers and Electrical Engineering,2017,62(8):511-523.
[21] Freitas P G,Farias M C Q,Araujo A P F.Hiding color watermarks in halftone images using maximum similarity binary patterns[J].Signal Processing:Image Communication,2016,48(10):1-11.
[22] Kiermaier M,Wassermann A,Zwanzger J.New upper bounds on binary linear codes and a Z(4)-code with a better-than-linear gray image[J].IEEE Transactions on Information Theory,2016,62(12):6768-6771.
[23] 姜涛,张云伟,何芳.基于流处理器的图像灰度变换并行处理研究[J].电子技术应用,2011,37(2):116-119.
[24] 班志华,陈华,刘田田,等.CUDA与Dot Net混合编程在图像灰度处理中的应用[J].电脑知识与技术,2011,7(11):2647-2648,2651.
[25] 占正锋,李戈,张学贺,等.基于CUDA的图像预处理并行化研究[J].机械与电子,2014(7):64-67.
[26] Jaksic Zoran,Cadenelli Nicola,Buchaca Prats David,et al.A highly parameterizable framework for conditional restricted boltzmann machine based workloads accelerated with FPGAs and OpenCL[J].Future Generation Computer Systems:The International Journal of Escience,2020,104(5):201-211.
[27] Singh Dhirendra Pratap,Joshi Ishan,Choudhary Jaytrilok.Survey of GPU based sorting algorithms[J].International Journal of Parallel Programming,2018,46(6):1017-1034.
[28] Maier Georg,Pfaff Florian,Wagner Matthias,et al.Real-time multitarget tracking for sensor-based sorting a new implementation of the auction algorithm for graphics processing units[J].Journal of Real:Time Image Processing,2019,16(6):2261-2272.
[29] Hajmohammadi S,Nooshabadi S,Archer G E,et al.Parallel hybrid bispectrum-multi-frame blind deconvolution image reconstruction technique[J].Journal of Real:Time Image Processing,2019,16(4):919-929.
[30] Funasaka S,Nakano K,Ito Y.Fully parallelized LZW decompression for CUDA-enabled GPUs[J].IEICE Transactions on Information and Systems,2016,E99D(12):2986-2994.
[31] D'Ambra P,Filippone S.A parallel generalized relaxation method for high-performance image segmentation on GPUs[J].Journal of Computational and Applied Mathematics,2016,293(2):35-44.

备注/Memo

备注/Memo:
收稿日期:2020-02-19
基金项目:国家自然科学基金(41701525,41601496),山东省自然科学基金(ZR2017LD002)和山东省重点研发计划(2018GGX106002)资助项目.
作者简介:肖 汉(1970-),男,湖北武汉人,教授,博士后,主要从事大规模并行算法研究与设计、遥感大数据并行处理的研究.E-mail:xiaohan70@163.com
通信作者:郭宝云(1986-),女,安徽滁州人,讲师,博士,主要从事数字摄影测量与计算机视觉研究.E-mail:guobaoyun@sdut.edu.cn
更新日期/Last Update: 2020-10-20