|本期目录/Table of Contents|

[1]骆岩红,李公平,王建华.基于CUDA架构的FDK算法的研究[J].工业仪表与自动化装置,2015,(06):3.
 LUO Yanhong,LI Gongping,WANG Jianhua.Research based on CUDA architecture of FDK algorithm[J].Industrial Instrumentation & Automation,2015,(06):3.
点击复制

基于CUDA架构的FDK算法的研究(PDF)

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2015年06期
页码:
3
栏目:
出版日期:
2015-12-15

文章信息/Info

Title:
Research based on CUDA architecture of FDK algorithm
文章编号:
1000-0682(2015)06-0000-00
作者:
骆岩红12李公平2王建华1
(1.西北民族大学 电气工程学院,兰州 730030;2.兰州大学 核科学与技术学院,兰州 730000)
Author(s):
LUO Yanhong12 LI Gongping2 WANG Jianhua
(1. Electrical Engineering,Northwest University for Nationalities, Lanzhou 730030, China;2. School of Nuclear Science and Technology, Lanzhou University, Lanzhou 730000, China)
关键词:
三维锥束CTFDK算法图像处理器CUDA
Keywords:
3D cone-beam CT FDK Algorithm GPU CUDA
分类号:
TP391
DOI:
-
文献标志码:
A
摘要:
该文研究了一种利用GPU并行架构的CUDA来完成FDK三维图像重建算法的加速。首先分析了FDK三维图像重建算法的可并行性特点,然后设计了适合CUDA的并行的方法分别在算法加权、滤波和反投影3个阶段,实现FDK的加速。经过实验验证,该文提出的方法与算法由CPU单独实现图像重建相比,不仅获得了128倍以上的加速效果,并且两种方式完成的重建图像,质量接近,平均误差小于10-4。由此可得出结论,利用GPU的三维锥束CT图像重建能够得到较满意的结果。
Abstract:
This paper studies a kind of using CUDA GPU parallel architecture to complete the FDK three-dimensional image reconstruction algorithm acceleration.In this paper, it analyzed the FDK algorithm parallelism characteristics, then it designed for CUDA parallel method in weighted, filtering algorithm and the projection three phases. It realized the FDK acceleration.Through experiment compared with the algorithm implementation alone by CPU image reconstruction, it not only won more than 128 times speedup, but also got better quality the image. The average error is less than 10-4. So it concluded that use of GPU 3D cone beam CT image reconstruction can obtain satisfactory results.

参考文献/References:

[1] Fang Xu,Klaus Mueller.Ultra-fast 3D filtered backprojection on commodity graphics hardware[J]. IEEE International Symposium on Biomedical Imaging: Macro to Nanno, Arlington United states, 2004(1):571-574.

[2] 陈雪松.CT图像重建可扩展多DSP并行计算系统结构[J]. 清华大学学报:自然科学版,2004,44(3):44-47.
[3] 邹永宁,谭辉,黄亮.CT图像重建加速的几种方法[J].计算机系统应用,2009,18(4):167-170.
[4] B Cabral, N Cam, J Foran. Accelerated volume rendering and tomographic reconstruction using texture mapping hardware[J].Proc. Symp.On Volume Visualization,1994(10): 91-98.
[5] Klaus Mueller, Fang Xu. Practical considerations for GPU- accelerated CT[J]. IEEE International Symposium on Biomedical Imaging: Macro to Nano,2006(7):1184-1187.
[6] 戴智晟,陈志强.用通用显卡加速三维锥束T-FDK重建算法[J].清华大学学报:自然科学版,2006,46(9):1589-1592.
[7] 马东平,曾理.GPU多重纹理加速三维CT图像重建[J].计算机工程与应用,2008,44(7):227-230.
[8] Holger Scherl,Benjamin Keck,Markus Kowarschik,et al.Fast GPU-Based CT Reconstruction using the Common Unified Device Architecture(CUDA)[J]. Nuclear Science Sympo- sium Conference Record, 2007,26(280):4464-4466.
[9] 王珏,曹思远,邹永宁.利用CUDA技术实现锥束CT图像快速重建[J].核电子学与探测技术,2010,30(3):315-320.
[10] 孙毅刚,孙修宇,张红颖.基于现代GPU的实时锥束重建算法研究[J].核电子学与探测技术,2010,30(9):1260-1265.
[11] 肖江,胡柯良,邓元勇.基于CUDA的矩阵乘法和FFT性能测试[J].计算机工程,2009,35(10):7-10.
[12] De Beer R, Van Ormondt,D Di, Cesare F,et al.Accelerating batched 1D-FFT with a CUDA-capable computer[C]. Imaging Systems and Techniques(IST), IEEE International Conference,2010:446-451.
[13] Kauker D, Sanftmann H, Frey S. Memory Saving Discrete Fourier Transform on GPUs[J].Computer and Information Technology(CIT),2010(6):1152-1157.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2015-01-05
基金项目:中央高校项目(319201300160)
作者简介:骆岩红(1973),女,副教授,研究方向为CT图像处理与重建技术研究。
更新日期/Last Update: 1900-01-01