浏览全部资源
扫码关注微信
1. 中国科学院 长春光学精密机械与物理研究所,吉林 长春,中国,130033
2. 中国科学院 研究生院 北京,100039
收稿日期:2008-04-16,
修回日期:2008-06-06,
纸质出版日期:2009
移动端阅览
李仕, 张葆, 孙辉. 航空成像像移补偿的并行计算[J]. 光学精密工程, 2009,17(1): 225-230
LI Shi, ZHANG Bao, SUN Hui. Parallel restoration for motion-blurred aerial image[J]. Editorial Office of Optics and Precision Engineering, 2009,17(1): 225-230
基于图像处理器(GPU)平台提出了维纳并行滤波算法
解决了航空成像的像移实时补偿问题。介绍了原有像移补偿算法及其PC运行平台的不足
立足于现有图像处理器通用计算技术对原有像移补偿算法做多线程并行计算的改进。针对图像处理器件的硬件并行架构
优化设置算法多线程访问
提高了各个线程的访问速度。该环节的改进甚至能将算法效率提升到原来的3倍。借助图像处理器的并行运算优势
单帧1 0241 024灰度图像的恢复处理时间只需要8 ms
整个算法的运行速度达到原先的20倍
能够完全满足高分辨率航拍视频图像的像移模糊实时恢复的需求。
In order to improve the speed of restoration algorithm
a parallel Wiener filtering method based on Graphic Processing Unit(GPU)platform is presented to restore motion-blurred aerial image degraded in a deterministic way by motion or vibration. The shortages of the original algorithm using Wiener filtering and original PC run-time platform are introduced. On the basis of the new General Purpose GPU (GPGPU) technology
the original algorithm is divided into thousands of single algorithm threads to be computed in parallel. According to the special simultaneous operating mode of GPU hardware
a way in which the algorithm threads access the data on the GPU global memory is specially configured to improve the accessing speed
the algorithm efficiency by the special configuration can even be improved roughly 3 times that by original configuration. With the parallel computing ability of GPU
the new algorithm can restore 1 0241 024 gray image in 8 ms per frame. The experimental result shows the new algorithm based on GPU reaches approximately 20 times that of original algorithm based on CPU of personal PC
which can completely be applied to the real time restoration of high resolution motion-blurred aerial image.
贾平,张葆,孙辉. 航空成像像移模糊恢复技术[J]. 光学 精密工程,2006,14(4):697-703. JIA P, ZHANG B,SUN H. Restoration of motion-blurred aerial image [J]. Opt. Precision Eng.,2006,14(4) :697-703. (in Chinese)[2] 孙辉,张葆,刘晶红. 基于维纳滤波的运动模糊消除算法及其在航空成像系统中的应用[J]. 光学 精密工程,2005,13(6):735-740. SUN H, ZHANG B, LIU J H. Restoration of motion-blurred image based on Wiener filter and its application in aerial imaging system [J].Opt. Precision Eng.,2005,13(6):735-740.(in Chinese)[3] 李仕,孙辉,张葆 . 一种运动模糊图像的实时恢复算法[J]. 光学 精密工程,2007,15(5):767-772. LI SH, SUN H, ZHANG B. A method for real-time restoration of motion-blurred images [J].Opt. Precision Eng.,2007,15(5):767-772.(in Chinese)[4] 李仕,张葆,孙辉. 航空光电成像模糊的实时恢复 . 光学 精密工程,2007,15(8):1287-1292. LI SH, ZHANG B, SUN H. Real-time restoration using real discrete Fourier transform for aerial E-O imaging system [J].Opt. Precision Eng.,2007,15(8):1287-1292.(in Chinese)[5] MORELAND K, ANGEL E. The FFT on a GPU . In SIGGRAPH/Eurographics Workshop on Graphics Hardware 2003 Proceedings, 2003:112-119. [6] 韩昌元.信息光学基础理论及其应用[M]. 长春:长春出版社,1989. HAN CH Y. Fundamental Theory and Application of Information Optics[M].Changchun: Changchun Press,1989. (in Chinese)[7] PHARR M, FERNANDO R. GPU Gems2[M]. Addison-Wesley Professional, 2005.[8] 邓劲. 图形处理器上的快速傅立叶变换[J]. 现代电子技术,2007(10):151-154. DENG J. FFT on graphics processing unit[J]. Modern Electronic Technique, 2007(10):151-154.(in Chinese)
0
浏览量
238
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构