首页 | 本学科首页   官方微博 | 高级检索  
     检索      

CUDA和OpenCV图像并行处理方法研究
引用本文:刘鑫,姜超,冯存永.CUDA和OpenCV图像并行处理方法研究[J].测绘科学,2012(4):123-125.
作者姓名:刘鑫  姜超  冯存永
作者单位:新疆69028部队四队;信息工程大学测绘学院
基金项目:国家863项目“城市空间信息系统网格化集成和智能化服务技术”(2009AA12Z228);国家863项目“网格地理信息系统软件及其重大应用-苏州数字城市网格应用示范系统”(2007AA120504);国家科技支撑计划课题“区域空间信息资源共享与服务关键技术研发与集成”(2007BAH16B03-r3)
摘    要:CUDA架构与传统GPU通用计算相比,编程更简单、应用领域更广泛,将CUDA架构引入到图像处理中可以提高图像的处理效率。本文提出了一种基于CUDA和OpenCV的图像并行处理方法,实现了图像二值化以及融合,经实验结果表明基于该方法可以提高图像处理效率;将该方法集成到MFC框架,能够应用到实际工程开发领域。

关 键 词:GPU  GPGPU  CUDA  OpenCV  图像二值化  图像融合

Image parallel processing based on CUDA and OpenCV
LIU Xin,JIANG Chao,FENG Cun-yong.Image parallel processing based on CUDA and OpenCV[J].Science of Surveying and Mapping,2012(4):123-125.
Authors:LIU Xin  JIANG Chao  FENG Cun-yong
Institution:①(①Fourth Group of Sinkiang Troops 69028,Urumqi 830006,China;②Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450052,China)
Abstract:NVIDIA’s CUDA architecture programs easier,is more powerful and has more extensive applications than the traditional general-purpose GPU computing,so the introduction of the CUDA architecture to the image processing can improve image processing efficiency.This paper presented a parallel processing method combining OpenCV and CUDA to achieve the image binarization and the integration.The experimental results showed that this method could greatly improve image processing efficiency,and finally it was integrated into the MFC framework in order to apply in practical engineering fields.
Keywords:GPU  GPGPU  CUDA  OpenCV  binarization  image fusion
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号