摘要
在高分辨率遥感影像信息提取过程中,为提高信息提取的精度,采用基于特征基元的尺度分割方法;为提高信息提取的速度,采用并行计算机制实现遥感影像的信息提取.在采用并行计算实现遥感影像特征提取过程中,提出非均匀数据分配策略,并对其进行基于MPI的实现及效率的分析.结果表明,非均匀的遥感数据划分策略在针对特定图像的并行处理时能够得到比常规均匀划分策略更高的效率.
This paper presents the method of improving the efficiency of information extraction based on feature unit of high - resolution remotely sensed image. To improve the precision of image processing, investigators propose the research idea of image rough - classification based on large scale and precise - segmentation based on small scale. To improve the speed of image processing, parallel computing method was used to solve this problem. For the data partition method of parallel computing of remotely sensed image, a new scale asymmetric partition method is given, and the implementation and partition effect based on MPI (Message Passing Interface) are analysed. Results show that the new data - partition method can improve the efficiency of parallel computing for some special remotely sensed image.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2006年第11期1968-1971,1976,共5页
Journal of Harbin Institute of Technology
基金
国家自然科学基金资助项目(4060105740301030)
中国博士后科学基金资助项目(2005038406)
中国科学院王宽诚博士后工作奖励基金资助项目(20050827005406)
中国科学院资源与环境信息系统国家重点实验室开放研究基金资助项目(A0615)
关键词
MPI
并行计算
信息提取
尺度
数据划分
MPI
parallel computing
information extraction
scale
data partition