Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (17): 5-7.DOI: 10.3778/j.issn.1002-8331.2010.17.002

• 博士论坛 • Previous Articles     Next Articles

Method of parallel contours extraction based on cluster and multi-core CPU

WANG Zong-yue1,2,MA Hong-chao2,XU Hong-gen3,WU Jian-wei2,PENG Jian-gui2   

  1. 1.Computer Engineering College,Jimei University,Xiamen,Fujian 361021,China
    2.School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China
    3.China Aero Geophysical Survey and Remote Sensing Center for Land and Resources,Beijing 100083,China
  • Received:2010-03-10 Revised:2010-04-26 Online:2010-06-11 Published:2010-06-11
  • Contact: WANG Zong-yue



  1. 1.集美大学 计算机工程学院,福建 厦门 361021
    2.武汉大学 遥感信息工程学院,武汉 430079
    3.中国国土资源航空物探遥感中心,北京 100083
  • 通讯作者: 王宗跃

Abstract: After analyzing the advantages/disadvantages of distributed memory programming model in cluster environment and shared memory programming model in multi-core CPU respectively,a parallel method,combining clustering and multi-core,is proposed to enhance the strengths and eliminate the weaknesses.Then the relevant parallel algorithms of extracting contours are studied,of which establishing TIN-Mesh and tracking contours are as study cases of parallel shared memory.At last,the feasibility of the parallel method is verified by experiments.

Key words: Light Detection And Ranging(LiDAR), contours, parallel, multi-core CPU, cluster

摘要: 分析集群环境下分布式存储编程模型和多核CPU环境下共享存储编程模型各自的优缺点,采用结合集群和多核CPU的并行环境来取长补短;并研究其在等高线提取中的相关并行算法,其中以建立三角网和跟踪等高线作为共享存储并行的研究实例;最后通过实验验证了该并行方案的可行性。

关键词: 机载激光雷达, 等高线, 并行, 多核CPU, 集群

CLC Number: