期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

Parallel Extraction of Marine Targets Applying OIDA Architecture

下载PDF
导出
摘要 Computing resources are one of the key factors restricting the extraction of marine targets by using deep learning.In order to increase computing speed and shorten the computing time,parallel distributed architecture is adopted to extract marine targets.The advantages of two distributed architectures,Parameter Server and Ring-allreduce architecture,are combined to design a parallel distributed architecture suitable for deep learning–Optimal Interleaved Distributed Architecture(OIDA).Three marine target extraction methods including OTD_StErf,OTD_Loglogistic and OTD_Sgmloglog are used to test OIDA,and a total of 18 experiments in 3categories are carried out.The results show that OIDA architecture can meet the timeliness requirements of marine target extraction.The average speed of target parallel extraction with single-machine 8-core CPU is 5.75 times faster than that of single-machine single-core CPU,and the average speed with 5-machine 40-core CPU is 20.75 times faster.
作者 LIU Lin LI Wanwu ZHANG Jixian SUN Yi CUI Yumeng
机构地区 College of Geodesy and Geomatic National Quality Inspection and Testing Center for Surveying and Mapping Products
出处 《Journal of Ocean University of China》 SCIE CAS CSCD 2022年第3期737-747,共11页 中国海洋大学学报（英文版）
基金 the Natural Science Foundation of Shandong Province(No.ZR2019MD034) the Education Reform Project of Shandong Province(No.M2020266)。
关键词 parallel computing distributed architecture deep learning target extraction PolSAR image
分类号 P71 [天文地球—海洋科学]
  • 相关文献

参考文献3

二级参考文献29

  • 1杨凌云.基于多核技术的并行图像检索系统的研究[D].北京:北京化工大学,2008.
  • 2HU W, TAN T, WANG L, et al. A survey on visual surveillance of ob- ject motion and behaviors[J]. IEEE Trans. Systems, Man. , and Cyber- netics:Applications and Reviews,2004,34(3) : 334-352.
  • 3ZIVKOVIC Z. Improved adaptive Gaussian mixture model for background subtraction [ C ]//Proc. 17th International Conference on Pattern Recogni- tion. [S. 1. ] :IEEE Press,2004:28-31.
  • 4SIKORA T. The MPEG-7 visual standard for content description-an o- verview[J]. IEEE Trans. Circuits and Systems tbr Video Technology, 2001, 11(6) : 696-702.
  • 5ASANOVIC K, BODIK R, DEMMEL J, et al. A view of the parallel computing landscape[J]. Communicati6ns of the ACM, 2009, 52(10) : 56-67.
  • 6ASANOVIC K, BODIK R, CATANZARO B C, et al. The landscape of parallel computing research : a view from Berkeley [ R ]. Berkeley : Uni- versity of California ,2006.
  • 7JANG H, PARK A, JUNG K. Neural network implementation using euda and openmp [ C ]//Prec. DICTA' 08. [ S. 1. ] : IEEE Press, 2008: 155-161.
  • 8DAGUM L, MENON R. OpenMP: an industry standard API for shared- memory programming[J]. Computational Science & Engineering, IEEE, 1998, 5(1): 46-55.
  • 9ROY M, KIM M, KANG H K, et al. MPEG-7 homogeneous texture de- scriptor[J]. ETRI Journal, 2001, 23(2) : 41-51.
  • 10BOBER M. MPEG-7 visual shape descriptors [ J ]. IEEE Trans. Circuits and Systems for Video Technology,2001, 11 (6) : 716-719.

共引文献3

Journal of Ocean University of China
2022年 第3期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部