期刊文献+

几何操作中重采样问题的数据并行实现

Data Parallel Implementation of Resampling Problem in Geometric Operations
下载PDF
导出
摘要 通过SIMD PE阵列之间的数据并行传送,数据并行实现重采样,使实现重采样的复杂度由存储器数据流访问实现方法的Ο(MN)降低到Ο(M+N),从而大大提高了处理速度,能更好地满足图像快速实时处理的需要. Through the data parallel passing between SIMD PE arrays,this paper implements the problem of ressmpling in geometric operations in data parallel.This kind of data parallel implementation reduces implementing complexity of resampling from Ο(MN) implemented by accessing memory to Ο(M+N),and greatly enhances processing speed of processor.Thereby,it can meet the requirements of real-time processing of image effectively.
作者 朱曦 王光
出处 《西安文理学院学报(自然科学版)》 2009年第4期90-93,共4页 Journal of Xi’an University(Natural Science Edition)
关键词 几何操作 重采样 数据映射 数据并行 geometric operation resampling data mapping data parallelism
  • 相关文献

参考文献6

  • 1KOREN I. Computer arithmetic algorithms[ M ]. Englewood Cliffs:Prentice Hall, 1993.
  • 2KANADE T, MORITA T. A sequential factorization method for recovering shape and motion from image streamsr[ C]. In Proc. of the ARPA Image Understanding Workshopr San Fransisco: Morgan Kaufmann Publishers, 1994,2:1177 -1188.
  • 3WEN Y H, CARPENTER B, ZHANG G S, et al. Java data parallel extensions with runtime system support[ C]. Fifth International Conference on High Performance Computing Washington, DC, USA: IEEE Computer Society. 1998:12 -17.
  • 4OWENS J D, RIXNER S, KAPASI U J, et al. Media processing applications on the imagine stream processor[ C]. Proceedings of International Conference on Computer Design, Freiburg Germany: 2002:295 -302.
  • 5KOZYRAKIS C. Scalable vector media - processors for embedded systems [ M ]. UC Berkeley, C. Ph.D. dissertation, 2002.
  • 6EFFORD N. Digital image processing: A practical introduction using java [ M ]. Addison Wesley, Harlow, UK : Pearson Education Limited, 2000.

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