西南石油大学学报(自然科学版) ›› 2008, Vol. 30 ›› Issue (5): 148-151.DOI: 10.3863/j.issn.1000-2634.2008.05.035

• 石油机械工程及其它 • 上一篇    下一篇

信号稀疏表示的研究及应用

程文波1,2王华军2   

  1. 1.宜宾学院物理学与电子信息系,四川宜宾644007;2.成都理工大学信息工程学院,四川成都610059
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-10-20 发布日期:2008-10-20

THE RESEARCH AND APPLICATION OF SPARSE SIGNAL REPRESENTATION

CHENG Wen-bo1,2WANG Hua-jun2   

  1. 1.Department of Physics and Electronic Information,Yibin University,Yibin Sichuan 644007,China; 2.College of Information Engineering,Chengdu University of Technology,Chengdu Sichuan 610059,China;
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-10-20 Published:2008-10-20

摘要:

针对传统的信号分解方法中所存在的一旦信号的特性与基函数不完全匹配时,所分解的结果不一定是信号的稀疏表示的问题,在分析传统信号分解方法不足的基础上,从确定性信号与随机信

号两方面探讨了基于过完备原子库的信号稀疏表示算法的特点及其应用,就国内外信号稀疏表示研究的发展状况,进行了对比性分析,指出基于过完备原子库的信号稀疏表示方法不但能有效实现数

据的高效压缩,而且可以提高变换域的分辨率,相对于传统方法具有独特优越的性能,该方法对运用高分辨遥感影像进行油气勘探的数据表达将产生积极作用。

关键词: 过完备原子库, 稀疏成份分析, 高分辨遥感, 油气勘探, 数据表达

Abstract: Aiming at the problems that the decomposition is not necessarily the sparse signal representation while the characteristic of signal is not completely in accordance with orthogonalbasis function in traditional signal decomposition,the characteristic abd of application of sparse signal representation algorithm are probed from the aspects of certainsignal and randomsignal based on overcomplete dictionary of atoms as well as analyzing the shortcoming of traditional signal decomposition,the development and current situation of sparse signal representation both home and abroad are correlated and studied,it is pointed out that the sparse signal representation of overcomplete dictionary of atoms can effectively realized high efficiency compression,but also enhance the resolution of transformation domain,and possesses unique superiority compared with traditional method.The technology will play an active role in data representation of hydrocarbon exploration by means of high resolution remote sensing imagination.

Key words: over-complete dictionary of atoms, sparse component analysis, highresolution remote sensing, oil-gas exploration, data representation

中图分类号: