全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于高光谱图像主成分分量的小目标检测算法研究

Keywords: 高光谱目标检测超平面小目标检测算法主成分分析遥感图像

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出了一种基于图像主成分分量的高光谱小目标检测算法.作为一种多元数据集合,通常高光谱数据形成的几何体是一个超平面.主成分分析能有效估计这一几何体的本征维数.显著特征值对应的主成分体现了几何体大部分信息;而不显著特征值对应的主成分则代表了正交于几何体的信息,而这些信息中则包含了重要的内容,例如目标特性。文中提出的方法就是利用这些不显著的主成分分量来进行小目标检测.该方法减少了对先验光谱信息的依赖,提高了算法的实用性.

References

[1]  Bruske J, Sommer G. Intrinsic dimensionality estimation with optimally topology preserving maps[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1998, 20(5): 572-575.
[2]  HU Guo-Ding, ZHANG Run-Chu. Multivariate Data Analysis[M]. Tianjin: NanKai university press(胡国定,张润楚.多元数据分析.天津:南开大学出版社), 1990.
[3]  XUE Yong-Qi, WANG Jian-Yu. Operative Modulor Imaging Spectrometer. Development of Information Acquisition and Processing Technology[M].Beijing: China Timbering Industral Publishing House(薛永祺,王建宇.实用型模块化机载成像光谱仪,信息获取与处理技术.北京: 中国建材工业出版社), 1998, 43-46.
[4]  Marcus Stavos Stefanou, Richard c Olsen, Herschel H Loomis. Signal Perspectives of Hyperspectral Imagery Analysis Techniques[R], 1998, AD-A333 254.
[5]  Dimitris Manolakis, Chrisitina Siracusa, David Marden, et al. Hyperspectral adaptive matched filter detectors:Practical performance comparison[J]. SPIE, 2001, 4381: 18-33.
[6]  Joseph C Harsanyi, CheinI Chang. Hyperspectral image classifacation and dimensionality reduction: An orthogonal subspace projection approach[J]. IEEE Trans. On Geoscience and Remote sensing, 1994, 32(4): 779-785.
[7]  Schaum A. Spectral subspace matched filtering[J]. SPIE, 2001, 4381: 1-17.
[8]  David Gillis, Peter Palmadesso, Jeffrey Bowles. An automatic target recognition system for hyperspectral imagery using ORASIS[J]. SPIE, 2001, 4381: 34-43.
[9]  Manolakis D, Shaw G. Detection algorithms for hyperspectral imaging applications[J]. IEEE Signal Processing Magazine, 2002, 19(7): 29-43.
[10]  Peter j Verveer, Robert P W Duin. An evaluation of intrinsic dimensionality estimators[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1995, 17(1): 81-85.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133