期刊文献+

基于抗噪声ICA的高光谱数据特征提取方法 被引量:7

Noise robust ICA feature extraction algorithm for hyperspectral image
在线阅读 下载PDF
导出
摘要 特征提取是高光谱数据应用的一个重要环节,用于将高光谱数据中具有特殊性质的地物分离出来并去除冗余信息.提出了一种使用独立成分分析(ICA,Independent Component Analysis)进行高光谱遥感地物特征提取的方法.为了解决ICA对噪声过分敏感的问题,采用最大噪声分量(MNF,Maximum Noise Fraction)算法替代传统的主成分分析对数据作降噪处理,由MNF引出的不完全独立成分分析(UICA,Undercomplete ICA)在不牺牲特征提取能力的情况下能够获得很高的运算效率.给出了HYDICE和PHI的数据试验结果,分别测试了算法在时间效率和特征提取能力方面的性能,证明了该算法具有预期的性能. Feature extraction is important to hyperspectral imagery processing in that it can distinguish special featured object from background clutter and remove redundant information. An ICA(independent component analysis) based on the feature extraction algorithm for hyperspectral remote sensing data is proposed. In order to handle the over-sensitivity of ICA to noise and data imperfection, the MNF(maximum noise fraction) is adopted as the replacement of conventional principal component analysis. The UICA(undercomplete ICA) led by the MNF not only raises the time efficiency, but also maintains the extracting ability of ICA. The performance of the algorithm is verified by the results of HYIDCE and PHI experiments.
作者 杜鹏 赵慧洁
出处 《北京航空航天大学学报》 EI CAS CSCD 北大核心 2005年第10期1101-1105,共5页 Journal of Beijing University of Aeronautics and Astronautics
基金 总装备部预研基金资助项目
关键词 高光谱遥感 特征提取 独立成分分解 抗噪声 最大噪声分量 hyperspectral remote sensing feature extraction independent component analysis noise robust maximum noise fraction
  • 相关文献

参考文献12

  • 1Neil H Timm. Applied Multivariate Analysis[M]. Springer, 2002.
  • 2Tadjudin Saldju, Landgrebe David. Classification of high dimensional data with limited training [EB/OL].http://dynamo.ecn.purdue.edu/~landgreb/Saldju_TR.pdf.
  • 3Hsu H P, Tseng H Y. Feature extraction for hyperspectral image[A]. Proc. 20th ACRS[C]. Hong Kong, 1999,1:405~410.
  • 4Hyvrinen A, J Karhunen, Oja E. Independent component analysis[M].Wiley, 2001.
  • 5Stefan A Robila, Pramod K Varshney. Target detection in hyperspectral images based on independent component analysis[A]. Proc. SPIE Int. Soc. Opt. Eng[C]. Orlando, USA, 2002.
  • 6Chiang Shao-Shan, Chang Chein-I, Ginsberg I W. Unsupervised hyperspectral image analysis using independent component analysis [A]. Geoscience and Remote Sensing Symposium, 2000 Proceedings. IGARSS 2000 IEEE 2000 International Vol.7[C]. 2000. 3136~3138.
  • 7Shah C A, Arora M K, Robila S A, et al. ICA mixture model based unsupervised classification of hyperspectral imagery [A]. 31st Applied Imagery Pattern Recognition Workshop, 2002. Proceedings[C]. 2002. 29~35.
  • 8Green A A, Berman M, Switzer P, et al . A transformation for ordering multispectral data in terms of image quality with implications for noise removal[J]. Geoscience and Remote Sensing, IEEE Transactions on, 1988, 26(1):65~74.
  • 9Lee J B, Woodyatt A S, Berman M. Enhancement of high spectral resolution remote-sensing data by a noise-adjusted principal components transform[J]. Geoscience and Remote Sensing, IEEE Transactions on, 1990, 28(3):295~304.
  • 10Cheriyadat A, Bruce L M. Why principal component analysis is not an appropriate feature extraction method for hyperspectral data [A]. Geoscience and Remote Sensing Symposium, 2003. IGARSS '03. Proceedings. 2003 IEEE International.Vol.6[C]. 2003. 3420~3422.

同被引文献92

引证文献7

二级引证文献54

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