期刊文献+

基于像元混合模型估计的高光谱图像解混 被引量:3

Hyperspectral Unmixing Based on Estimation of Pixels Mixing Models
下载PDF
导出
摘要 在高光谱图像中,线性混合像元和非线性混合像元同时存在,若采用基于单一混合模型的解混算法,会使解混精度降低。因此,提出采用神经网络对高光谱图像中的像元混合模型进行估计,然后针对不同的混合模型进行相应的像元解混。像元解混时,在目标函数中添加丰度非负和丰度和为一约束项,利用差分搜索算法优化求解目标函数以实现高光谱图像的解混。仿真和实际高光谱数据实验表明,本算法提高了解混精度,适用于线性和非线性混合模型。 Both linear and nonlinear mixing pixels exist in the hyperspectral images. The unmixing accuracy will decrease if the unmixing algorithm is only based on a single mixing model. In this paper, we propose to adopt neural network to estimate the pixels mixing model in the hyperspectral images, and then unmix the pixels under different mixing models. To achieve the hyperspectral unmixing, we introduce the abundance non-negative constraint and abundance sum-to-one constraint to the objective function, and then the differential search algorithm is used to optimize the objective function. The experimental results on simulated data and real hyperspectral data demonstrate that the proposed algorithm can improve the accuracy of the unmixing, and it can be applied to linear and nonlinear mixing models.
出处 《红外技术》 CSCD 北大核心 2016年第2期132-137,共6页 Infrared Technology
基金 国家自然科学基金资助项目(61401307) 中国博士后科学基金资助项目(2014M561184) 天津市应用基础与前沿技术研究计划资助项目(15JCYBJC17100)
关键词 高光谱图像解混 神经网络 像元混合模型 差分搜索算法 hyperspectral images unmixing, neural network, pixels mixing model, differential search algorithm
  • 相关文献

参考文献15

  • 1KESHAVA N, MUSTARD J F. Spectral unmixing[J]. Signal Processing Magazine of IEEE, 2002, 19(1): 44-57.
  • 2HAPKE B. Bidirectional reflectance spectroscopy: 1. Theory[J]. Journal of Geophysical Research: Solid Earth(1978-2012), 1981, 86(B4): 3039-3054.
  • 3VERHOEF W. Light scattering by leaf layers with application to canopy reflectance modeling: the SAIL model[J]. Remote Sensing of Environment, 1984, 16(2): 125-141.
  • 4NASCIMENTO J M P, BIOUCAS-Dias J M. Nonlinear mixture model for hyperspectral unmixing[C]//Proceedings of SPIE on Image and Signal Processing for Remote Sensing XV, 2009, 7477: doi: 10.1117 /12.830492.
  • 5FAN W, HU B, MILLER J, et al. Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated-forest hyperspectral data[J]. International Journal of Remote Sensing, 2009, 30(11): 2951-2962.
  • 6CIVICIOGLU P. Transforming geocentric cartesian coordinates to geodetic coordinates by using differential search algorithm[J]. Computers & Geosciences, 2012, 46: 229-247.
  • 7ALTMAN Y, HALIMI A, DOBIGEON N, et al. Supervised nonlinear spectral unmixing using a post nonlinear mixing model for hyper- spectral imagery[J]. IEEE Transactions on Image Processing, 2012, 21(6): 3017-3025.
  • 8COMBE J P, LAUNEAU P, CARRèRE V, et al. Mapping micro- phytobenthos biomass by non-linear inversion of visible-infrared hyperspectral images[J]. Remote Sensing of Environment, 2005, 98(4): 371-387.
  • 9普晗晔,王斌,夏威.约束最小二乘的高光谱图像非线性解混[J].红外与毫米波学报,2014,33(5):552-559. 被引量:9
  • 10吴柯,张良培,李平湘.一种端元变化的神经网络混合像元分解方法[J].遥感学报,2007,11(1):20-26. 被引量:25

二级参考文献25

  • 1吴波,张良培,李平湘.高光谱端元自动提取的迭代分解方法[J].遥感学报,2005,9(3):286-293. 被引量:17
  • 2范闻捷,徐希孺.混合像元组分信息的盲分解方法[J].自然科学进展,2005,15(8):993-999. 被引量:7
  • 3吴波,张良培,李平湘.基于光谱维小波特征的混合像元投影迭代分解[J].电子学报,2005,33(11):1933-1936. 被引量:7
  • 4朱述龙 张占睦.遥感图像获取与分析[M].北京:科学出版社,2000.4.
  • 5Plaza A,Martinez P,Perez R.A Quantitative and Comparative Analysis of Endmember Extracion Algorithms From Hyperspectral Data[J].IEEE Trans.Geoscience and Remote Sensing,2004,42(3):650-663.
  • 6Tu T M,Huang P S,Chen P Y.Blind Separation of Spectral Signatures in Hyperspectral Imagery[J].IEEE Proc.-Vis.Image Signal Process,2001,148(4):217-225.
  • 7Liu W,Gopal S,Woodcock C.ARTMAP Multisensor/resolution Framework for Land Cover Characterization[A].The 4th International Conference on Information Fusion,Montreal,Canada[C].7-10 August,2001,WeC2-11-WeC2-16.
  • 8Ichoku Charles,Karnieli Arnon.A Review of Mixture Modeling Techniques for Sub Pixel Land Cover Estimation[J].Remote Sensing Review,1996,13:161-186.
  • 9Ju J,Kolaczyk E D,Gopal S.Gaussian Mixture Discriminant Anlaysis and Sub-pixel Land Cover Characterization in Remote Sensing[J].Remote Sensing of Environment,2003,84:550-560.
  • 10DeFries R,Townshend J,Hansen M.Continuous Fields of Vegetationcharacteristics at the Global Scale at 1-km Resolution[J].Journal of Geophysical Research,1999,104:16911-16923.

共引文献32

同被引文献17

引证文献3

二级引证文献3

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