首页 > 论文 > 红外与激光工程 > 45卷 > 10期(pp:1028003--1)

应用监督近邻重构分析的高光谱遥感数据特征提取

Feature extraction of hyperspectral remote sensing data using supervised neighbor reconstruction analysis

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对高光谱遥感数据特征提取方法的研究, 提出了一种新的监督近邻重构分析(Supervised Neighbor Reconstruction Analysis, SNRA) 算法。该方法首先利用同一类别的近邻数据点对各数据点进行重构; 然后在低维嵌入空间中保持该重构关系不变, 尽可能地分离开非同类数据点, 并利用总体散度矩阵来约束数据间的相关性; 最后求解得到一个最佳投影矩阵, 进而提取出鉴别特征。SNRA算法不仅保持了同类数据的局部结构而且增强了非同类数据的可分性, 同时减少了数据的冗余信息。在Indian Pine和KSC高光谱遥感数据集上的实验结果表明: 提出的方法能更好地揭示出高光谱遥感数据的内在特性, 提取出更有效的鉴别特征, 改善分类效果。

Abstract

For the feature extraction methods of hyperspectral remote sensing data, a new method, called supervised neighbor reconstruction analysis(SNRA), was proposed. First, this method reconstructs each point with neighbor points from the same class. Then, it preserves the reconstruction relationship and separates the data points from different classes as far as possible in low-dimension embedding space. And a total scatter matrix is used to constrain the correlation between data points. Finally, it obtains an optimized projection matrix and extracts the discriminating feature. SNRA not only preserves the local structures of intraclass data but also enhances the separability of interclass data. And it reduces the redundant information. The experiments on Indian Pine and KSC hyperspectral remote data sets show that the proposed method can better reveal the intrinsic property of hyperspectral remote sensing data and effectively extract the discriminating feature to improve the classification result.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP751

DOI:10.3788/irla201645.1028003

所属栏目:景象信息处理

基金项目:国家自然科学基金(理论物理专项)(11547196); 四川省教育厅重点资助(15ZA0229); 四川理工学院人才引进资助(2013RC07)

收稿日期:2016-02-11

修改稿日期:2016-03-05

网络出版日期:--

作者单位    点击查看

方 敏:四川理工学院 理学院, 四川 自贡 643000
王 君:四川理工学院 理学院, 四川 自贡 643000
王红艳:四川理工学院 理学院, 四川 自贡 643000
李天涯:四川理工学院 理学院, 四川 自贡 643000

联系人作者:方敏(fangmin631114@163.com)

备注:方敏(1963-), 女, 副教授, 硕士, 主要从事光学信息处理、高光谱遥感信息处理、光谱分析等方面的研究。

【1】Tang Y Y, Yuan H L, Li L Q. Manifold-based sparse representation for hyperspectral image classification [J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(12): 7606-7618.

【2】Wang Xiaofei, Hou Chuanlong, Yan Qiujing, et al. Noise estimation algorithm based on relevance vector machine for hyperspectral imagery [J]. Infrared and Laser Engineering, 2014, 43(12): 4159-4163. (in Chinese)
王晓飞, 侯传龙, 阎秋静, 等. 基于相关向量机的高光谱图像噪声评估算法[J]. 红外与激光工程, 2014, 43(12): 4159-4163.

【3】Cai Hui, Li Na, Zhao Huijie. Features extraction method based on intrinsic mode function for hyperspectral data [J]. Infrared and Laser Engineering, 2013, 42(12): 3475-3480. (in Chinese)
蔡辉, 李娜, 赵慧洁. 基于本征模函数的高光谱数据特征提取方法[J]. 红外与激光工程, 2013, 42(12): 3475-3480.

【4】Pu Hanye, Wang Bin, Zhang Liming. New dimensionality reduction algorithms for hyperspectral imagery based on manifold learning [J]. Infrared and Laser Engineering, 2014, 43(1): 232-237. (in Chinese)
普晗晔, 王斌, 张立明. 基于流形学习的新高光谱图像降维算法[J]. 红外与激光工程, 2014, 43(1): 232-237.

【5】Ding L, Tang P, Li H Y. Subspace feature analysis of local manifold learning for hyperspectral remote sensing images classification[J]. Applied Mathematics & Information Sciences, 2014, 8(4): 1987-1995.

【6】Bachmann C M, Ainsworth T L, Fusina R A. Exploiting manifold geometry in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 884-897.

【7】He X, Niyogi P. Locality preserving projections[C]//Proceedings of the 17th Annual Conference on Neural Information Processing Systems, 2004, 16: 153-160.

【8】He X F, Cai D, Yan S C, et al. Neighborhood preserving embedding[C]//Proceedings of the 10th IEEE International Conference on Computer Vision, 2005: 1208-1213.

【9】Jin Zhong, Yang Jingyu, Lu Jianfeng. An optimal set of uncorrelated discriminant features [J]. Chinese Journal of Computers, 1999, 22(10): 1105-1108. (in Chinese)
金忠, 杨静宇, 陆建峰. 一种具有统计不相关性的最佳鉴别矢量集[J]. 计算机学报, 1999, 22(10): 1105-1108.

【10】Yan S, Xu D, Zhang B, et al. Graph embedding and extensions: a general framework for dimensionality reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51.

引用该论文

Fang Min,Wang Jun,Wang Hongyan,Li Tianya. Feature extraction of hyperspectral remote sensing data using supervised neighbor reconstruction analysis[J]. Infrared and Laser Engineering, 2016, 45(10): 1028003

方 敏,王 君,王红艳,李天涯. 应用监督近邻重构分析的高光谱遥感数据特征提取[J]. 红外与激光工程, 2016, 45(10): 1028003

被引情况

【1】侯榜焕,姚敏立,贾维敏,沈晓卫,金 伟. 空谱结构保持的高光谱图像分类. 红外与激光工程, 2017, 46(同学12): 1228001--1

【2】侯榜焕,姚敏立,贾维敏,沈晓卫,金 伟. 空谱结构保持的高光谱图像分类. 红外与激光工程, 2017, 46(12): 1228001--1

【3】侯榜焕,姚敏立,贾维敏,张峰干,王道平. 面向高光谱图像分类的空谱判别分析. 光学 精密工程, 2018, 26(2): 450-460

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF