基于多尺度分割的高光谱图像稀疏表示与分类

唐中奇; 付光远; 陈进; 张利

doi:10.3788/OPE.20152309.2708

您当前的位置：

首页 >

文章列表页 >

基于多尺度分割的高光谱图像稀疏表示与分类

信息科学 | 更新时间：2020-08-12

- 基于多尺度分割的高光谱图像稀疏表示与分类
- Multiscale segmentation-based sparse coding for hyperspectral image classification
- 光学精密工程 2015年23卷第9期页码：2708-2714
- 作者机构：
  
  1. 清华大学电子工程系北京,100084
  2. 北京市遥感信息研究所北京,100192
  3. 第二炮兵工程大学信息工程系,陕西西安,710025
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61132007,No.61202332)();中国博士后科学基金资助项目(No.2012M521905)()
- DOI：10.3788/OPE.20152309.2708
  中图分类号： TP751
- 收稿日期：2015-04-27，
  
  修回日期：2015-06-01，
  
  纸质出版日期：2015-09-25
- 稿件说明：
移动端阅览
唐中奇, 付光远, 陈进等. 基于多尺度分割的高光谱图像稀疏表示与分类[J]. 光学精密工程, 2015,23(9): 2708-2714

TANG Zhong-qi, FU Guang-yuan, CHEN Jin etc. Multiscale segmentation-based sparse coding for hyperspectral image classification[J]. Editorial Office of Optics and Precision Engineering, 2015,23(9): 2708-2714
唐中奇, 付光远, 陈进等. 基于多尺度分割的高光谱图像稀疏表示与分类[J]. 光学精密工程, 2015,23(9): 2708-2714 DOI： 10.3788/OPE.20152309.2708.

TANG Zhong-qi, FU Guang-yuan, CHEN Jin etc. Multiscale segmentation-based sparse coding for hyperspectral image classification[J]. Editorial Office of Optics and Precision Engineering, 2015,23(9): 2708-2714 DOI： 10.3788/OPE.20152309.2708.

摘要

针对高光谱特征的稀疏表示

提出了一种基于多尺度分割的空间加权算法用于高光谱图像分类。该算法采用更合理的邻域定义挖掘空间先验信息

优化类边缘像元的稀疏表示。首先

通过多尺度分割提供邻域空间约束;结合拉普拉斯尺度混合(LSM)先验

分别对每个邻域组内像元进行空间加权的稀疏表示。然后

采用概率支持向量机(SVM)分类

同时提供像元的分类标签及其置信度。最后

以此置信度为权重

对多尺度分类图进行加权融合

生成最终的分类图。实验显示

本文算法能够增强光谱特征表示的稀疏性和鲁棒性

提高总体分类精度;在小样本训练下

单类的分类精度可提升30%左右

表明该算法在高光谱应用中具有较强的实用性。

Abstract

For the sparse representation of hyperspectral characteristics

a spatial weighted algorithm based on multiscale segmentation is proposed for hyperspectral classification. The algorithm uses a more reasonable neighborhood definition to mine spatial prior information to optimize the sparse representation of a like-edge pixel. Firstly

spatial neighborhoods were obtained through multiscale segmentation

and Laplacian Scale Mixture

(LSM) priori was then combined for the spatial-weighted sparse representation of pixels in each neighborhood. Then

the probabilistic Support Vector Machine(SVM) was used to classify the hyperspectral images and to provide classification labels and their confidences. Finally

the multiscale segmentation was weighted by the confidence of each label and the classification map was obtained by the fusion of labels. Experiments show that the algorithm enhances the sparse and roughness characterized by spectral features and improves the classification accuracy. Under smaller sample training

the classification accuracy of single ground surface has increased by 30%

which verifies the practicability of the proposed algorithm in hyperspectral applications.

关键词

Keywords

references

CAMPS-VALLS G, TUIA D L, BRUZZONE J. Atli-Benediktsson. Advances in hyperspectral image classification [J]. IEEE Signal Process, 2014, 21(4):45-54.

李志敏, 张杰, 黄鸿, 等. 面向高光谱图像分类的半监督丛流形学习[J]. 光学精密工程, 2015, 23(5):1434-1442. LI ZH M, ZHANG J, HUANG H,et al.. Semi-supervised bundle manifold learning for hyperspectral image classification [J]. Opt. Precision Eng., 2015, 23(5):1434-1442. (in Chinese)

何勇, 陈纳, 刘飞, 等. 近红外高光谱成像技术快速鉴别国产咖啡豆品种[J]. 光学精密工程, 2015, 23(2):349-355. HE Y, CHEN N, LIU F, et al..Rapid identification of coffee bean variety by near infrared hyperspectral imaging technology [J]. Opt. Precision Eng., 2015, 23(2):349-355. (in Chinese)

BIOUCAS-DIAS J, PLAZA A, CAMPS-VALLS G, et al.. Hyperspectral remote sensing data analysis and future challenges [J]. IEEE Remote Sens., 2013, 1(2):6-36.

黄鸿, 曲焕鹏. 基于半监督稀疏鉴别嵌入的高光谱遥感影像分类[J]. 光学精密工程, 2014, 22(2):434-442. HUANG H, QU H P.Hyperspectral remote sensing image classification based on SSDE [J]. Opt. Precision Eng., 2014, 22(2):434-442. (in Chinese)

BIOUCAS-DIAS J M, PLAZA A, DOBIGEON N, et al.. Hyperspectral unmixing overview:Geometrical, statistical, sparse regression-based approaches[J]. IEEE J. Sel. Topics Appl. Earth Observ., 2012, 5(2):354-379.

MAIRAL J, BACH F, PONCE J. Task-driven dictionary learning [J]. IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34(4):791-804.

IORDACHE M, BIOUCAS-DIAS J, PLAZA A. Total variation spatial regularization for sparse hyperspectral unmixing [J]. IEEE Trans. Geosci. Remote Sens., 2012, 50(11):4484-4502.

CHEN Y, NASRABADI N M, TRAN T P. Hyperspectral image classification using dictionary-based sparse representation [J]. IEEE Trans. Geosci. Remote Sens., 2011, 49(10):3973-3985.

CHARLES A, OLSHAUSEN B, ROZELL C. Learning sparse codes for hyperspectral imagery [J]. IEEE Sel. Topics Signal Process, 2011, 5(5):963-978.

SOLTANI-FARANI A, RABIEE H R. When pixels team up:spatially weighted sparse coding for hyperspectral image classification[J]. IEEE Geosci. Remote Sens. Lett., 2015, 12(1):107-111.

TILTON J C. RHSEG User's Manual (version 1.47) [OL]. http://ipp.gsfc.nasa.gov/RHSEG, 2009.

TANG Z Q, FU G Y, YU X, et al.. A class-Oriented model for hyperspectral image classification through hierarchy-tree-based selection [C]. The 2nd International Sym. on Computer Vision in Remote Sens., Xiamen, P.R. China: CVRS, 2015, 2:1-4.

GARRIGUES P, OLSHAUSEN B A. Group sparse coding with a Laplacian scale mixture prior[C]. The 24th Annu. Conf. NIPS, 2010, 23:1-9.

CHANG C, LIN C. LIBSVM:A library for Support Vector Machines (Version 3.20) [CP]. http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2014.

AVIRIS NW Indiana's Indian Pines 1992 Data Set. [OL]. http://engineering.purdue.edu/~biehl/MultiSpec/hyperspectral.html, 1992.

浏览量

307

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向高光谱图像分类的空谱判别分析