测绘学报 ›› 2015, Vol. 44 ›› Issue (7): 775-781.doi: 10.11947/j.AGCS.2015.20140207

• 摄影测量学与遥感 • 上一篇    下一篇

空-谱信息与稀疏表示相结合的高光谱遥感影像分类

杨钊霞, 邹峥嵘, 陶超, 田彦平, 何小飞   

  1. 中南大学地球科学与信息物理学院, 湖南 长沙 410083
  • 收稿日期:2014-04-23 修回日期:2014-10-28 发布日期:2015-07-28
  • 通讯作者: 陶超,E-mail:kingtaochao@126.com E-mail:kingtaochao@126.com
  • 作者简介:杨钊霞(1990-),女,硕士,研究方向为高光谱遥感影像分类。E-mail:yzxnice@163.com
  • 基金资助:

    国家973计划(2012CB719903);国家自然科学基金(41301453);中国博士后科学基金(2013M530361);教育部博士点基金(20130162120027)

Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation

YANG Zhaoxia, ZOU Zhengrong, TAO Chao, TIAN Yanping, HE Xiaofei   

  1. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
  • Received:2014-04-23 Revised:2014-10-28 Published:2015-07-28
  • Supported by:

    The National Basic Research Program of China(973 Program)(No.2012CB719903);The National Natural Science Foundation of China(No.41301453);The China Postdoctoral Science Foundation(No.2013M530361);Research Fund for the Doctoral Program of Higher Education(No.20130162120027)

摘要:

针对传统的高光谱遥感影像分类中多依赖光谱信息而忽视空间信息以及提取的特征维数高的问题,提出了一种空-谱信息与稀疏表示相结合的分类算法。首先,利用最小噪声分离对原始影像进行降维,在此基础上,对主成分图上局部影像块内的所有像素进行重组,并用排序的方法得到旋转不变的空-谱特征。然后,对空-谱特征进行监督学习得到字典,并将提取的测试样本的空-谱特征编码到字典中以得到测试样本的稀疏表示。最后,使用支持向量机分类器(SVM)对高光谱影像进行分类。3组高光谱数据试验表明,与传统的分类方法比较,本文方法能有效提高分类精度。

关键词: 高光谱影像, 最小噪声分离, 空-谱特征, 字典学习, 稀疏表示

Abstract:

In order to avoid the problem of being over-dependent on high-dimensional spectral feature in the traditional hyperspectral image classification, a novel approach based on the combination of spatial-spectral feature and sparse representation is proposed in this paper. Firstly, we extract the spatial-spectral feature by reorganizing the local image patch with the first d principal components(PCs) into a vector representation, followed by a sorting scheme to make the vector invariant to local image rotation. Secondly, we learn the dictionary through a supervised method, and use it to code the features from test samples afterwards. Finally, we embed the resulting sparse feature coding into the support vector machine(SVM) for hyperspectral image classification. Experiments using three hyperspectral data show that the proposed method can effectively improve the classification accuracy comparing with traditional classification methods.

Key words: hyperspectral image, minimum noise fraction, spatial-spectral feature, dictionary learning, sparse representation

中图分类号: