Please wait a minute...
img

官方微信

遥感技术与应用  2006, Vol. 21 Issue (2): 115-119    DOI: 10.11873/j.issn.1004-0323.2006.2.115
技术研究与图像处理     
基于独立成分分析和神经网络的高光谱遥感数据分类
宋江红, 冯 燕
  ( 西北工业大学电子信息学院, 陕西 西安 710072)
Hyperspectral Data Classification by Independent Component Analysis and Neural Network
SONG Jiang-hong, FENG Yan
( Institute of Electronic Information, Northwestern Polytechnical University , X i'an 710072, China)
 全文: PDF 
摘要:

高光谱遥感数据以数据量大、含混度高、地面样本数据少的特点给分类处理带来了困难。将独立成分分析技术与多层前向神经网络相结合, 得到一种新的分类算法。独立成分分析在提取有效光谱特征的同时, 大大降低了数据的维数。神经网络作为分类器, 分类精度显著高于传统的bayes 分类器。通过对220 波段的高光谱数据进行实验, 得到了良好的效果。

关键词: 高光谱分类独立成分分析特征提取 神经网络    
Abstract:

The basic premise of hyperspectral data classification is that the spectral features of various materials are different from each other. With the development of sensor technology , hyperspectral sensor can collect in as many as several hundreds spectral bands at once. The hyperspectral data, which features high spectral resolution, also brings great difficult ies to classification. Because of the high dimension of data, great confusion and limited samples, the performance of traditional algorithms in hyperspectral data classification is deteriorated. In this paper a new combined algorithm based on independent component analysis( ICA) and neural network is proposed. Firstly, the independent component analysis algorithm is
used for feature abstraction. The spectral features are assumed to be a linear mixture of constituent spectra from the material types. The independent components are informative for classification, meanwhile the number of independent components is much smaller than the bands of original data. Then the multi-layer feed-forward neural network is used for classification. The spectral features of each pixel are used to be the input vector of neural network. The neural network is trained by Levenberg-Marquardt back-propagation ( LMBP) algorithm. The classification precision is remarkably superior to that of the conventional bayes classsifier. It proves by the experiment upon the 220-band hyperspectral data that the performance of this
combined algorithm is satisfying .

Key words:  Hyperspectral    Classification    Independent component analysis    Feature abstraction    Neural network
收稿日期: 2005-10-25 出版日期: 2011-09-27
:  TP 75   
作者简介: 宋江红( 1981- ) , 男, 硕士研究生, 主要从事遥感信息处理方面的研究。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

宋江红, 冯 燕. 基于独立成分分析和神经网络的高光谱遥感数据分类[J]. 遥感技术与应用, 2006, 21(2): 115-119.

SONG Jiang-hong, FENG Yan. Hyperspectral Data Classification by Independent Component Analysis and Neural Network. Remote Sensing Technology and Application, 2006, 21(2): 115-119.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2006.2.115        http://www.rsta.ac.cn/CN/Y2006/V21/I2/115


〔1〕 曾志远. 卫星遥感图像计算机分类与地学应用研究〔M〕. 北京: 科学出版社, 2004.
〔2〕 Lillesand M T , Kiefer R W. 遥感与图像解译〔M〕. 北京: 电子工业出版社, 2003.
〔3〕 Hagan M T, Demuth H B, Beale M H. 神经网络设计〔M〕.北京: 工业出版社, 2002.
〔4〕 Aapo Hyvarin en. A Family of Fixed-Point Algorithms For Independent Component Analysis 〔J〕. IEEE Transactions on
Neural Networks , 1997, ( 10) : 3917~3920.
〔5〕 Aapo Hyvarinen. Fast and Robust Fixed-Point Algorithms for Independent Component Analysis 〔J〕. IEEE Transactions onNeural Networks , 1999, ( 10) : 626~634.
〔6〕 Wei Lu. Approach and Applications of Constrained ICA〔J〕IEEE Transactions on Neural Networks,2005,( 16 ):203~212.

[1] 汪子豪,秦其明,孙元亨. 基于BP神经网络的地表温度空间降尺度方法[J]. 遥感技术与应用, 2018, 33(5): 793-802.
[2] 冯姣姣,王维真,李净,刘雯雯. 基于BP神经网络的华东地区太阳辐射模拟及时空变化分析[J]. 遥感技术与应用, 2018, 33(5): 881-889.
[3] 谢旭,陈芸芝. 基于PSO-RBF神经网络模型反演闽江下游水体悬浮物浓度[J]. 遥感技术与应用, 2018, 33(5): 900-907.
[4] 王常颖,田德政,韩园峰,隋毅,初佳兰. 基于属性差决策树的全极化SAR影像海冰分类[J]. 遥感技术与应用, 2018, 33(5): 975-982.
[5] 陈伟民,张凌,宋冬梅,王斌,丁亚雄,许明明,崔建勇. 基于AdaBoost改进随机森林的高光谱图像地物分类方法研究[J]. 遥感技术与应用, 2018, 33(4): 612-620.
[6] 苏阳,祁元,王建华,徐菲楠,张金龙. 基于航空高光谱影像的额济纳绿洲土地覆被提取[J]. 遥感技术与应用, 2018, 33(2): 202-211.
[7] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[8] 郭宇柏,卓莉,陶海燕,曹晶晶,王芳. 基于空谱初始化的非负矩阵光谱混合像元盲分解[J]. 遥感技术与应用, 2018, 33(2): 216-226.
[9] 刘爱林,郭宝平,李岩山 . 基于离散粒子群算法的凸多模态高光谱图像端元提取研究[J]. 遥感技术与应用, 2018, 33(2): 227-232.
[10] 吴兴,张霞,孙雪剑,张立福,戚文超. SPARK卫星高光谱数据辐射质量评价[J]. 遥感技术与应用, 2018, 33(2): 233-240.
[11] 侯海艳,侯金,黄春林,王昀琛. 基于人工神经网络和AMSR2多频微波亮温的北疆地区雪深反演[J]. 遥感技术与应用, 2018, 33(2): 241-251.
[12] 杨朦朦,汪汇兵,欧阳斯达,范奎奎,戚凯丽. 基于双树复小波分解的BP神经网络遥感影像分类[J]. 遥感技术与应用, 2018, 33(2): 313-320.
[13] 李想,刘凯,朱远辉,蒙琳,于晨曦,曹晶晶. 基于资源三号影像的红树林物种分类研究[J]. 遥感技术与应用, 2018, 33(2): 360-369.
[14] 宋婷婷,付秀丽,陈玉,魏永明,王钦军,程先锋. 云南个旧矿区土壤锌污染遥感反演研究[J]. 遥感技术与应用, 2018, 33(1): 88-95.
[15] 刘慧珺,苏红军,赵-波. 基于改进萤火虫算法的高光谱遥感多特征优化方法[J]. 遥感技术与应用, 2018, 33(1): 110-118.