|Table of Contents|

Unsupervised Classification of Hyperspectral Images Based on Min-related-window

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2012年01期
Page:
86-90
Research Field:
Publishing date:

Info

Title:
Unsupervised Classification of Hyperspectral Images Based on Min-related-window
Author(s):
YUE JiangBAI Lian-faZHANG YiXU Hang-wei
School of Electronic Engineering and Optoelectronic Technology,NUST,Nanjing 210094,China
Keywords:
ex-spectral curves Bhattacharyya distance min-related-window image classification hyperspectral images
PACS:
TP751.1
DOI:
-
Abstract:
In order to improve classification accuracy and reduce discrete points,an unsupervised classification of hyperspectral images based on a min-related-window model is proposed.A variable called ex-spectral curve is introduced for target distinguishing;with this variable and spatial coherence property,the algorithm of inherited classification based on a pixel ’ s min-related-window is proposed.Bhattacharyya distance is used to measure an interlayer distance,and similar classes are combined to achieve the classification.AVIRIS data are utilized to evaluate the performance of the proposed algorithm,which is compared with K-MEANS and ISODATA.Experimental results show that the proposed algorithm outperforms K-MEANS and ISODATA in classification accuracy and has less discrete points.

References:

[1] 李娜,赵慧洁. 高光谱数据非监督分类的改进独立成分分析方法[J]. 国土资源遥感, 2011, 22( 2) : 70-74.
[2] 王凯,赵永强,程咏梅,等. 基于均值漂移和模糊积分融合的高光谱图像分类[J]. 光子学报,2010, 39( 1) : 188-192.
[3] 杨新,唐宏,宋金玲,等. 基于核方法的光谱角制图模型及其在高光谱图像分割中的应用[J]. 遥感信息, 2005,3 ( 6) : 20-23.
[4] Du Qian,Yang He. Similarity-based unsupervised band selection for hyperspectral image analysis[J]. IEEE Geoscience and Remote Sensing Society,2008,5( 4) : 564-568.
[5] 张钧萍,张晔. 基于多特征多分辨率融合的高光谱图像分类[J]. 红外与毫米波学报, 2004, 23( 5) : 345-348.
[6] 贾建华,焦李成. 空间一致性约束谱聚类算法用于图像分割[J]. 红外与毫米波学报, 2010, 29( 1) : 69-74.
[7] Jia Sen,Qian Yuntao. MRF based spatial complexity for hyperspectral imagery unmixing[A]. Joint IAPR International Workshop on Statistical Techniques in Pattern Recognition[C]. Hong Kong,China: SPR, 2006: 531-540.
[8] 张保民. 成像系统分析导论[M]. 北京: 国防工业出版社, 1992.
[9] 刘世才. 光辐射测量技术[M]. 北京: 国防工业出版社, 1991.
[10] 李庆波,李响,张广军. 一种基于光谱奇异值检测的高光谱遥感小目标探测方法[J]. 光谱学与光谱分析, 2008, 28( 8) : 1832-1836.
[11] 杜培军,陈云浩,方涛,等. 高光谱遥感数据光谱特征的提取与应用[J]. 中国矿业大学学报, 2003, 32( 5) : 500-504.
[12] 曹建农,关泽群,李德仁. 基于DMN 的高光谱图像分割方法研究[J]. 遥感学报, 2005,9 ( 5) : 596-603.
[13] Purdue University. AVIRIS image Indian Pine Test Site 3 [EB/OL]. ftp: / /ftp. ecn. purdue. edu /biehl / MultiSpec /92AV3C9. lan, 2006-08-30.

Memo

Memo:
-
Last Update: 2012-10-12