基于光谱知识的高光谱图像自动识别方法

牛志宇; 赵慧洁

基于光谱知识的高光谱图像自动识别方法

北京航空航天大学仪器科学与光电工程学院, 北京 100191

基金项目: 国家863计划资助项目(2008AA121102,2008AA12A201); 国家自然科学基金资助项目(61008047); 长江学者和创新团队发展计划资助项目(IRT0705)

详细信息

中图分类号: TP 751.1
计量
- 文章访问数: 2690
- HTML全文浏览量: 79
- PDF下载量: 814
- 被引次数: 0
出版历程
- 收稿日期: 2010-11-03
- 网络出版日期: 2012-02-29

Automatic recognition of hyperspectral image based on spectral knowledge

School of Instrument Science and Opto-electronics Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 针对传统高光谱图像矿物识别方法未能充分利用矿物光谱诊断吸收特征与矿物光谱知识、识别过程人为干预多等问题,提出了一种基于光谱知识的高光谱图像自动识别方法.该方法引入了基于光谱吸收特征与波形特征的光谱知识作为自动识别的标准,利用连续统去除操作增强光谱吸收特征,采取基于光谱主次吸收特征的识别决策策略,建立多级约束准则以提高识别精度及避免误识别,通过利用模拟数据进行算法精度评价并应用航空高光谱成像仪AVIRIS(Airborne Visible/Infrared Imaging Spectrometer)数据进行应用分析与验证.结果表明:当图像信噪比大于200时,识别准确率可以达到80.3%,能够得到良好的识别结果以及较高的精度,并实现了基于高光谱图像的矿物自动识别.
- 高光谱遥感 /
- 自动识别 /
- 光谱吸收特征
Abstract: In order to solve the problems of current methods for mineral recognition from hyperspectral data, such as the requirement for prior information, the failure to make full use of absorption features and the lack of the automation of recognition process, an automatic recognition approach based on the spectral knowledge was proposed. The spectral knowledge library including the spectral information and absorption features was generated as the recognition standard, in which the absorption features were enhanced by removing the continuum of image spectra and library spectra as well. The decision method was proposed based on the major and minor absorption features, and a multi-constraint criterion was established to improve the recognition accuracy and avoid the false recognition. The accuracy evaluation of the proposed approach was performed on the simulated data and the airborne visible/infrared imaging spectrometer (AVIRIS) data as well. Experimental results show that the recognition accuracy reaches 80.3% when the signal-to-noise of image is higher than 200. Fine results with the high accuracy are obtained by the proposed approach, and the mineral automatic recognition from hyperspectral data is achieved simultaneously.
- hyperspectral remote sensing /
- automatic recognition /
- spectral absorption feature

HTML全文

参考文献(10)

[1]	王润生,杨苏明,阎柏琨.成像光谱矿物识别方法与识别模型评述[J].国土资源遥感,2007,71(1):1-9 Wang Runsheng,Yang Suming,Yan Baikun.A review of mineral spectral identification methods and models with imaging spectrometer[J].Remote Sensing for Land & Resources,2007,71(1):1-9(in Chinese)
[2]	赵慧洁,李娜,贾国瑞,等.改进独立成分分析在高光谱图像分类中的应用[J].北京航空航天大学学报,2006,32(11):1333-1336 Zhao Huijie,Li Na,Jia Guorui,et al.Improved independent component analysis applied to classification hyperspectral imagery[J].Journal of Beijing University of Aeronautics and Astronautics,2006,32(11):1333-1336(in Chinese)
[3]	黄光玉,沈占锋,赵欣梅.高光谱遥感矿物识别方法研究[J].资源环境与工程,2007,21(1):50-54 Huang Guangyu,Shen Zhanfeng,Zhao Xinmei.Discussion for discrimination method of mineral using hyperspectral remote sensing[J].Resources Environment & Engineering,2007,21(1):50-54(in Chinese)
[4]	白继伟.基于高光谱数据库的光谱匹配技术研究 .北京:中国科学院遥感应用研究所,2002 Bai Jiwei.The study on the spectral mapping technique based on the hyperspectral database .Beijing:Institute of Remote Sensing Application,China Academy of Sciences,2002(in Chinese)
[5]	Clark R N,Swayze G A,Livo K E,et al.Imaging spectroscopy:earth and planetary remote sensing with the USGS tetracorder and expert systems[J].Journal of Geophysical Research,2003,108(12):1-44
[6]	李兴.高光谱数据库及数据挖掘研究 .北京:中国科学院遥感应用研究所,2006 Li Xing.Research on hyperspectral database and hyperspectral data mining .Beijing:Institute of Remote Sensing Application,China Academy of Sciences,2006(in Chinese)
[7]	Du Peijun.Feature extraction for target identification and image classification of OMIS hyperspetral image[J].Mining Science and Technology,2009,19(6):835-841
[8]	燕守勋,张兵.高光谱遥感岩矿识别填图的技术流程与主要技术方法综述[J].遥感技术与应用,2004,19(1):52-63 Yan Shouxun,Zhang Bing.Summarizing the technical flow and main approaches for discrimination and mapping of rocks and minerals using hyperspectral remote sensing[J].Remote Sensing Technology and Application,2004,19(1):52-63(in Chinese)
[9]	Swayze G A,Clark R N,Goetz A F H,et al.Effects of spectrometer band pass,sampling,and signalto-noise ratio on spectral identification using the Tetracorder algorithm[J].Journal of Geophysical Research,2003,108(E9):5105-5134
[10]	梁继,王建,王建华.基于光谱角分类器遥感影像的自动分类和精度分析研究[J].遥感技术与应用,2002,17(6):299-303 Liang Ji,Wang Jian,Wang Jianhua.Study on automatic classification and accuracy analysis of remote sensing image based on SAM[J].Remote Sensing Technology and Application,2002,17(6):299-303(in Chinese)