首页 > 论文 > 光学学报 > 30卷 > 7期(pp:2116-2122)

基于方差最小的高光谱目标探测算法研究

Research of Hyperspectral Target Detection Algorithms Based on Variance Minimum

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

目标探测技术是遥感理论与应用中的重要领域之一,由于高光谱遥感图像能够同时提供地物目标的辐射、几何和光谱信息,与其他多光谱遥感图像相比,能更好地进行目标识别。从信息论中的自信息概念出发,针对探测结果影像中目标突出且信息确定性强的特征,提出了基于方差最小(BVM)的目标检测算子。利用不同空间分辨率和光谱分辨率的高光谱影像数据进行实验,并与约束能量最小化(CEM)算子的应用效果进行了比较分析。实验结果表明,基于方差最小的算子具有更稳健的探测性能。

Abstract

Target detection is one of the most important aspects in remote sensing theory and application. Hyperspectral image can provide radiation,geometrical and spectral information of targets simultaneously,making target detection much better than other methods. A target detection algorithm based on variance minimum (BVM) which makes use of highlighting information of detection results is presented. And two experiments on different spatial resolution and spectral resolution are conducted to compare BVM method and constrained energy minimization (CEM). Results show the more robust performance of BVM method.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP751.1

DOI:10.3788/aos20103007.2116

所属栏目:遥感与传感器

基金项目:国家973计划(2009CB723902),国家863计划(2008AA12Z113)和国家自然科学基金(40901225)资助课题。

收稿日期:2009-07-02

修改稿日期:2009-09-22

网络出版日期:0001-01-01

作者单位    点击查看

李山山:中国科学院 对地观测与数字地球科学中心,北京 100101
张兵:中国科学院 对地观测与数字地球科学中心,北京 100101
高连如:中国科学院 对地观测与数字地球科学中心,北京 100101
彭嫚:中国科学院 遥感应用研究所,北京 100101

联系人作者:李山山(ssli@irsa.ac.cn)

备注:李山山|主要从事高光谱目标探测、分类等方面的研究|(1980-),男,博士研究生。

【1】Y. E. Shimabukuro,J. A. Smith. The least-squares mixing models to generate fraction images derived from remote sensing multispectral data[J]. IEEE Trans. Geoscience and Remote sensing,1991,29(1):16-20

【2】J. J. Settle,N. A. Drake. Linear mixing and estimation of ground cover proportions[J]. Int. J. Remote Sensing,1993,14(6):1159-1177

【3】E. A. Aston,A. Schaum. Algorithm for the detection of sub-pixel targets in multispectral imagery[J]. Photogrammetric Engineering and Remote Sensing,1998,64(7):723-731

【4】D. Heinz,C. -I. Chang. Fully constrained least squares linear mixture analysis method for material quantification in hypersyectral imagery[J]. IEEE Trans. Geoscience and Remote Sensing,2001,39(3):529-545

【5】C. -I. Chang,Qian Du,S. -S. Chiang et al.. Unsuperoised target sulpixel detection in hyperspectal imagery[C]. SPIE,2001,4381:370-379

【6】J. C. Harsanyi,C. -I Chang. Hyperspectral image classification and dimensionality reduction:an orthogonal subspace projection approach[J]. IEEE Trans. Geoscience and Remote Sensing,1994,32(4):779-785

【7】Sun Jixiang. Modern Pattern Recognition [M]. Changsha:National University of Defense Technology Press,2001. 213-227
孙即详. 现代模式识别[M]. 长沙:国防科技大学出版社,2001. 213-227

【8】Tai Sucai,Sun Wenyu,He Juanjuan. Applied Mathematical Statistics[M]. Wuhan:Wuhan University Press. 2005. 105-132
邰淑彩,孙韫玉,何娟娟. 应用数理统计[M]. 武汉:武汉大学出版社. 2005. 105-132

【9】Sheng Zhou,Xie Shiqian,Pan Chenyi. Probability Theory and Mathematical Statistics (the 3rd Edition)[M]. Hangzhou:Zhejiang University Press,2001. 150-198
盛骤,谢式千,潘承毅 等. 概率论与数理统计(第三版)[M]. 杭州:浙江大学出版社,2001. 150-198

【10】G. F. Hughes. On the mean accuracy of statistical pattern recognizers[J]. IEEE Trans. Information Theory,1968,IT-14(1):55-58

【11】Xun Lina,Fang Yonghua,Li Xin. A mall target detection approach based on endmember extraction in hyperspectral image[J]. Acta Optica Sinica,2007,27(7):1178-1182
寻丽娜,方勇华,李新. 高光谱图像中基于端元提取的小目标检测算法[J]. 光学学报,2007,27(7):1178-1182

【12】Li Na,Zhao Huijie,Jia Gruorui et al.. Anomaly detection based on extended mathematical morphology for hyperectral imagery[J]. Acta Optica Sinica,2008,28(8):1480-1484
李娜,赵慧洁,贾国瑞 等. 基于扩展数学形态学的高光谱图像异常检测[J]. 光学学报,2008,28(8):1480-1484

【13】He Lin,Pan Quan,Di Wei et al.. A mall-target detector based on single likelihood test for hyperspectral imagery[J]. Acta Optica Sinica,2007,27(12):2155-2162
贺霖,潘泉,邸韡 等. 一种基于单似然检测的高光谱图像小目标检测器[J]. 光学学报,2007,27(12):2155-2162

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF