高光谱图像快速Gram行列式端元提取优化方法

doi:10.3969/j.issn.1001-506X.2019.09.01

系统工程与电子技术 ›› 2019, Vol. 41 ›› Issue (9): 1913-1921.doi: 10.3969/j.issn.1001-506X.2019.09.01

高光谱图像快速Gram行列式端元提取优化方法

许宁^1,2, 孙康⁴, 胡玉新^1,2,3, 耿修瑞^1,2,3

1. 中国科学院电子学研究所, 北京 100190; 2. 中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190; 3. 中国科学院大学, 北京 100049; 4. 中国电子科技集团公司第五十四研究所, 河北石家庄 050081

出版日期:2019-08-27 发布日期:2019-08-20

Improved endmember extraction method based on fast Gram determinant analysis for hyperspectral imagery

XU Ning^1,2, SUN Kang⁴, HU Yuxin^1,2,3, GENG Xiurui^1,2,3

1. Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China; 2. Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing 100190, China; 3. University of Chinese Academy of Sciences, Beijing 100049, China; 4. The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, China

Online:2019-08-27 Published:2019-08-20

摘要/Abstract

摘要：

高光谱图像快速Gram行列式端元提取算法基于高光谱图像最大单形体体积标准,具有容易理解、算法复杂度低、无需降维处理等特点,但是其在进行端元提取时,采用的计算公式仍需进行矩阵求逆,随着端元的逐个求解,矩阵维数增多导致计算量增加。由于端元提取时获得的端元Gram矩阵满足对称特性,引入埃尔米特矩阵(Hermitian matrix)分块求逆引理,简化矩阵求逆处理,优化快速Gram行列式端元提取方法。采用美国Cuprite矿区的机载可见光/红外成像光谱仪(airborne visible/infrared imaging spectrometer,AVIRIS)机载高光谱图像进行实验验证,并对该方法在不同初始化条件下的求解结果进行分析,结果表明快速Gram行列式端元提取方法会受到初始条件的影响,在端元、像元数量增加时所提方法可提升计算效率。

关键词: 端元提取, 分块矩阵求逆引理, 单形体体积, 线性混合模型, 高光谱图像

Abstract:

On the basis of the maximum volume criterion in the hyperspectral imagery, the fast Gram determinant-based endmember extraction algorithm (FGDA) has the characteristics of simplicity, low computational complexity and no dimensionality reduction needed. However, the inversion matrix needs to be calculated in the procedure of FGDA, which still leads to the expensively computational cost as the number of extracted endmembers grows. The block matrix inversion lemma is used to solve the problem due to the symmetry property of the endmember Gram matrix. The improved approach can raise the efficiency through taking advantages of the recursive relationship of the block inversion matrix. A sub-scene of airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral data collected over Cuprite mining site, Nevada, is used to validate the method and the results of different initial conditions for FGDA are also analyzed. Experimental results demonstrate FGDA is affected by its initial condition, and the proposed approach can improve the computational efficiency of FGDA as the number of endmembers and pixels in hyperspectral imagery increases.

Key words: endmember extraction, block matrix inversion lemma, simplex volume, linear mixture model, hyperspectral imagery

许宁, 孙康, 胡玉新, 耿修瑞. 高光谱图像快速Gram行列式端元提取优化方法[J]. 系统工程与电子技术, 2019, 41(9): 1913-1921.

XU Ning, SUN Kang, HU Yuxin, GENG Xiurui. Improved endmember extraction method based on fast Gram determinant analysis for hyperspectral imagery[J]. Systems Engineering and Electronics, 2019, 41(9): 1913-1921.

[1]	陈善学, 王欣欣. 基于空间预处理联合稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2021, 43(9): 2422-2429.
[2]	汪建均, 杨桂康, 冯泽彪. 加速寿命数据的贝叶斯建模与分析[J]. 系统工程与电子技术, 2021, 43(5): 1420-1429.
[3]	陈善学, 陈雯雯. 基于二级字典的联合稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2020, 42(3): 550-556.
[4]	宋晓瑞, 吴玲达, 郝红星, 孔舒亚. 高光谱图像修复算法的自适应稀疏编码实现[J]. 系统工程与电子技术, 2019, 41(9): 1922-1929.
[5]	陈善学, 周艳发, 漆若兰. 基于核函数的联合稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2018, 40(3): 692-698.
[6]	孟令博, 耿修瑞. 改进的主峭度分析算法及其在高光谱图像小目标检测中的应用[J]. 系统工程与电子技术, 2018, 40(12): 2855-2861.
[7]	陈善学, 屈龙瑶, 胡灿. 基于空间约束加权条件稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2016, 38(2): 442-449.

高光谱图像快速Gram行列式端元提取优化方法

Improved endmember extraction method based on fast Gram determinant analysis for hyperspectral imagery

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价