自适应冗余字典学习的高光谱混合像元解混

王蕊; 李恒超; 尹忠科

doi:10.3969/j.issn.0258-2724.2014.04.006

自适应冗余字典学习的高光谱混合像元解混

doi: 10.3969/j.issn.0258-2724.2014.04.006

基金项目:

国家自然科学基金资助项目（61371165）

教育部新世纪优秀人才支持计划资助项目（NCET-11-0711）

四川省青年科技创新研究团队项目（2011JTD0007）

中央高校基本科研业务费专项资金资助项目（SWJTU11CX038，SWJTU12CX004，SWJTU12ZT02）

四川省百人计划资助项目（SWJTU2011BR017EM）

计量
- 文章访问数: 1242
- HTML全文浏览量: 66
- PDF下载量: 729
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-01
- 刊出日期: 2014-08-25

Hyperspectral Sparse Unmixing via Adaptive Overcomplete Dictionary Learning

摘要

摘要: 针对线性稀疏解混模型无法准确识别真实端元造成丰度估计误差较大的问题，本文提出一种基于自适应冗余字典的高光谱混合像元解混算法.该算法根据地物在空间上的连续性，以及高光谱数据中信号成分与光谱库中物质光谱的强相关性，首先保留每个像元在光谱库上投影系数大于设定阈值所对应的光谱，将其作为与每个像元信号成分最匹配的光谱集合；然后合并该集合以构建高光谱数据的自适应冗余字典；最后利用ADMM算法求解高光谱数据在该字典上的丰度矩阵.仿真和实际高光谱数据实验结果表明，本文所提出的算法可减小丰度估计误差，在信噪比为15~35 dB时，其丰度估计准确性高于性能较优的SUnSAL算法约1~2 dB.
- 高光谱 /
- 图像 /
- 稀疏 /
- 解混 /
- 自适应
Abstract: In the linear sparse unmixing model of hyperspectral data, large estimation error of the fractional abundances of endmembers in each mixed pixel may be caused by the incorrect identification of endmembers. A novel sparse unmixing algorithm was proposed based on adaptive overcomplete dictionary. Firstly, according to the spatial continuity of ground objects and the strong correlation between signal components of the hyperspectral data and spectral signatures in the library, the signatures with the projection coefficients of each pixels larger than the preset threshold were grouped as an optimal subset of signatures that best match the signal component of each mixed pixel. Secondly, an adaptive overcomplete dictionary of hyperspectral data was constructed by combining such subsets. Finally, the fractional abundances in this dictionary were obtained using the alternating direction method of multipliers (ADMM). Experimental results on synthetic and real hyperspectral data show that the proposed algorithm improves the accuracy of identifying endmembers, with the reduced abundance estimation error r. When the signal to noise ratio range from 15 to 35 dB, the accuracy of the abundance estimation is improved about 1 to 2 dB compared with SUnSAL (sparse unmixing by variable splitting and augmented Lagrangian).
- hyperspectral /
- image /
- sparse /
- unmixing /
- adaptive

HTML全文

参考文献(17)

LANDGREBE D. Hyperspectral image data analysis[J]. IEEE Signal Processing Magazine, 2002, 19(1): 17-28.

PLAZA A, BENEDIKTSSON J A, BOARDMAN J, et al. Recent advances in techniques for hyperspectral image processing[J]. Remote Sensing of Environment, 2009, 113(1): 110-122.

BIOUCAS-DIAS J, PLAZA A, DOBIGEON N, et al. Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches[J]. IEEE Journal Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(2): 354-378.

CHAN T H, MA W K, AMBIKAPATHI A, et al. A simlex volume maximization framework for hyperspectral endmember extraction[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(11): 4177-4193.

RITTER G X, URCID G. A lattice matrix method for hyperspectral image unmixing[J]. Information Sciences, 2011, 181(10): 1787-1803.

普晗晔,王斌,张立明. 基于单形体几何的高光谱遥感图像解混算法[J]. 中国科学,2012,42(8): 1019-1033. PU Hanye, WANG Bin, ZHANG Liming. Simplex geometry-based abundance estimation algorithm for hyperspectral unmixing[J]. Scientia Sinica Infor-mationis, 2012, 42(8): 1019-1033.

ZARE A, GADER P. Robust endmember detection using L1 norm factorization[C]//IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Honolulu: IEEE, 2010: 971-974.

罗文斐,钟亮,张兵,等. 高光谱遥感图像光谱解混的独立成分分析技术[J]. 光谱学与光谱分析,2010,30(6): 1628-1633. LUO Wenfei, ZHONG Liang, ZHANG Bing, et al. Independent component analysis for spectral unmixing in hyperspectral remote sensing image[J]. Spectroscopy and Spectral Analysis, 2010, 30(6): 1628-1633.

SCHMIDT F, SCHMIDT A, TR GUIER E, et al. Implementation strategies for hyperspectral unmixing using bayesian source separation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(11): 4003-4013.

IORDACHE M D, BIOUCAS-DIAS J M, PLAZA A. Sparse unmixing of hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(6): 2014-2039.

BIOUCAS-DIAS J, FIGUEIREDO M. Alternating direction algorithms for constrained sparse regression: application to hyperspectral unmixing[C]//Hyperspectral Image and Signal Process: Evolution in Remote Sensing, (WHISPERS), 2010 2nd Workshop on. Reykjavik: WHISPERS, 2010: 1-4.

IORDACHE M D, PLAZA A, BIOUCAS-DIAS J. Recent development in sparse hyperspectral unmixing[C]//IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Honolulu: IEEE, 2010: 1281-1284.

吴泽彬,韦志辉,孙乐,等. 基于迭代加权L1正则化的高光谱混合像元分解[J]. 南京理工大学学报,2011,35(4): 431-435. WU Zebin, WEI Zhihui, SUN Le, et al. Hyperspectral unmixingbased on iterative weighted L1 regularization[J]. Journal of Nanjing University Science and Technology, 2011, 35(4): 431-435.

CHANG C I. Hyperspectral imaging: techniques for spectral detection and classification[M]. New York: Plenum, 2003: 39-50.

DENG G, TAY D B H, MARUSIC S. A signal denoising algorithm based on overcomplete wavelet representations and gaussian models[J]. Signal Processing, 2007, 87(5): 866-876.

QIAN Y T, YE M C. Hyperspectral imagery restoration using nonlocal spectral-spatial structured sparse representation with noise estimation[J]. IEEE Journal Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6(2): 499-515.

IORDACHE M D, BIOUCAS-DIAS J M, PLAZA A. Collaborative sparse regression for hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 341-354.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1242
HTML全文浏览量: 66
PDF下载量: 729
被引次数: 0

自适应冗余字典学习的高光谱混合像元解混

doi: 10.3969/j.issn.0258-2724.2014.04.006

计量

出版历程

Hyperspectral Sparse Unmixing via Adaptive Overcomplete Dictionary Learning

计量

出版历程

目录