Hyperspectral image unmixing algorithm based on spectral distance clustering

doi:10.11772/j.issn.1001-9081.2019020351

Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (9): 2541-2546.DOI: 10.11772/j.issn.1001-9081.2019020351

• Artificial intelligence • Previous Articles Next Articles

Hyperspectral image unmixing algorithm based on spectral distance clustering

LIU Ying^1,2, LIANG Nannan¹, LI Daxiang^1,2, YANG Fanchao³

1. College of Communication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an Shaanxi 710121, China;
2. Key Laboratory of Electronic Information and Application Technology for Scene Investigation, Ministry of Public Security(Xi'an University of Posts & Telecommunications), Xi'an Shaanxi 710121, China;
3. Key Laboratory of Spectral Imaging Technique, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an Shaanxi 710119, China

Received:2019-03-06 Revised:2019-05-13 Online:2019-09-10 Published:2019-05-21
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61571361), the Shaanxi International Cooperation and Exchange Project of China (2017KW-013), the Graduate Innovation Fund for Xi'an University of Posts and Telecommunications (CXJJLY2018024).

基于光谱距离聚类的高光谱图像解混算法

刘颖^1,2, 梁楠楠¹, 李大湘^1,2, 杨凡超³

1. 西安邮电大学通信与信息工程学院, 西安 710121;
2. 电子信息现场勘验应用技术公安部重点实验室(西安邮电大学), 西安 710121;
3. 中国科学院西安光学精密机械研究所光谱成像技术重点实验室, 西安 710119

通讯作者: 梁楠楠
作者简介:刘颖(1972-),女,陕西户县人,高级工程师,博士,主要研究方向:图像视频检索;梁楠楠(1994-),女,陕西延安人,硕士研究生,主要研究方向:刑侦图像处理、高光谱图像处理;李大湘(1974-),男,湖南麻阳人,副教授,博士,主要研究方向:数字图像处理、机器学习;杨凡超(1987-),男,陕西西安人,助理研究员,博士,主要研究方向:高光谱成像、偏振技术。
基金资助:
国家自然科学基金资助项目（61571361）；陕西省国际合作交流项目（2017KW-013）；西安邮电大学研究生创新基金资助项目（CXJJLY2018024）。

Abstract

Abstract:

In order to solve the problem of the effect of noise on the unmixing precision and the insufficient utilization of spectral and spatial information in the actual Hyperspectral Unmixing (HU), an improved unmixing algorithm based on spectral distance clustering for group sparse nonnegative matrix factorization was proposed. Firstly, the HYperspectral Signal Identification by Minimum Error (Hysime) algorithm for the large amount of noise existing in the actual hyperspectral image was introduced, and the signal matrix and the noise matrix were estimated by calculating the eigenvalues. Then, a simple clustering algorithm based on spectral distance was proposed and used to merge and cluster the adjacent pixels generated by multiple bands, whose spectral reflectance distances are less than a certain value, to generate the spatial group structure. Finally, sparse non-negative matrix factorization was performed on the basis of the generated group structure. Experimental analysis shows that for both simulated data and actual data, the algorithm produces smaller Root-Mean-Square Error (RMSE) and Spectral Angle Distance (SAD) than traditional algorithms, and can produce better unmixing effect than other advanced algorithms.

Key words: Hyperspectral Unmixing (HU), Hyperspectral signal identification algorithm by minimum error (Hysime), spectral distance metric, Non-negative Matrix Factorization (NMF), remote sensing

摘要：

为了解决实际高光谱解混（HU）中噪声对解混精度的影响和光谱、空间信息利用不足的问题，提出了一种改进的基于光谱距离聚类的群稀疏非负矩阵分解的解混算法。首先，引入了基于最小误差的高光谱信号辨识算法（Hysime），通过计算特征值的方式估计信号矩阵和噪声矩阵；然后，提出了一种简单的基于光谱距离的聚类算法，对多个波段生成的光谱反射率距离值小于某一值的相邻像元进行合并聚类生成空间群结构；最后，在生成的群结构基础上进行稀疏化非负矩阵分解。实验分析表明，对于模拟数据和实际数据而言，该算法都比传统算法产生更小的均方根误差（RMSE）和光谱角距离（SAD），能够产生优于同类算法的解混效果。

关键词: 高光谱解混, 基于最小误差的高光谱信号辨识算法, 光谱距离度量, 非负矩阵分解, 遥感

CLC Number:

TP751

LIU Ying, LIANG Nannan, LI Daxiang, YANG Fanchao. Hyperspectral image unmixing algorithm based on spectral distance clustering[J]. Journal of Computer Applications, 2019, 39(9): 2541-2546.

刘颖, 梁楠楠, 李大湘, 杨凡超. 基于光谱距离聚类的高光谱图像解混算法[J]. 计算机应用, 2019, 39(9): 2541-2546.

References

[1] FENG R Y, TIAN T, LI X, et al. Rolling guidance based scaled-aware spatial sparse unmixing for hyperspectral remote sensing imagery[C]//Proceedings of the 2018 IEEE International Geoscience and Remote Sensing Symposium. Piscataway,NJ:IEEE, 2018:4273-4276.
[2] 彭倩.基于非负矩阵分解的高光谱图像解混研究[D].北京:中国科学院大学(中国科学院遥感与数字地球研究所),2017:1-10.(PENG Q.Hyperspectral unmixing based on constrained nonnegative matrix factorization[D]. Beijing:University of Chinese Academy of Sciences (Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences), 2017:1-10.)
[3] HEYLEN R, BURAZEROVIC D, SCHEUNDERS P. Non-linear spectral unmixing by geodesic simplex volume maximization[J]. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(3):534-542.
[4] 王天成,刘相振,董泽政,等.一种自适应鲁棒最小体积高光谱解混算法[J].自动化学报,2017,43(12):2141-2159.(WANG T C, LIU X Y, DONG Z Z, et al. A robust minimum volume based algorithm with automatically estimating regularization parameters for hyperspectral unmixing[J]. Acta Automatica Sinica, 2017, 43(12):2141-2159.)
[5] 聂明钰.高光谱图像线性解混算法研究[D].济南:山东大学,2016. (NIE M Y. Research on hyperspectral image linear unmixing algorithm[D]. Jinan:Shandong University, 2016.)
[6] 袁博.空间与谱间相关性分析的NMF高光谱解混[J].遥感学报,2018,22(2):265-276.(YUAN B. NMF hyperspectral unmixing algorithm combined with spatial and spectral correlation analysis[J]. Journal of Remote Sensing, 2018, 22(2):265-276.)
[7] 贾志成,薛允艳,陈雷,等.基于去噪降维和蝙蝠优化的高光谱图像盲解混算法[J].光子学报,2016,45(5):106-115.(JIA Z C, XUE Y Y, CHEN L, et al. Blind separation algorithm for hyperspectral image based on the denoising reduction and the bat optimization[J]. Acta Photonica Sinica, 2016, 45(5):112-115.)
[8] 尹凤.高光谱线性解混的理论与方法及应用研究[D].成都:成都理工大学,2017:20-28.(YIN F. Study on the theory and method of linear hyperspectral unmixing and its application[D]. Chengdu:Chengdu University of Technology, 2017:20-28.)
[9] 孔繁锵,卞陈鼎,李云松等.非凸稀疏低秩约束的高光谱解混方法[J].西安电子科技大学学报(自然科学版),2016,43(6):116-121.(KONG F Q, BIAN C D, LI Y S, et al. Hyperspectral unmixing method based on the non-cinvex sparse and low-rank constraints[J]. Journal of Xidian University (Natural Science), 2016, 43(6):116-121.)
[10] 郭文骏.基于联合稀疏表示的高光谱图像解混方法研究[D].南京:南京航空航天大学,2016:1-22.(GUO W J. Research on hyperspectral imagery unmixing algorithms based on simultaneous sparse represent[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2016:1-22.)
[11] 陈洁,杜磊,李京,等.基于噪声白化的高光谱数据子空间维数算法[J].国土资源遥感,2017,29(2):60-66.(CHEN J, DU L, LI J, et al. Hyperspectral data subspace dimension algorithm based on noise whitening[J]. Remote Sensing for Land and Resources, 2017, 29(2):60-66.)
[12] 郑思远.面向异常检测的高光谱数据线性子空间估计[D].长沙:国防科学技术大学,2013:32-36.(ZHENG S Y. Hyperspectral linear subspace estimation for anomaly detection[D]. Changsha:National University of Defense Technology, 2013:32-36.)
[13] SUN Y L, BIOUCAS-DIAS J M, ZHANG X, et al. A new classification-oriented endmember extraction and sparse unmixing approach for hyperspectral data[C]//Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium. Piscataway, NJ:IEEE, 2017:3644-3647.
[14] ZHANG S, LI J, PLAZA J, et al. Spatial weighted sparse regression for hyperspectral image unmixing[C]//Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium. Piscataway, NJ:IEEE, 2017:225-228.
[15] WANG X, ZHONG Y, ZHANG L, et al. Spatial group sparsity regularized nonnegative matrix factorization for hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(11):6287-6304.
[16] ERTVRK A, ERTVRK S, PLAZA A. Unmixing with SLIC superpixels for hyperspectral change detection[C]//Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium. Piscataway, NJ:IEEE, 2016:3370-3373.
[17] LIN C. Projected gradient methods for nonnegative matrix factorization[J]. Neural Computation, 2007, 19(10):2756-2779.
[18] SHEN X, BAO W, QU K W. Clustering based spatial spectral preprocessing for hyperspectral unmxing[C]//Proceedings of the 4th International Conference on Communication and Information Processing. New York:ACM, 2018:313-316.
[19] HENDRIX E M T, GARCIA I, PLAZA J, et al. New minimum-volume enclosing algorithm for endmember identification and abundance estimation in hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(7):2744-2757.
[20] HARTIGAN J A, WONG M A. Algorithm AS 136:a K-means clustering algorithm[J]. Journal of the Royal Statistical Society. Series C (Applied Statistics), 1979, 28(1):100-108.
[21] CORBINEAU M, CHOUZENOUX E, PESQUET J. PIPA:a new proximal interior point algorithm for large-scale convex optimization[C]//Proceedings of the 2018 International Conference on Acoustics, Speech and Signal processing. Piscataway, NJ:IEEE, 2018:1343-1347.

Hyperspectral image unmixing algorithm based on spectral distance clustering

基于光谱距离聚类的高光谱图像解混算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	SONG Zhongshan, LIANG Jiarui, ZHENG Lu, LIU Zhenyu, TIE Jun. Remote sensing scene classification based on bidirectional gated scale feature fusion [J]. Journal of Computer Applications, 2021, 41(9): 2726-2735.
[2]	REN Qiuru, YANG Wenzhong, WANG Chuanjian, WEI Wenyu, QIAN Yunyun. Review of remote sensing image change detection [J]. Journal of Computer Applications, 2021, 41(8): 2294-2305.
[3]	SUN Xiao, XU Jindong. Remote sensing image dehazing method based on cascaded generative adversarial network [J]. Journal of Computer Applications, 2021, 41(8): 2440-2444.
[4]	WU Lei, YANG Xiaomin. Improved remote sensing image fusion algorithm based on channel attention feedback network [J]. Journal of Computer Applications, 2021, 41(4): 1172-1178.
[5]	REN Yuanyuan, WANG Chuanjian. Remote sensing time-series images classification algorithm with abnormal data [J]. Journal of Computer Applications, 2021, 41(3): 662-668.
[6]	ZHANG Yonghong, LIU Hao, TIAN Wei, WANG Jiangeng. Rainfall cloud segmentation method in Tibet based on DeepLab v3 [J]. Journal of Computer Applications, 2020, 40(9): 2781-2788.
[7]	WANG Rui, HUANG Wei, HU Nanqiang. Thick cloud removal algorithm for multi-temporal remote sensing images based on total variation model [J]. Journal of Computer Applications, 2020, 40(7): 2126-2130.
[8]	XU Jinrong, GUO Caiping, TONG Endong. Time-aware QoS prediction for SOA-based remote sensing image processing platform [J]. Journal of Computer Applications, 2020, 40(6): 1714-1721.
[9]	ZHANG Wu, CHEN Hongmei. Hyperspectral band selection based on multi-kernelized fuzzy rough set and grasshopper optimization algorithm [J]. Journal of Computer Applications, 2020, 40(5): 1425-1430.
[10]	WANG Quanfang, ZHANG Mengru, ZHANG Yu, WANG Qianqian, CHEN Longyue, YANG Yuqi. Intelligent extraction of remote sensing information on large-scale water based on visual attention mechanism [J]. Journal of Computer Applications, 2020, 40(4): 1038-1044.
[11]	BIAN Xiaoyong, FEI Xiongjun, MU Nan. Remote sensing image scene classification based on scale-attention network [J]. Journal of Computer Applications, 2020, 40(3): 872-877.
[12]	SHI Wenxu, BAO Jiahui, YAO Yu. Remote sensing image target detection and identification based on deep learning [J]. Journal of Computer Applications, 2020, 40(12): 3558-3562.
[13]	ZHANG Wu, CHEN Hongmei. Hyperspectral band selection algorithm based on kernelized fuzzy rough set [J]. Journal of Computer Applications, 2020, 40(1): 258-263.
[14]	CHEN Shanxue, CHU Chengquan. Hyperspectral unmixing based on sparse and orthogonal constrained non-negative matrix factorization [J]. Journal of Computer Applications, 2019, 39(8): 2276-2280.
[15]	WANG Yulong, PU Jun, ZHAO Jianghua, LI Jianhui. Detection of new ground buildings based on generative adversarial network [J]. Journal of Computer Applications, 2019, 39(5): 1518-1522.