предыдущий|следующий

Efficient unmixing algorithm using Sinkhorn distance and graph regularization constraints

  • role： First author第一作者
  • Affiliation：

    School of Information Engineering, Huzhou University, Huzhou 313000, China

  • Email：yll_scholar@163.com
  • Introduction：杨露露，研究方向为高光谱混合像元分解。E-mail： yll_scholar@163.com
YANG Lulu,  
  • role： Corresponding author通信作者
  • Affiliation：

    School of Information Engineering, Huzhou University, Huzhou 313000, China

  • Email：lichunzhi82@zjhu.edu.cn
  • Introduction：李春芝，研究方向为生物特征提取与识别，遥感图像处理等。E-mail： lichunzhi82@zjhu.edu.cn
LI Chunzhi*,  
  • Affiliation：

    School of Information Engineering, Huzhou University, Huzhou 313000, China

CHEN Xiaohua,  
  • Affiliation：

    School of Information Engineering, Huzhou University, Huzhou 313000, China

WANG Li

реферат

Hyperspectral remote sensing technology, as a new type of earth observation technology, provides rich spectral information of features and can identify and finely classify feature targets. A single pixel in hyperspectral images contains multiple features as limited by the spatial resolution. As a result, the mixed pixels become widespread. Ultimately, the accuracy of pixel-level applications is difficult to improve. Nonnegative Matrix Factorization (NMF), with its clear physical meaning, lays the foundation for the development of unsupervised linear spectral unmixing. Thus, traditional NMF often uses Euclidean distance as a similarity measure method. On the one hand, hyperspectral data have manifold distribution. Thus, simple linear measurement between two points cannot accurately represent the distance between data. This problem makes the sample internal features weakly correlated, which results in the NMF algorithm having an inaccurate prediction of the high-dimensional spatial inaccurate prediction of the translational noise in high-dimensional space. On the other hand, the objective function constructed based on this method ignores the correlation characteristics in the image space, which inhibits the performance of the algorithm.Method Considering the correlation between data manifolds and features, this study proposes a nonnegative matrix factorization unmixing algorithm based on Sinkhorn distance and graph regularization constraint (SDGNMF). On the basis of fully exploiting the advantages of EMD, the algorithm imposes entropy regularization constraint on EMD, improves EMD to Sinkhorn distance, and takes it as the standard of measuring error, which effectively reduces the computational complexity. In addition, EMD with entropy regularization constraint, that is, the representation of the model by Sinkhorn distance, can better model the relationship between different dimensional features and fully utilize the correlation of features. In particular, this study introduces the graph regularity constraint based on the Sinkhorn distance to further characterize the manifold structure of data. Compared with the unmixing model constructed by Euclidean distance, SDGNMF is relatively insensitive to the noise in hyperspectral data and can better extract the internal structural information of the data, which improves the unmixing accuracy.Result An experiment was conducted on simulated and real datasets. Experimental results prove that the proposed algorithm proposed has achieved excellent subspace learning results and has good robustness. Compared with several other algorithms, SDGNMF can retain the similar structure after iteration. The correlation between the endmember features is also fully considered in SDGNMF. Thus, the similar substances distributed in adjacent regions can be separated. Therefore, SDGNMF can better display the details of local abundance and obtain a more realistic and perfect abundance map.Conclusion In general, the proposed unmixing model can overcome noise and consider the correlation of features and data manifold structure simultaneously. Experimental results show that the proposed algorithm can effectively improve the unmixing accuracy of most hyperspectral remote sensing data, especially those with high feature correlation. However, the proposed algorithm has high computational complexity. In addition, the algorithm only considers the prior knowledge of abundance. Therefore, future work will focus on solving these problems.

ключеви́че слова́

hyperspectral unmixing;nonnegative matrix factorization (NMF);Sinkhorn distance;entropy regularization;graph regularization

References

  1. 1.
    Akhtar N and Mian A. 2017. RCMF: robust constrained matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 55(6): 3354-3366
  2. 2.
    Bajorski P. 2011. Second moment linear dimensionality as an alternative to virtual dimensionality. IEEE Transactions on Geoscience and Remote Sensing, 49(2): 672-678
  3. 3.
    Bruckstein A M, Elad M and Zibulevsky M. 2008. On the uniqueness of nonnegative sparse solutions to underdetermined systems of equations. IEEE Transactions on Information Theory, 54(11): 4813-4820
  4. 4.
    Cuturi M. 2013. Sinkhorn distances: Lightspeed computation of optimal transport//Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe: Curran Associates Inc.: 2292-2300
  5. 5.
    Cuturi M and Avis D. 2014. Ground metric learning. The Journal of Machine Learning Research, 15(1): 533-564
  6. 6.
    Feng X R, Li H C, Li J, Du Q, Plaza A and Emery W J. 2018. Hyperspectral unmixing using sparsity-constrained deep nonnegative matrix factorization with total variation. IEEE Transactions on Geoscience and Remote Sensing, 56(10): 6245-6257
  7. 7.
    Févotte C and Dobigeon N. 2015. Nonlinear hyperspectral unmixing with robust nonnegative matrix factorization. IEEE Transactions on Image Processing, 24(12): 4810-4819
  8. 8.
    Frogner C, Zhang C Y, Mobahi H, Araya-Polo M and Poggio T. 2015. Learning with a Wasserstein loss//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal: MIT Press: 2053-2061.
  9. 9.
    Gan Y Q, Liu W H, Feng X P, Yu T, Hu B L and Wen D S. 2019. A sparse constrained graph regularized nonnegative matrix factorization algorithm for hyperspectral unmixing. Spectroscopy and Spectral Analysis, 39(4): 1118-1127
  10. 10.
    Genevay A, Chizat L, Bach F, Cuturi M and Peyré G. 2019. Sample complexity of sinkhorn divergences//Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics. Naha: PMLR: 1574-1583.
  11. 11.
    Ghamisi P, Plaza J, Chen Y S, Li J and Plaza A J. 2017. Advanced spectral classifiers for hyperspectral images: a review. IEEE Geoscience and Remote Sensing Magazine, 5(1): 8-32
  12. 12.
    Han H W, Wang G X, Wang M Z, Miao J Q, Guo S, Chen L, Zhang M Y and Guo K. 2020. Hyperspectral unmixing via nonconvex sparse and low-rank constraint. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 5704-5718
  13. 13.
    He W, Zhang H Y and Zhang L P. 2016. Sparsity-regularized robust non-negative matrix factorization for hyperspectral unmixing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(9): 4267-4279
  14. 14.
    Hendrix E M T, Garcia I, Plaza J, Martin G and Plaza A. 2012. A new minimum-volume enclosing algorithm for endmember identification and abundance estimation in hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 50(7): 2744-2757
  15. 15.
    Heylen R, Parente M and Gader P. 2014. A review of nonlinear hyperspectral unmixing methods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 1844-1868.
  16. 16.
    Khan M J, Khan H S, Yousaf A, Khurshid K and Abbas A. 2018. Modern trends in hyperspectral image analysis: a review. IEEE Access, 6: 14118-14129.
  17. 17.
    Lan J H, Zou J L, Hao Y S, Zeng Y L, Zhang Y Z and Dong M W. 2018. Research progress on unmixing of hyperspectral remote sensing imagery. Journal of Remote Sensing, 22(1): 13-27
  18. 18.
    Lee D D and Seung H S. 1999. Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755): 788-791
  19. 19.
    Lee D D and Seung H S. 2000. Algorithms for non-negative matrix factorization//Proceedings of the 13th International Conference on Neural Information Processing Systems. Denver: MIT Press: 535-541
  20. 20.
    Li C Z and Chen X H. 2020. Error approximation of hyperspectral unmixing via correntropy-induced metric. IEEE Geoscience and Remote Sensing Letters, 17(2): 282-286
  21. 21.
    Li C Z, Gu Y G, Chen X H, Zhang Y and Ruan L J. 2021. Hyperspectral unmixing via latent multiheterogeneous subspace. IEEE Transactions on Geoscience and Remote Sensing, 59(1): 563-577
  22. 22.
    Li J, Bioucas-Dias J M, Plaza A and Liu L. 2016. Robust collaborative nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 54(10): 6076-6090
  23. 23.
    Liu X S, Xia W, Wang B and Zhang L M. 2011. An approach based on constrained nonnegative matrix factorization to unmix hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 49(2): 757-772
  24. 24.
    Lu X Q, Wu H, Yuan Y, Yan P K and Li X L. 2013. Manifold regularized sparse NMF for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 51(5): 2815-2826
  25. 25.
    Marrinan T and Gillis N. 2021. Hyperspectral unmixing with rare endmembers via minimax nonnegative matrix factorization//Proceedings of the 28th European Signal Processing Conference. Amsterdam: IEEE: 1015-1019
  26. 26.
    Mei S H, Bi Q Q, Ji J Y, Hou J H and Du Q. 2016. Spectral variation alleviation by low-rank matrix approximation for hyperspectral image analysis. IEEE Geoscience and Remote Sensing Letters, 13(6): 796-800
  27. 27.
    Miao L D and Qi H R. 2007. Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 45(3): 765-777
  28. 28.
    Nascimento J M P and Dias J M B. 2005. Does independent component analysis play a role in unmixing hyperspectral data? IEEE Transactions on Geoscience and Remote Sensing, 43(1): 175-187
  29. 29.
    Qian W, Hong B, Cai D, He X F and Li X L. 2016. Non-negative matrix factorization with sinkhorn distance//Proceedings of the 25th International Joint Conference on Artificial Intelligence. New York: AAAI Press: 1960-1966
  30. 30.
    Qian Y T, Jia S, Zhou J and Robles-Kelly A. 2011. Hyperspectral unmixing via sparsity-constrained nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 49(11): 4282-4297
  31. 31.
    Qin J, Lee H, Chi J T, Drumetz L, Chanussot J, Lou Y F and Bertozzi A L. 2021. Blind hyperspectral unmixing based on graph total variation regularization. IEEE Transactions on Geoscience and Remote Sensing, 59(4): 3338-3351
  32. 32.
    Rathnayake B, Ekanayake E M M B, Weerakoon K, Godaliyadda G M R I, Ekanayake M P B and Herath H M V R. 2020. Graph-based blind hyperspectral unmixing via nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 58(9): 6391-6409
  33. 33.
    Rubner Y, Tomasi C and Guibas L J. 2000. The earth mover’s distance as a metric for image retrieval. International Journal of Computer Vision, 40(2): 99-121
  34. 34.
    Sandler R and Lindenbaum M. 2011. Nonnegative matrix factorization with earth mover’s distance metric for image analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(8): 1590-1602
  35. 35.
    Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
  36. 36.
    Tsinos C G, Rontogiannis A A and Berberidis K. 2017. Distributed blind hyperspectral unmixing via joint sparsity and low-rank constrained non-negative matrix factorization. IEEE Transactions on Computational Imaging, 3(2): 160-174
  37. 37.
    Wang J and Chang C I. 2006. Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 44(9): 2601-2616
  38. 38.
    Wang N, Du B and Zhang L P. 2013. An endmember dissimilarity constrained non-negative matrix factorization method for hyperspectral unmixing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2): 554-569
  39. 39.
    Wang W H, Qian Y T and Tang Y Y. 2016. Hypergraph-regularized sparse NMF for hyperspectral unmixing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(2): 681-694
  40. 40.
    Wang X Y, Zhong Y F, Zhang L P and Xu Y Y. 2017. Spatial group sparsity regularized nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 55(11): 6287-6304
  41. 41.
    Yao J, Meng D Y, Zhao Q, Cao W F and Xu Z B. 2019. Nonconvex-sparsity and nonlocal-smoothness-based blind hyperspectral unmixing. IEEE Transactions on Image Processing, 28(6): 2991-3006
  42. 42.
    Yu Y and Sun W D. 2007. Minimum distance constrained non-negative matrix factorization for the endmember extraction of hyperspectral images//Proceedings of SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications. Wuhan: SPIE Press: 679015 [DOI: 10.1117/12.748379]
  43. 43.
    Yuan Y, Fu M and Lu X Q. 2015. Substance dependence constrained sparse NMF for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 53(6): 2975-2986
  44. 44.
    Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090
  45. 45.
    Zhang B, Chen Z C, Peng D L, Benediktsson J A, Liu B, Zou L, Li J and Plaza A. 2019. Remotely sensed big data: evolution in model development for information extraction [point of view]. Proceedings of the IEEE, 107(12): 2294-2301
  46. 46.
    Zhang X R, Zhang J Y, Li C, Cheng C, Jiao L C and Zhou H Y. 2018. Hybrid unmixing based on adaptive region segmentation for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 56(7): 3861-3875
  47. 47.
    Zhang Y M, Shu Z Q, Zhang J, You C Z, Weng Z H, Fan H H and Ye F Y. 2020. Dual graph regularized NMF with sinkhorn distance//Proceedings of the 19th International Symposium on Distributed Computing and Applications for Business Engineering and Science. Xuzhou: IEEE: 146-149
  48. 48.
    Zhi T X, Yang B, Chen Z and Wang B. 2017. Nonnegative matrix factorization with constraints on endmember and abundance for hyperspectral unmixing//Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium. Fort Worth: IEEE: 1149-1152

Читать полностью

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website