Subspace multi-regularized non-negative matrix factorization for hyperspectral unmixing | Applied Intelligence Skip to main content
Springer Nature Link
Log in

Subspace multi-regularized non-negative matrix factorization for hyperspectral unmixing

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Hyperspectral unmixing (HU) is an important task in hyperspectral image (HSI) processing, which estimates endmembers and their corresponding abundances. Generally, the unmixing process of HSI can be approximated by a linear mixing model. Since each type of material only appears in a few pixels in HSI, sparse non-negative matrix factorization (NMF) and its extensions are regarded as the main unmixing methods. However, due to the lack of consideration of the spatial distribution in the local domain, most HU methods lose the inducing effect of spatial correlation in the decomposition process, and ignore the correlation of the real distribution of different materials in different images. In this paper, a novel NMF unmixing model is proposed, called SMRNMF, which learns multiple subspace structures from the original hyperspectral images and combines them into a sparse NMF framework to improve the performance of the model. Firstly, subspace clustering is embedded into the sparse NMF model. According to the spatial correlation of the original data, two similarity matrices are learned, which make full use of the local correlations between the pixels of the original data. Secondly, based on the self-expression characteristics of the data in the subspace, the global similarity pixel graph matrix is embedded into the model to construct a self-expression regularizer to improve the unmixing performance. Finally, a smoothing matrix is cleverly constructed and embedded in the model to overcome the adverse effects of noisy information in the abundance images. Experiments on several simulated and real HSI data sets show that our method has superior performance compared with the existing methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Algorithm 1
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Ma J, Sun D-W, Pu H, Cheng J-H, Wei Q (2019) Advanced techniques for hyperspectral imaging in the food industry: Principles and recent applications. Annu Rev Food Sci Technol 10:197–220

    Google Scholar 

  2. Chang C-I (2020) An effective evaluation tool for hyperspectral target detection: 3d receiver operating characteristic curve analysis. IEEE Trans Geosci Remote Sens 59(6):5131–5153

    Google Scholar 

  3. Imani M, Ghassemian H (2020) An overview on spectral and spatial information fusion for hyperspectral image classification: Current trends and challenges. Inform Fusion 59:59–83

    Google Scholar 

  4. Pour AB, Zoheir B, Pradhan B, Hashim M (2021) Editorial for the Special issue: Multispectral and hyperspectral remote sensing data for mineral exploration and environmental monitoring of mined areas. Multidisciplinary Digital Publishing Institute

  5. Yao J, Hong D, Xu L, Meng D, Chanussot J, Xu Z (2022) Sparsity-enhanced convolutional decomposition: a novel tensor-based paradigm for blind hyperspectral unmixing. IEEE Trans Geosci Remote Sens 60:1–14

    Google Scholar 

  6. Dai J, Huang K, Liu Y, Yang C, Wang Z (2020) Global reconstruction of complex network topology via structured compressive sensing. IEEE Syst J 15(2):1959–1969

    Google Scholar 

  7. Hong D, Yokoya N, Chanussot J, Xu J, Zhu XX (2020) Joint and progressive subspace analysis (jpsa) with spatial–spectral manifold alignment for semisupervised hyperspectral dimensionality reduction. IEEE Trans Cybern 51(7):3602–3615

    Google Scholar 

  8. Xu X, Li J, Wu C, Plaza A (2018) Regional clustering-based spatial preprocessing for hyperspectral unmixing. Remote Sens Environ 204:333–346

    Google Scholar 

  9. COCHRANE MA (1998) Linear mixture model classification of burned forests in the eastern amazon. Int J Remote Sens 19(17):3433–3440

    Google Scholar 

  10. Lu D, Moran E, Batistella M (2003) Linear mixture model applied to amazonian vegetation classification. Remote Sens Environ 87(4):456–469

    Google Scholar 

  11. Zhou Y, Rangarajan A, Gader PD (2018) A gaussian mixture model representation of endmember variability in hyperspectral unmixing. IEEE Trans Image Process 27(5):2242–2256

    MathSciNet  MATH  Google Scholar 

  12. Qian Y, Xiong F, Qian Q, Zhou J (2020) Spectral mixture model inspired network architectures for hyperspectral unmixing. IEEE Trans Geosci Remote Sens 58(10):7418–7434

    Google Scholar 

  13. Tong L, Zhou J, Li X, Qian Y, Gao Y (2016) Region-based structure preserving nonnegative matrix factorization for hyperspectral unmixing. IEEE J Sel Top Appl Earth Obs Remote Sens 10(4):1575–1588

    Google Scholar 

  14. Ma Y, Li C, Mei X, Liu C, Ma J (2016) Robust sparse hyperspectral unmixing with l2,1 norm. IEEE Trans Geosci Remote Sens 55(3):1227–1239

    Google Scholar 

  15. Zhang Z, Liao S, Zhang H, Wang S, Wang Y (2018) Bilateral filter regularized l2 sparse nonnegative matrix factorization for hyperspectral unmixing. Remote Sens 10(6):816

    Google Scholar 

  16. Nie M, Liu Z, He X, Qiu Q, Zhang Y, Chang J (2017) End-member extraction based on segmented vertex component analysis in hyperspectral images. Appl Opt 56(9):2476–2482

    Google Scholar 

  17. Feng X-R, Li H-C, Wang R, Du Q, Jia X, Plaza AJ (2022) Hyperspectral unmixing based on nonnegative matrix factorization: A comprehensive review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

  18. Zhu Y, Hu X, Zhang Y, Li P (2018) Transfer learning with stacked reconstruction independent component analysis. Knowl-Based Syst 152:100–106

    Google Scholar 

  19. Winter ME (1999) N-findr: An algorithm for fast autonomous spectral end-member determination in hyperspectral data. In: Imaging Spectrometry V, vol 3753, International Society for Optics and Photonics pp 266–275

  20. Qian Y, Xiong F, Zeng S, Zhou J, Tang YY (2016) Matrix-vector nonnegative tensor factorization for blind unmixing of hyperspectral imagery. IEEE Trans Geosci Remote Sens 55(3):1776–1792

    Google Scholar 

  21. Heylen R, Burazerovic D, Scheunders P (2011) Fully constrained least squares spectral unmixing by simplex projection. IEEE Trans Geosci Remote Sens 49(11):4112–4122

    Google Scholar 

  22. Zheng P, Su H, Du Q (2021) Sparse and low-rank constrained tensor factorization for hyperspectral image unmixing. IEEE J Sel Top Appl Earth Obs Remote Sens 14:1754–1767

    Google Scholar 

  23. Iordache M-D, Bioucas-Dias JM, Plaza A (2011) Sparse unmixing of hyperspectral data. IEEE Trans Geosci Remote Sens 49(6):2014–2039

    Google Scholar 

  24. Shi Z, Tang W, Duren Z, Jiang Z (2013) Subspace matching pursuit for sparse unmixing of hyperspectral data. IEEE Trans Geosci Remote Sens 52(6):3256–3274

    Google Scholar 

  25. Lee D, Seung HS (2000) Algorithms for non-negative matrix factorization. Advances in neural information processing systems 13

  26. Jia S, Qian Y (2008) Constrained nonnegative matrix factorization for hyperspectral unmixing. IEEE Trans Geosci Remote Sens 47(1):161–173

    Google Scholar 

  27. Liu X, Xia W, Wang B, Zhang L (2010) An approach based on constrained nonnegative matrix factorization to unmix hyperspectral data. IEEE Trans Geosci Remote Sens 49(2):757–772

    Google Scholar 

  28. Li J, Bioucas-Dias JM, Plaza A, Liu L (2016) Robust collaborative nonnegative matrix factorization for hyperspectral unmixing. IEEE Trans Geosci Remote Sens 54(10):6076–6090

    Google Scholar 

  29. Wang X, Zhong Y, Zhang L, Xu Y (2017) Spatial group sparsity regularized nonnegative matrix factorization for hyperspectral unmixing. IEEE Trans Geosci Remote Sens 55(11):6287–6304

    Google Scholar 

  30. Lu X, Wu H, Yuan Y, Yan P, Li X (2012) Manifold regularized sparse nmf for hyperspectral unmixing. IEEE Trans Geosci Remote Sens 51(5):2815–2826

    Google Scholar 

  31. Lu X, Dong L, Yuan Y (2019) Subspace clustering constrained sparse nmf for hyperspectral unmixing. IEEE Trans Geosci Remote Sens 58(5):3007–3019

    Google Scholar 

  32. Lu N, Miao H (2016) Structure constrained nonnegative matrix factorization for pattern clustering and classification. Neurocomputing 171:400–411

    Google Scholar 

  33. Yang S, Zhang X, Yao Y, Cheng S, Jiao L (2015) Geometric nonnegative matrix factorization (gnmf) for hyperspectral unmixing. IEEE J Sel Top Appl Earth Obs Remote Sens 8(6):2696–2703

    Google Scholar 

  34. Cai D, He X, Han J, Huang TS (2010) Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 33(8):1548–1560

    Google Scholar 

  35. Ekanayake E, Weerasooriya H, Ranasinghe D, Herath S, Rathnayake B, Godaliyadda G, Ekanayake M, Herath H (2021) Constrained nonnegative matrix factorization for blind hyperspectral unmixing incorporating endmember independence. IEEE J Sel Top Appl Earth Obs Remote Sens 14:11853–11869

    Google Scholar 

  36. Zhang J, Zhang X, Jiao L (2021) Sparse nonnegative matrix factorization for hyperspectral unmixing based on endmember independence and spatial weighted abundance. Remote Sens 13(12):2348

    Google Scholar 

  37. Li S, Li W, Hu J, Li Y (2022) Semi-supervised bi-orthogonal constraints dual-graph regularized nmf for subspace clustering. Appl Intell 52(3):3227–3248

    Google Scholar 

  38. Salehani YE, Gazor S (2017) Smooth and sparse regularization for nmf hyperspectral unmixing. IEEE J Sel Top Appl Earth Obs Remote Sens 10(8):3677–3692

    Google Scholar 

  39. Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791

    MATH  Google Scholar 

  40. Chachlakis DG, Dhanaraj M, Prater-Bennette A, Markopoulos PP (2021) Dynamic l1-norm tucker tensor decomposition. IEEE J Sel Top Signal Process PP(99):1–1

    Google Scholar 

  41. Xu G (2020) Dual calibration mechanism based l2, p-norm for graph matching. IEEE Transactions on Circuits and Systems for Video Technology PP(99)

  42. Shi C, Ruan Q, An G, Zhao R (2015) Hessian semi-supervised sparse feature selection based on l2,1/2 -matrix norm. IEEE Trans Multimedia 17(1):16–28

    Google Scholar 

  43. Ammanouil R, Ferrari A, Richard C (2015) A graph laplacian regularization for hyperspectral data unmixing. In: 2015 IEEE International conference on acoustics, speech and signal processing (ICASSP), pp 1637–1641. IEEE

  44. Wang Q, He X, Li X (2018) Locality and structure regularized low rank representation for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(2):911–923

    Google Scholar 

  45. Dong W, Wozniak M, Wu J, Li W, Bai Z (2022) De-noising aggregation of graph neural networks by using principal component analysis. IEEE Transactions on Industrial Informatics

  46. Nie F, Wang X, Huang H (2014) Clustering and projected clustering with adaptive neighbors. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 977–986

  47. Huang S, Xu Z, Kang Z, Ren Y (2020) Regularized nonnegative matrix factorization with adaptive local structure learning. Neurocomputing 382:196–209

    Google Scholar 

  48. Zhou L, Zhang X, Wang J, Bai X, Tong L, Zhang L, Zhou J, Hancock E (2020) Subspace structure regularized nonnegative matrix factorization for hyperspectral unmixing. IEEE J Sel Top Appl Earth Obs Remote Sens 13:4257–4270

    Google Scholar 

  49. Wieczorek M, Siłka J, Woźniak M, Garg S, Hassan MM (2021) Lightweight convolutional neural network model for human face detection in risk situations. IEEE Trans Ind Inform 18(7):4820–4829

    Google Scholar 

  50. Basak H, Kundu R, Singh PK, Ijaz MF, Woźniak M, Sarkar R (2022) A union of deep learning and swarm-based optimization for 3d human action recognition. Sci Rep 12(1):1–17

    Google Scholar 

  51. Yan G, Woźniak M (2022) Accurate key frame extraction algorithm of video action for aerobics online teaching. Mobile Networks and Applications, pp 1–10

Download references

Acknowledgements

This work was funded by the National Natural Science Foundation of China under Grant 51774219, Key R&D Projects in Hubei Province under grant 2020BAB098.

Author information

Authors and Affiliations

  1. School of Information Science and Engineering, Wuhan University of Science and Technology, No.947, Heping Road, Qingshan District, Wuhan, 430081, People’s Republic of China

    Songtao Li, Weigang Li & Yang Li

  2. School of Economics and Business, Hunan University, NO.109, Shijiachong Road, Yuelu District, Changsha, 410079, People’s Republic of China

    Lian Cai

Authors
  1. Songtao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Weigang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lian Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Weigang Li.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, S., Li, W., Cai, L. et al. Subspace multi-regularized non-negative matrix factorization for hyperspectral unmixing. Appl Intell 53, 12541–12563 (2023). https://doi.org/10.1007/s10489-022-04121-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04121-y

Keywords

Search

Navigation