Article Details

Title · Authors · Abstract · Keywords · DOI · References

HU Based on L1/2 Sparsity and Kurtosis Smoothing Constrained Non-negative Matrix Factorization

YANG Guoliang, ZHANG Jiaqi, SHENG Yangyang

(School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, China)

Section：Artificial Intelligence · Vol. 2025, Issue 5 · Pages：45-50 · 2096-4706（2025）05-0045-06 · CLC number：TP751.2 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2025.05.008

Abstract

In order to solve the problems existing in traditional HU methods, such as low unmixing efficiency, complex computation and vulnerability to noise and outliers, an algorithm based on L1/2-KSNMF is proposed. Aiming at nonlinear mixing situation in HSI, this method first introduces the L1/2 norm as a measure of sparsity to improve the accuracy of unmixing. By introducing kurtosis smoothing constraint, the spatial information is fused into the unmixing model to enhance the spatial continuity of the unmixing results. The experimental results show that this algorithm demonstrates excellent performance in terms of unmixing accuracy, computational efficiency, as well as the extraction of endmember spectra from hyperspectral data.

Keywords

HSI; Non-negative Matrix Factorization; L1/2 sparse constraint; HU

References

  1. [1] KHAN M J，KHAN H S，YOUSAF A，et al. Modern Trends in Hyperspectral Image Analysis: A Review [J].IEEE Access，2018，6：14118–14129.
  2. [2] NASCIMENTO J M，BIOUCAS-DIAS J M. Blind Hyperspectral Unmixing [C]//Image and Signal Processing for Remote Sensing XIII. San Diego：SPIE，2007：12-23.
  3. [3] BHATT J S，JOSHI M V. Deep Learning in Hyperspectral Unmixing: A Review [C]//IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. Waikoloa：IEEE，2020：1-5.
  4. [4] LU X Q，WU H，YUAN Y，et al. Manifold Regularized Sparse NMF for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2012，51（5）：2815-2826.
  5. [5] LIU Y，GUO Y，LI F，et al. Sparse Dictionary Learning for Blind Hyperspectral Unmixing [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2018，16（4）：578-582.
  6. [6] TONG L，ZHOU J，QIAN B，et al. Adaptive Graph Regularized Multilayer Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，13：434-447.
  7. [7] PENG J，ZHOU Y，SUN W，et al. Self-Paced Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2020，59（2）：1501-1515.
  8. [8] HAN H，WANG G，WANG M，et al. Hyperspectral Unmixing via Nonconvex Sparse and Low-Rank Constraint [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，13：5704-5718.
  9. [9] ZHANG S，ZHANG G，LI F，et al. Spectral-Spatial Hyperspectral Unmixing Using Nonnegative Matrix Factorization [J].IEEE Transactions on Geoscience and Remote Sensing，2021，60：1-13.
  10. [10] EKANAYAKE E，WEERASOORIYA H，RANASINGHE D Y L，et al. Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2021，14：11853-11869.
  11. [11] BURRED J J. Detailed Derivation of Multiplicative Update Rules for NMF [EB/OL].（2024-06-25）.https://www.jjburred.com/research/pdf/jjburred_nmf_updates.pdf.
  12. [12] PASCUAL-MONTANO A，CARAZO J M，KOCHI K，et al. Nonsmooth Nonnegative Matrix Factorization (nsNMF) [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2006，28（3）：403-415.
  13. [13] LEE D，SEUNG H. Algorithms for Non-Negative Matrix Factorization [C]//Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS).Vancouver：NIPS，2001：535-541.
  14. [14] SHI C，WANG L. Linear Spatial Spectral Mixture Model [J].IEEE Transactions on Geoscience and Remote Sensing，2016，54（6）：3599-3611.
  15. [15] QIAN Y，JIA S，ZHOU J，et al. Hyperspectral Unmixing via L1/2 Sparsity-Constrained Nonnegative Matrix Factorization [J].IEEE Transactions on Geoscience and Remote Sensing，2011，49（11）：4282-4297.
  16. [16] 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.
  17. [17] LEPALT V，ANG A M S，GILLIS N. Minimum-Volume Rank-Deficient Nonnegative Matrix Factorizations [C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brighton：IEEE，2019：3402-3406.
  18. [18] LI J，BIOUCAS-DIAS J M，PLAZA A，et al. Robust Collaborative Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2016，54（10）：6076-6090.

Funding

Science and Technology Plan Project of Jiangxi Provincial Department of Education (GJJ210861); Science and Technology Project of Jiangxi Provincial Department of Education (GJJ200879)

About the authors

Yang Guoliang (1973-), male, Han ethnicity, from Yichun, Jiangxi, professor, PhD, research direction: artificial intelligence and pattern recognition; Corresponding author: Zhang Jiaqi (2000-), male, Han ethnicity, from Yichun, Jiangxi, currently pursuing a master's degree in deep learning and pattern recognition; Sheng Yangyang (1997-), male, Han ethnicity, from Yangzhou, Jiangsu, is currently pursuing a master's degree in deep learning and pattern recognition.