Nonnegative matrix factorization (NMF) is commonly used in hyperspectral image (HSI) unmixing due to its high interpretability and computability. To effectively address HSI noise and improve unmixing efficiency, this study proposed a method for hyperspectral unmixing based on spectral-spatial total variation nonnegative matrix factorization (SSTVNMF) with feature space augmentation. First, the original data space was converted to the feature space through feature extraction, allowing the unmixing process to be performed in the feature space for enhanced unmixing efficiency. Second, to reduce the impact of noise, the spatial information was extracted using the bilateral filtering (BF) method for enhanced feature extraction, thereby ensuring the accuracy of extracted features. Third, to ensure the effectiveness of the unmixing method, total variation (TV) regularization that considers both spatial and spectral features was established based on the NMF method. The spatial TV promotes abundance smoothing by calculating the horizontal and vertical differences in abundance between neighboring pixels. Based on the minimum-volume TV, the spectral TV enhances endmember extraction by applying constraint forces between endmembers to minimize the volume. Finally, the proposed method was verified using the synthetic data from the USGS spectral library as simulated data and the Jasper Ridge, APEX, and Cuprite datasets as actual data. The experimental results demonstrate that the proposed method outperformed other improved NMF-based methods in terms of qualitative and quantitative assessments.
覃子怡, 杨隆珊. 基于特征空间增强下空谱全变差非负矩阵分解的高光谱解混[J]. 自然资源遥感, 2025, 37(4): 21-30.
QIN Ziyi, YANG Longshan. Hyperspectral unmixing based on spectral-spatial total variation nonnegative matrix factorization with feature space augmentation. Remote Sensing for Natural Resources, 2025, 37(4): 21-30.
Su Y C, Xu R Q, Gao L R, et al. Development of deep learning-based hyperspectral remote sensing image unmixing[J]. National Remote Sensing Bulletin, 2024, 28(1):1-19.
Sun X, Xu L L, Wang X Y, et al. Mineral identification from hyperspectral images based on the optimized K-P-Means unmixing method[J]. Remote Sensing for Natural Resources, 2022, 34(3):43-49.doi:10.6046/zrzyyg.2021215.
Li Y N, Li Z Q, Zheng Y, et al. Spectral reconstruction method of mid-infrared surface characteristics based on non-negative matrix factorization[J]. Spectroscopy and Spectral Analysis, 2024, 44(2):563-570.
[5]
Zhao X L, Wang F, Huang T Z, et al. Deblurring and sparse unmixing for hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(7):4045-4058.
Wang J Y, Li C L. Development and prospect of hyperspectral imager and its application[J]. Chinese Journal of Space Science, 2021, 41(1):22-33.
[7]
Chen B H, Cheng H Y, Tseng Y S, et al. Two-pass bilateral smooth filtering for remote sensing imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19:8006405.
[8]
Guo J, Xie R, Jin G. An efficient method for NMR data compression based on fast singular value decomposition[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(2):301-305.
[9]
Zheng Y B, Huang T Z, Zhao X L, et al. Mixed noise removal in hyperspectral image via low-fibered-rank regularization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(1):734-749.
[10]
Zhuang L, Lin C H, Figueiredo M A T, et al. Regularization para-meter selection in minimum volume hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(12):9858-9877.
[11]
Yao J, Hong D, Xu L, et al. Sparsity-enhanced convolutional decomposition:A novel tensor-based paradigm for blind hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:5505014.
[12]
Qin J, Lee H, Chi J T, et al. Blind hyperspectral unmixing based on graph total variation regularization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(4):3338-3351.
[13]
Cruz-Guerrero I A, Campos-Delgado D U, Mejía-Rodríguez A R. Extended blind end-member and abundance estimation with spatial total variation for hyperspectral imaging[C]// 2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).Mexico.IEEE, 2021: 1957-1960.
[14]
Shao Y, Lan J, Zhang Y, et al. Spectral unmixing of hyperspectral remote sensing imagery via preserving the intrinsic structure inva-riant[J]. Sensors, 2018, 18(10):3528.
[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]
Ekanayake E M M B, Weerasooriya H M H K, 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, 1853, 14:11853-11869.
[17]
Feng X R, Li H C, Li J, et al. Hyperspectral unmixing using sparsity-constrained deep nonnegative matrix factorization with total variation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(10):6245-6257.
[18]
Qu K, Li Z, Wang C, et al. Hyperspectral unmixing using higher-order graph regularized NMF with adaptive feature selection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:5511815.
[19]
Schaepman M E, Jehle M, Hueni A, et al. Advanced radiometry measurements and earth science applications with the airborne prism experiment (APEX)[J]. Remote Sensing of Environment, 2015, 158:207-219.
[20]
Yao J, Meng D, Zhao Q, et al. Nonconvex-sparsity and nonlocal-smoothness based blind hyperspectral unmixing[J]. IEEE Transactions on Image Processing:A Publication of the IEEE Signal Processing Society, 2019:2991-3006.
[21]
Ghosh P, Roy S K, Koirala B, et al. Hyperspectral unmixing using transformer network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:5535116.
2025, Vol. 37 
), 杨隆珊(
