Benchmark for Hyperspectral Unmixing Algorithm Evaluation
Volume 34, Issue 2 (2023), pp. 285–315
Pub. online: 15 June 2023
Type: Research Article
Open Access
Open Access
Received
1 December 2022
1 December 2022
Accepted
1 June 2023
1 June 2023
Published
15 June 2023
15 June 2023
Abstract
Over the past decades, many methods have been proposed to solve the linear or nonlinear mixing of spectra inside the hyperspectral data. Due to a relatively low spatial resolution of hyperspectral imaging, each image pixel may contain spectra from multiple materials. In turn, hyperspectral unmixing is finding these materials and their abundances. A few main approaches to performing hyperspectral unmixing have emerged, such as nonnegative matrix factorization (NMF), linear mixture modelling (LMM), and, most recently, autoencoder networks. These methods use different approaches in finding the endmember and abundance of information from hyperspectral images. However, due to the huge variation of hyperspectral data being used, it is difficult to determine which methods perform sufficiently on which datasets and if they can generalize on any input data to solve hyperspectral unmixing problems. By trying to mitigate this problem, we propose a hyperspectral unmixing algorithm testing methodology and create a standard benchmark to test already available and newly created algorithms. A few different experiments were created, and a variety of hyperspectral datasets in this benchmark were used to compare openly available algorithms and to determine the best-performing ones.
References
BaySpec (2021). OCI™-F Hyperspectral Imager (VIS-NIR, SWIR). [Read on: 2021-10-12]. https://www.bayspec.com/spectroscopy/oci-f-hyperspectral-imager/.
Bioucas-Dias, J.M., Figueiredo, M.A.T. (2010). Alternating direction algorithms for constrained sparse regression: Application to hyperspectral unmixing. In: 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, pp. 1–4. https://doi.org/10.1109/WHISPERS.2010.5594963.
Bioucas-Dias, J.M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., Chanussot, J. (2012). Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 354–379. https://doi.org/10.1109/JSTARS.2012.2194696.
Borsoi, R.A., Imbiriba, T., Bermudez, J.C.M. (2020). Deep generative endmember modeling: an application to unsupervised spectral unmixing. IEEE Transactions on Computational Imaging, 6, 374–384. https://doi.org/10.1109/TCI.2019.2948726.
Dong, L., Yuan, Y., Lu, X. (2020). Spectral-spatial joint sparse NMF for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 59(3), 2391–2402. https://doi.org/10.1109/TGRS.2020.3006109.
Feng, X.-R., Li, H.-C., Liu, S., Zhang, H. (2022). Correntropy-based autoencoder-like NMF with total variation for hyperspectral unmixing. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. https://doi.org/10.1109/LGRS.2020.3020896.
Gabay, D., Mercier, B. (1976). A dual algorithm for the solution of nonlinear variational problems via finite element approximation. Computers & Mathematics with Applications, 2(1), 17–40. https://doi.org/10.1016/0898-1221(76)90003-1.
Goel, P.K., Prasher, S.O., Patel, R.M., Landry, J.A., Bonnell, R.B., Viau, A.A. (2003). Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn. Computers and Electronics in Agriculture, 39(2), 67–93. https://doi.org/10.1016/S0168-1699(03)00020-6. https://www.sciencedirect.com/science/article/pii/S0168169903000206.
Guo, Y., Han, S., Li, Y., Zhang, C., Bai, Y. (2018). K-nearest neighbor combined with guided filter for hyperspectral image classification. Procedia Computer Science, 129, 159–165. 2017 International Conference on Identification, Information and Knowledge in the Internet of Things. https://doi.org/10.1016/j.procs.2018.03.066. https://www.sciencedirect.com/science/article/pii/S1877050918302904.
Guo, Z., Wittman, T., Osher, S. (2009). L1 unmixing and its application to hyperspectral image enhancement. In: Proceedings SPIE Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV. https://doi.org/10.1117/12.818245.
Hapke, B. (1981). Bidirectional reflectance spectroscopy: 1. Theory. Journal of Geophysical Research: Solid Earth, 86(B4), 3039–3054. https://doi.org/10.1029/JB086iB04p03039. https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/JB086iB04p03039.
He, W., Zhang, H., Zhang, L. (2017). Total variation regularized reweighted sparse nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 55(7), 3909–3921. https://doi.org/10.1109/TGRS.2017.2683719.
Hong, D., Yokoya, N., Chanussot, J., Zhu, X.X. (2019). An augmented linear mixing model to address spectral variability for hyperspectral unmixing. IEEE Transactions on Image Processing, 28(4), 1923–1938. https://doi.org/10.1109/TIP.2018.2878958.
Hua, Z., Li, X., Qiu, Q., Zhao, L. (2021). Autoencoder network for hyperspectral unmixing with adaptive abundance smoothing. IEEE Geoscience and Remote Sensing Letters, 18(9), 1640–1644. https://doi.org/10.1109/LGRS.2020.3005999.
Houston dataset of Science and Technology (2021). Hyperspectral Data Set. [Last read on: 2021-10-10]. http://lesun.weebly.com/hyperspectral-data-set.html.
Iordache, M., Bioucas-Dias, J.M., Plaza, A. (2012). Total variation spatial regularization for sparse hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 50(11), 4484–4502. https://doi.org/10.1109/TGRS.2012.2191590.
Iordache, M., Bioucas-Dias, J.M., Plaza, A. (2014). Collaborative sparse regression for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 52(1), 341–354. https://doi.org/10.1109/TGRS.2013.2240001.
Kaya, A., Ataş, K., Kahraman, S. (2021). LiDAR-aided total variation regularized nonnegative tensor factorization for hyperspectral unmixing. In: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp. 5063–5066. https://doi.org/10.1109/IGARSS47720.2021.9553137.
Koirala, B., Khodadadzadeh, M., Contreras, C., Zahiri, Z., Gloaguen, R., Scheunders, P. (2019). A supervised method for nonlinear hyperspectral unmixing. Remote Sensing, 11(20), 2458. https://doi.org/10.3390/rs11202458.
Kokaly, R.F., Clark, R.N., Swayze, G.A., Livo, K.E., Hoefen, T.M., Pearson, N.C., Wise, R.A., Benzel, W.M., Lowers, H.A., Driscoll, R.L., Klein, A.J. (2017). USGS Spectral Library Version 7. Technical report, Reston, VA. https://doi.org/10.3133/ds1035.
Li, H., Feng, R., Wang, L., Zhong, Y., Zhang, L. (2021). Superpixel-based reweighted low-rank and total variation sparse unmixing for hyperspectral remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 59(1), 629–647. https://doi.org/10.1109/TGRS.2020.2994260.
Li, J., Bioucas-Dias, J.M., Plaza, A., Liu, L. (2016). Robust collaborative nonnegative matrix factorization for hyperspectral Unmixing. IEEE Transactions on Geoscience and Remote Sensing, 54(10), 6076–6090. https://doi.org/10.1109/TGRS.2016.2580702.
Li, X., Huang, R., Zhao, L. (2021). Correntropy-based spatial-spectral robust sparsity-regularized hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 59(2), 1453–1471. https://doi.org/10.1109/TGRS.2020.2999936.
Lu, X., Wu, H., Yuan, Y., Yan, P., Li, X. (2013). Manifold regularized sparse NMF for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 51(5), 2815–2826. https://doi.org/10.1109/TGRS.2012.2213825.
Lu, X., Dong, L., Yuan, Y. (2020). Subspace clustering constrained sparse NMF for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 58(5), 3007–3019. https://doi.org/10.1109/TGRS.2019.2946751.
NASA (2004). The Advanced Spaceborne Thermal Emission and Reflection Radiometer. [Last read on: 2021-11-01]. https://asterweb.jpl.nasa.gov/.
NASA (2015). AVIRIS Data – Ordering Free AVIRIS Standard Data Products. [Last read on: 2021-10-10]. https://aviris.jpl.nasa.gov/data/free_data.html.
Palsson, B., Ulfarsson, M.O., Sveinsson, J.R. (2021). Convolutional autoencoder for spectral–spatial hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 59(1), 535–549. https://doi.org/10.1109/TGRS.2020.2992743.
Peng, J., Sun, W., Jiang, F., Chen, H., Zhou, Y., Du, Q. (2022). A general loss-based nonnegative matrix factorization for hyperspectral unmixing. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. https://doi.org/10.1109/LGRS.2020.3017233.
Prasad, S., Le Saux, B., Yokoya, N., Hansch, R. (2020). 2018 IEEE GRSS data fusion challenge – fusion of multispectral LiDAR and hyperspectral data. IEEE Dataport. https://doi.org/10.21227/jnh9-nz89.
Qi, L., Li, J., Wang, Y., Huang, Y., Gao, X. (2020). Spectral–spatial-weighted multiview collaborative sparse unmixing for hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 58(12), 8766–8779. https://doi.org/10.1109/TGRS.2020.2990476.
Ranasinghe, Y., Weerasooriya, K., Godaliyadda, R., Herath, V., Ekanayake, P., Jayasundara, D., Ramanayake, L., Senarath, N., Wickramasinghe, D. (2022). GAUSS: Guided Encoder-Decoder Architecture for Hyperspectral Unmixing with Spatial Smoothness. https://doi.org/10.48550/ARXIV.2204.07713.
Schaepman, M.E., Jehle, M., Hueni, A., D’Odorico, P., Damm, A., Weyermann, J., Schneider, F.D., Laurent, V., Popp, C., Seidel, F.C., Lenhard, K., Gege, P., Küchler, C., Brazile, J., Kohler, P., De Vos, L., Meuleman, K., Meynart, R., Schläpfer, D., Kneubühler, M., Itten, K.I. (2015). Advanced radiometry measurements and Earth science applications with the Airborne Prism Experiment (APEX). Remote Sensing of Environment, 158, 207–219. https://doi.org/10.1016/j.rse.2014.11.014. https://www.sciencedirect.com/science/article/pii/S0034425714004568.
Su, H., Jia, C., Zheng, P., Du, Q. (2022). Superpixel-based weighted collaborative sparse regression and reweighted low-rank representation for hyperspectral image unmixing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 393–408. https://doi.org/10.1109/JSTARS.2021.3133428.
Su, Y., Xu, X., Li, J., Qi, H., Gamba, P., Plaza, A. (2021). Deep autoencoders with multitask learning for bilinear hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 59(10), 8615–8629. https://doi.org/10.1109/TGRS.2020.3041157.
Wang, J.-J., Wang, D.-C., Huang, T.-Z., Huang, J. (2021). Endmember constraint non-negative tensor factorization via total variation for hyperspectral unmixing. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp. 3313–3316. https://doi.org/10.1109/IGARSS47720.2021.9554468.
Wang, X., Zhong, Y., Zhang, L., Xu, Y. (2017). Spatial group sparsity regularized nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 55(11), 6287–6304. https://doi.org/10.1109/TGRS.2017.2724944.
Xu, Y., Yin, W., Wen, Z., Zhang, Y. (2012). An alternating direction algorithm for matrix completion with nonnegative factors. Frontiers of Mathematics in China, 7(2), 365–384. https://doi.org/10.1007/s11464-012-0194-5.
Yokoya, N., Yairi, T., Iwasaki, A. (2012). Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion. IEEE Transactions on Geoscience and Remote Sensing, 50(2), 528–537. https://doi.org/10.1109/TGRS.2011.2161320.
Zhang, G., Mei, S., Xie, B., Ma, M., Zhang, Y., Feng, Y., Du, Q. (2022). Spectral variability augmented sparse unmixing of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–13. https://doi.org/10.1109/TGRS.2022.3169228.
Zhang, S., Li, J., Li, H., Deng, C., Plaza, A. (2018). Spectral–spatial weighted sparse regression for hyperspectral image unmixing. IEEE Transactions on Geoscience and Remote Sensing, 56(6), 3265–3276. https://doi.org/10.1109/TGRS.2018.2797200.
Zhang, S., Zhang, G., Li, F., Deng, C., Wang, S., Plaza, A., Li, J. (2022). Spectral-spatial hyperspectral unmixing using nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–13. https://doi.org/10.1109/TGRS.2021.3074364.
Zhang, X., Tong, X.-H., Liu, M.-L. (2009). An improved N-FINDR algorithm for endmember extraction in hyperspectral imagery. In: 2009 Joint Urban Remote Sensing Event, pp. 1–5. https://doi.org/10.1109/URS.2009.5137677.
Zhao, M., Chen, J., He, Z. (2019). A laboratory-created dataset with ground-truth for hyperspectral unmixing evaluation. CoRR, abs/1902.08347. http://arxiv.org/abs/1902.08347.
Zhao, M., Yan, L., Chen, J. (2021a). LSTM-DNN based autoencoder network for nonlinear hyperspectral image unmixing. IEEE Journal of Selected Topics in Signal Processing, 15(2), 295–309. https://doi.org/10.1109/JSTSP.2021.3052361.
Zhao, Z., Wang, H., Liang, Y., Huang, T., Xiao, Y., Yu, X. (2021b). Sparsity constrained convolutional autoencoder network for hyperspectral image unmixing. In: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, pp. 3317–3320. https://doi.org/10.1109/IGARSS47720.2021.9553239.
Zhu, F. (2017). Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey. arXiv:1708.05125.
Zhu, F., Wang, Y., Fan, B., Xiang, S., Meng, G., Pan, C. (2014a). Spectral unmixing via data-guided sparsity. IEEE Transactions on Image Processing, 23(12), 5412–5427. https://doi.org/10.1109/tip.2014.2363423.
Zhu, F., Wang, Y., Xiang, S., Fan, B., Pan, C. (2014b). Structured sparse method for hyperspectral unmixing. ISPRS Journal of Photogrammetry and Remote Sensing, 88, 101–118. https://doi.org/10.1016/j.isprsjprs.2013.11.014. https://www.sciencedirect.com/science/article/pii/S0924271613002761.
