Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

AE-RED: A Hyperspectral Unmixing Framework Powered by Deep Autoencoder and Regularization by Denoising (2307.00269v1)

Published 1 Jul 2023 in cs.CV and eess.IV

Abstract: Spectral unmixing has been extensively studied with a variety of methods and used in many applications. Recently, data-driven techniques with deep learning methods have obtained great attention to spectral unmixing for its superior learning ability to automatically learn the structure information. In particular, autoencoder based architectures are elaborately designed to solve blind unmixing and model complex nonlinear mixtures. Nevertheless, these methods perform unmixing task as blackboxes and lack of interpretability. On the other hand, conventional unmixing methods carefully design the regularizer to add explicit information, in which algorithms such as plug-and-play (PnP) strategies utilize off-the-shelf denoisers to plug powerful priors. In this paper, we propose a generic unmixing framework to integrate the autoencoder network with regularization by denoising (RED), named AE-RED. More specially, we decompose the unmixing optimized problem into two subproblems. The first one is solved using deep autoencoders to implicitly regularize the estimates and model the mixture mechanism. The second one leverages the denoiser to bring in the explicit information. In this way, both the characteristics of the deep autoencoder based unmixing methods and priors provided by denoisers are merged into our well-designed framework to enhance the unmixing performance. Experiment results on both synthetic and real data sets show the superiority of our proposed framework compared with state-of-the-art unmixing approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. N. Dobigeon, L. Tits, B. Somers, Y. Altmann, and P. Coppin, “A comparison of nonlinear mixing models for vegetated areas using simulated and real hyperspectral data,” IEEE J. Sel. Topics Appl. Earth Observations Remote Sensing, vol. 7, no. 6, pp. 1869–1878, June 2014.
  2. P. W. Yuen and M. Richardson, “An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition,” The Imaging Science Journal, vol. 58, no. 5, pp. 241–253, 2010.
  3. Y. Duan, H. Huang, and T. Wang, “Semisupervised feature extraction of hyperspectral image using nonlinear geodesic sparse hypergraphs,” IEEE Trans. Geosci. Remote Sens., 2021.
  4. F. Luo, L. Zhang, B. Du, and L. Zhang, “Dimensionality reduction with enhanced hybrid-graph discriminant learning for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 8, pp. 5336–5353, 2020.
  5. J. M. Bioucas-Dias, A. Plaza, G. Camps-Valls, P. Scheunders, N. Nasrabadi, and J. Chanussot, “Hyperspectral remote sensing data analysis and future challenges,” IEEE Geosci. Remote Sens. Mag., vol. 1, no. 2, pp. 6–36, 2013.
  6. N. Dobigeon, J.-Y. Tourneret, C. Richard, J. C. M. Bermudez, S. McLaughlin, and A. O. Hero, “Nonlinear unmixing of hyperspectral images: Models and algorithms,” IEEE Signal Proc. Mag., vol. 31, no. 1, pp. 82–94, 2013.
  7. R. A. Borsoi, T. Imbiriba, J. C. M. Bermudez, C. Richard, J. Chanussot, L. Drumetz, J.-Y. Tourneret, A. Zare, and C. Jutten, “Spectral variability in hyperspectral data unmixing: A comprehensive review,” IEEE Geosci. Remote Sens. Mag., vol. 9, no. 4, pp. 223–270, 2021.
  8. L. Dong, Y. Yuan, and X. Luxs, “Spectral–spatial joint sparse NMF for hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 3, pp. 2391–2402, 2020.
  9. M. Zhao, T. Gao, J. Chen, and W. Chen, “Hyperspectral unmixing via nonnegative matrix factorization with handcrafted and learned priors,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2021.
  10. B. Palsson, M. O. Ulfarsson, and J. R. Sveinsson, “Convolutional autoencoder for spectral–spatial hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 1, pp. 535–549, 2020.
  11. L. Gao, Z. Han, D. Hong, B. Zhang, and J. Chanussot, “CyCU-Net: Cycle-consistency unmixing network by learning cascaded autoencoders,” IEEE Trans. Geosci. Remote Sens., 2021.
  12. S. Ozkan, B. Kaya, and G. B. Akar, “Endnet: Sparse autoencoder network for endmember extraction and hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 1, pp. 482–496, 2018.
  13. L. Miao and H. Qi, “Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization,” IEEE Trans. Geosci. Remote Sens., vol. 45, no. 3, pp. 765–777, 2007.
  14. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza, “Collaborative sparse regression for hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 52, no. 1, pp. 341–354, 2013.
  15. P. V. Giampouras, K. E. Themelis, A. A. Rontogiannis, and K. D. Koutroumbas, “Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 8, pp. 4775–4789, 2016.
  16. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza, “Total variation spatial regularization for sparse hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 50, no. 11, pp. 4484–4502, 2012.
  17. A. Halimi, Y. Altmann, N. Dobigeon, and J.-Y. Tourneret, “Nonlinear unmixing of hyperspectral images using a generalized bilinear model,” IEEE Trans. Geosci. Remote Sens., vol. 49, no. 11, pp. 4153–4162, 2011.
  18. J. Chen, M. Zhao, X. Wang, C. Richard, and S. Rahardja, “Integration of physics-based and data-driven models for hyperspectral image unmixing: A summary of current methods,” IEEE Signal Proc. Mag., vol. 40, no. 2, pp. 61–74, 2023.
  19. X. Zhang, Y. Yuan, and X. Li, “Sparse unmixing based on adaptive loss minimization,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–14, 2022.
  20. J. Peng, W. Sun, H.-C. Li, W. Li, X. Meng, C. Ge, and Q. Du, “Low-rank and sparse representation for hyperspectral image processing: A review,” IEEE Geosci. Remote Sens. Mag., 2021.
  21. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
  22. I. Sutskever, J. Martens, G. Dahl, and G. Hinton, “On the importance of initialization and momentum in deep learning,” in International conference on machine learning.   PMLR, 2013, pp. 1139–1147.
  23. J. Sigurdsson, M. O. Ulfarsson, and J. R. Sveinsson, “Hyperspectral unmixing with ℓpsubscriptℓ𝑝\ell_{p}roman_ℓ start_POSTSUBSCRIPT italic_p end_POSTSUBSCRIPT regularization,” IEEE Trans. Geosci. Remote Sens., vol. 52, no. 11, pp. 6793–6806, 2014.
  24. Y. Zhong, R. Feng, and L. Zhang, “Non-local sparse unmixing for hyperspectral remote sensing imagery,” IEEE J. Sel. Top. Appl. Earth Observat. Remote Sens., vol. 7, no. 6, pp. 1889–1909, 2013.
  25. X. Wang, Y. Zhong, L. Zhang, and Y. Xu, “Spatial group sparsity regularized nonnegative matrix factorization for hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 11, pp. 6287–6304, 2017.
  26. A. Lagrange, M. Fauvel, S. May, and N. Dobigeon, “Matrix cofactorization for joint spatial–spectral unmixing of hyperspectral images,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 7, pp. 4915–4927, 2020.
  27. L. Tong, J. Zhou, B. Qian, J. Yu, and C. Xiao, “Adaptive graph regularized multilayer nonnegative matrix factorization for hyperspectral unmixing,” IEEE J. Sel. Top. Appl. Earth Observat. Remote Sens., vol. 13, pp. 434–447, 2020.
  28. M. Zhao, X. Wang, J. Chen, and W. Chen, “A plug-and-play priors framework for hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2021.
  29. Z. Wang, L. Zhuang, L. Gao, A. Marinoni, B. Zhang, and M. K. Ng, “Hyperspectral nonlinear unmixing by using plug-and-play prior for abundance maps,” Remote Sensing, vol. 12, no. 24, p. 4117, 2020.
  30. Y. Qu and H. Qi, “uDAS: An untied denoising autoencoder with sparsity for spectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 3, pp. 1698–1712, 2018.
  31. M. Zhao, L. Yan, and J. Chen, “LSTM-DNN based autoencoder network for nonlinear hyperspectral image unmixing,” IEEE J. Sel. Top. Sig. Process., vol. 15, no. 2, pp. 295–309, 2021.
  32. M. Zhao, M. Wang, J. Chen, and S. Rahardja, “Hyperspectral unmixing for additive nonlinear models with a 3-D-CNN autoencoder network,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2021.
  33. Z. Hua, X. Li, Y. Feng, and L. Zhao, “Dual branch autoencoder network for spectral-spatial hyperspectral unmixing,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2021.
  34. M. Wang, M. Zhao, J. Chen, and R. Susanto, “Nonlinear unmixing of hyperspectral data via deep autoencoder network,” IEEE Geosci. Remote Sens. Lett., pp. 1–5, 2019.
  35. K. T. Shahid and I. D. Schizas, “Unsupervised hyperspectral unmixing via nonlinear autoencoders,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2021.
  36. R. Borsoi, T. Imbiriba, and J. Bermudez, “Deep generative endmember modeling: An application to unsupervised spectral unmixing,” IEEE Trans. Comput. Imag., vol. 6, pp. 374–384, 2019.
  37. S. Shi, M. Zhao, L. Zhang, Y. Altmann, and J. Chen, “Probabilistic generative model for hyperspectral unmixing accounting for endmember variability,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022.
  38. Y. Qian, F. Xiong, Q. Qian, and J. Zhou, “Spectral mixture model inspired network architectures for hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 10, pp. 7418–7434, 2020.
  39. F. Xiong, J. Zhou, S. Tao, J. Lu, and Y. Qian, “SNMF-Net: Learning a deep alternating neural network for hyperspectral unmixing,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–16, 2021.
  40. Z. Lai, K. Wei, and Y. Fu, “Deep plug-and-play prior for hyperspectral image restoration,” Neurocomputing, vol. 481, pp. 281–293, 2022.
  41. R. Dian, S. Li, and X. Kang, “Regularizing hyperspectral and multispectral image fusion by CNN denoiser,” IEEE transactions on neural networks and learning systems, vol. 32, no. 3, pp. 1124–1135, 2020.
  42. Y. Romano, M. Elad, and P. Milanfar, “The little engine that could: Regularization by denoising (RED),” SIAM Journal on Imaging Sciences, vol. 10, no. 4, pp. 1804–1844, 2017.
  43. A. Buades, B. Coll, and J.-M. Morel, “Non-local means denoising,” Image Processing On Line, vol. 1, pp. 208–212, 2011.
  44. M. Maggioni, V. Katkovnik, K. Egiazarian, and A. Foi, “Nonlocal transform-domain filter for volumetric data denoising and reconstruction,” IEEE Trans. Image Process., vol. 22, no. 1, pp. 119–133, 2012.
  45. B. Rasti, B. Koirala, P. Scheunders, and P. Ghamisi, “UnDIP: Hyperspectral unmixing using deep image prior,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2021.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now