سابِق|تال

Nonlinear hyperspectral unmixing algorithm based on deep autoencoder networks

  • role： First author第一作者
  • Affiliation：

    Key Laboratory of Digital Earth Sciences, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    University of Chinese Academy of Sciences, Beijing 100049, China

  • Email：hanzhuncut@outlook.com
  • Introduction： 韩竹, 1997年生, 女, 博士研究生, 研究方向为高光谱图像处理。E-mail: hanzhuncut@outlook.com
Han Zhu12,  
  • role： Corresponding author通信作者
  • Affiliation：

    Key Laboratory of Digital Earth Sciences, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

  • Email：gaolr@aircas.ac.cn
  • Introduction： 高连如, 1979年生, 男, 研究员, 研究方向为高光谱图像处理。E-mail: gaolr@aircas.ac.cn
Gao Lianru1*,  
  • Affiliation：

    Key Laboratory of Digital Earth Sciences, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    University of Chinese Academy of Sciences, Beijing 100049, China

Zhang Bing12,  
  • Affiliation：

    Key Laboratory of Digital Earth Sciences, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

Sun Xu1,  
  • Affiliation：

    Key Laboratory of Digital Earth Sciences, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

Li Qingting1

ملخص

The core of unmixing in hyperspectral images is to determine the mathematical form of the spectral mixing model in accordance with the radiative transmission characteristics of ground features and then obtain the endmember spectrum and abundance results. A nonlinear model is suitable for real mixed scenes because of the complexity of feature scenes. The accuracy of unmixing can be significantly improved by combining the advantages of autoencoder in internal structure data mining and feature extraction. However, this method cannot consider the collinearity of the model, resultingin overfittingand is sensitive to noise. This study proposed an unsupervised Enhanced Nonlinear AutoEncoder (ENAE) method. The introduction of endmember regularization reduces the collinearity between endmembers, thereby improving the accuracy of hyperspectral unmixing.The implementation steps of the ENAE method include two phases, where the first phaseis the initialization of the network structure, and the second phase is the nonlinear unmixing. The initialization phase determinesthe number of nodes of the encoder and initial value of endmember and abundance, and the nonlinear unmixing phase mainly realizesthe minimization of the loss function. The initialization of endmember and abundance aims to rapidly make the loss function converge. The objective function of the ENAE method includes the mean square error between the reconstructed and original images and endmember regularization. L2 regularization is used to constrain the weight of endmembers for enabling the ENAE to learn the nonlinear effect in the nonlinear mixing model. In the entire network iteration, the ENAE method is a self-learning process and does not require the participation of prior knowledge. Therefore, the ENAE method is an unsupervised nonlinear unmixing method.Experiments are conducted to validate the effectiveness of the proposed method. The experimental dataset includes simulation, urban real, and GF-5 satellite data. Three accuracy evaluation indices, namely, spectral angle distance, root mean square error of abundance, and image reconstruction error, are used to evaluate the effect of unmixing performance. Compared with the traditional nonlinear unmixing method, the deep learning method is superior in terms of endmember extraction and abundance estimation. The ENAE method can obtain high unmixing accuracy in the deep learning method, thereby provingthe effectiveness and robustness of the proposed method.The collinearity problem between endmembers is reduced by introducing the endmember regularization constraint in the autoencoder, thereby improving the accuracy of unmixing in hyperspectral images. In future work, we will introduce noise reduction, sparsity, and spatial information to improve the method and focus on obtaining the actual value of the pure ground spectrum to study the unmixing algorithm in hyperspectral images, which will be valuable in improving the application capabilities of hyperspectral remote sensing satellites in China. With the development of deep learning method interpretability research, exploring nonlinear unmixing methods withmany explanatory and physical meanings will be investigated forhyperspectral images withmixed pixel.

مفهوم

hyperspectral remote sensing;GF-5 satellite;autoencoder;mixed pixel;nonlinear unmixing

References

  1. 1.
    Altmann Y, Halimi A, Dobigeon and Tourneret J Y . 2012. Supervised nonlinear spectral unmixing using a postnonlinear mixing model for hyperspectral imagery. IEEE Transactions on Image Processing, 21(6): 3017-3025
  2. 2.
    Bioucas-Dias J M, Nascimento J M P . 2008. Hyperspectral subspace identification. IEEE Transactions on Geoscience and Remote Sensing, 46(8): 2435-2445
  3. 3.
    Chen J, Richard C and Honeine P . 2013. Nonlinear unmixing of hyperspectral data based on a linear-mixture/nonlinear-fluctuation model. IEEE Transactions on Signal Processing, 61(2): 480-492
  4. 4.
    Chen X H, Chen J, Jia X P, Somers B, Wu J and Coppin P . 2011. A quantitative analysis of virtual endmembers’ increased impact on the collinearity effect in spectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 49(8): 2945-2956
  5. 5.
    Cui G X and Li D K . 2018. Overview on deep learning based on automatic encoder algorithms. Computer Systems and Applications, 27(9): 47-51
  6. 6.
    Fan W Y, Hu B X, Miller J and Li M Z . 2009. Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated-forest hyperspectral data. International Journal of Remote Sensing, 30(11): 2951-2962
  7. 7.
    Guo R, Wang W and Qi H R . 2015. Hyperspectral image unmixing using autoencoder cascade//Proceedings of the 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Tokyo, Japan: IEEE: 1-4 [DOI: 10.1109/WHISPERS.2015.8075378]
  8. 8.
    Halimi A, Altmann Y, Dobigeon N and Tourneret J Y . 2011. Nonlinear unmixing of hyperspectral images using a generalized bilinear model. IEEE Transactions on Geoscience and Remote Sensing, 49(11): 4153-4162
  9. 9.
    Heinz D C and Chang C I . 2001. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 39(3): 529-545
  10. 10.
    Heylen R, Burazerovic D and Scheunders P . 2011. Non-linear spectral unmixing by geodesic simplex volume maximization. IEEE Journal of Selected Topics in Signal Processing, 5(3): 534-542
  11. 11.
    Heylen R and Scheunders P . 2016. A multilinear mixing model for nonlinear spectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 54(1): 240-251
  12. 12.
    Li J, Li XR, Huang B and Zhao LY . 2016. Hopfield neural network approach for supervised nonlinear spectral unmixing. IEEE Geoscience and Remote Sensing Letters, 13(7): 1002-1006
  13. 13.
    Licciardi G A and Del Frate F . 2011. Pixel unmixing in hyperspectral data by means of neural networks. IEEE Transactions on Geoscience and Remote Sensing, 49(11): 4163-4172
  14. 14.
    Nascimento J M P, Dias J M B . 2005. Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 43(4): 898-910
  15. 15.
    Ozkan S, Kaya B and Akar G B . 2019. EndNet: Sparse autoencoder network for endmember extraction and hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 57(1): 482-496
  16. 16.
    Palsson B, Sigurdsson J, Sveinsson J R and Ulfarsson M O . 2018. Hyperspectral unmixing using a neural network autoencoder. IEEE Access, 6: 25646-2565 6
  17. 17.
    Qu Y, Qi H R . 2019. uDAS: An untied denoising autoencoder with sparsity for spectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 57(3): 1698-1712
  18. 18.
    Raksuntorn N and Du Q . 2010. Nonlinear spectral mixture analysis for hyperspectral imagery in an unknown environment. IEEE Geoscience and Remote Sensing Letters, 7(4): 836-840
  19. 19.
    Somers B, Cools K, Delalieux S, Stuckens J, Van der Zande D, Verstraeten W W and Coppin P . 2009. Nonlinear hyperspectral mixture analysis for tree cover estimates in orchards. Remote Sensing of Environment, 113(6): 1183-1193
  20. 20.
    Srivastava N, Hinton G, Krizhevsky A, Sutskever I and Salakhutdinov R . 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15: 1929-1958
  21. 21.
    Su Y C, Li J, Plaza A, Marinoni A, Gamba P and Chakravortty S . 2019. DAEN: deep autoencoder networks for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 57(7): 4309-4321
  22. 22.
    Su Y C, Marinoni A, Li J, Plaza A and Gamba P . 2017. Nonnegative sparse autoencoder for robust endmember extraction from remotely sensed hyperspectral images//Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Fort Worth, TX, USA: IEEE: 205-208 [DOI: 10.1109/IGARSS.2017.8126930]
  23. 23.
    Taleb A and Jutten C . 1999. Source separation in post-nonlinear mixtures. IEEE Transactions on Signal Processing, 47(10): 2807-2820
  24. 24.
    Tong Q X, Zhang B, Zheng L F . 2006. Hyperspectral Remote Sensing. Beijing: Higher Education Press: 1-3
  25. 25.
    Wang M, Zhao M, Chen J and Rahardja S . 2019. Nonlinear unmixing of hyperspectral data via deep autoencoder networks. IEEE Geoscience and Remote Sensing Letters, 16(9): 1467-1471
  26. 26.
    Wu B, Zhang L P and Li P X . 2006. Unmixing hyperspectral imagery based on support vector nonlinear approximating regression. Journal of Remote Sensing, 10(3): 312-318
  27. 27.
    Yang B, Wang B and Wu Z M . 2018. Unsupervised nonlinear hyperspectral unmixing based on bilinear mixture models via geometric projection and constrained nonnegative matrix factorization. Remote Sensing, 10(5): 801
  28. 28.
    Yuan B . 2018. NMF hyperspectral unmixing algorithm combined with spatial and spectral correlation analysis. Journal of Remote Sensing, 22(2): 265-276
  29. 29.
    Zhang B and Sun X . 2015. Hyperspectral Images Unmixing Algorithm. Beijing: Science Press (张兵, 孙旭. 2015. 高光谱图像混合像元分解. 北京: 科学出版社)
  30. 30.
    Zhang X R, Sun Y J, Zhang J Y, Wu P and Jiao L C . 2018. Hyperspectral unmixing via deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 15(11): 1755-1759

قراءة النص الكامل

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website