Abstract
Hyperspectral cameras acquire images containing information across the electromagnetic spectrum, which convey useful information about the scene. To enable effective analysis of such data, spectral unmixing is often used. It is an important task in hyperspectral imaging, allowing one to obtain the information about spectral endmembers which make up each hyperspectral pixel. This task, traditionally solved with dedicated statistical methods, has recently been explored with deep learning methods. One of the methods well-suited to this task are autoencoders. These neural networks are initialized using multiple random weights, and their initialization often has a significant impact on their efficiency. Because of that, to improve the initialization of autoencoders for the spectral unmixing task, we propose to use the pre-training scheme consisting of clustering-based artificial labeling. We test the approach on two popular hyperspectral datasets, i.e. Samson and Jasper Ridge. Our experiment delivers promising results, improving autoencoders effectiveness in the case of Samson dataset, i.e. for 25-class labeling endmembers’ and abundances’ errors improve by 0.045 and 0.008, respectively. The worse results in the case of Jasper Ridge dataset (improvement of the endmembers’ error by 0.001, and worsening of the abundances’ error by 0.006 for 25-classes labeling) show that more research is required to understand when the proposed approach improves the results of the spectral unmixing. The auxiliary experiments that we also conduct allow us to partially answer that question.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The source code is available at the following link: https://github.com/iitis/ClusteringAE.
- 2.
Please note that this experiment was added during the review process, after the main experiment described later. It was placed earlier in the paper to make the presentation easier for the reader.
- 3.
During the publication process, it was discovered that abundances error values for the baseline model were incorrectly reported due to the wrong order of the abundances values in the prepared dataset. This was fixed in the final version of the paper and does not affect the conclusions of this work.
References
Bhatt, J.S., Joshi, M.V.: Deep learning in hyperspectral unmixing: a review. In: IGARSS 2020–2020 IEEE International Geoscience and Remote Sensing Symposium, pp. 2189–2192 (2020). https://doi.org/10.1109/IGARSS39084.2020.9324546
Bioucas-Dias, J.M.: A variable splitting augmented Lagrangian approach to linear spectral unmixing. In: 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, pp. 1–4 (2009)
Bioucas-Dias, J.M., et al.: Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 5(2), 354–379 (2012). https://doi.org/10.1109/JSTARS.2012.2194696
Chapelle, O., Schlkopf, B., Zien, A.: Semi-supervised learning. In: IEEE Transactions on Neural Networks, vol. 20 (2006)
Dobigeon, N., Moussaoui, S., Coulon, M., Tourneret, J.Y., Hero, A.O.: Joint Bayesian endmember extraction and linear unmixing for hyperspectral imagery. IEEE Trans. Signal Process. 57(11), 4355–4368 (2009). https://doi.org/10.1109/TSP.2009.2025797
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 9, pp. 249–256. PMLR, Chia Laguna Resort, Sardinia, Italy (2010). https://proceedings.mlr.press/v9/glorot10a.html
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Jia, S., Qian, Y.: Constrained nonnegative matrix factorization for hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 47(1), 161–173 (2009). https://doi.org/10.1109/TGRS.2008.2002882
Khajehrayeni, F., Ghassemian, H.: Hyperspectral unmixing using deep convolutional autoencoders in a supervised scenario. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 13, 567–576 (2020). https://doi.org/10.1109/JSTARS.2020.2966512
Krizhevsky, A., Hinton, G.E.: Using very deep autoencoders for content-based image retrieval. In: ESANN, vol. 1, p. 2. Citeseer (2011)
Książek, K., Głomb, P., Romaszewski, M., Cholewa, M., Grabowski, B.: Stable training of autoencoders for hyperspectral unmixing (2021)
Masarczyk, W., Głomb, P., Grabowski, B., Ostaszewski, M.: Effective training of deep convolutional neural networks for hyperspectral image classification through artificial labeling. Remote Sens. 12(16) (2020). https://doi.org/10.3390/rs12162653, https://www.mdpi.com/2072-4292/12/16/2653
Nascimento, J., Dias, J.: Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans. Geosci. Remote Sens. 43(4), 898–910 (2005). https://doi.org/10.1109/TGRS.2005.844293
Nascimento, J.M.P., Bioucas-Dias, J.M.: Hyperspectral unmixing based on mixtures of dirichlet components. IEEE Trans. Geosci. Remote Sens. 50(3), 863–878 (2012). https://doi.org/10.1109/TGRS.2011.2163941
Palsson, B., Ulfarsson, M.O., Sveinsson, J.R.: Convolutional autoencoder for spectral-spatial hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 59(1), 535–549 (2021). https://doi.org/10.1109/TGRS.2020.2992743
Palsson, F., Sigurdsson, J., Sveinsson, J.R., Ulfarsson, M.O.: Neural network hyperspectral unmixing with spectral information divergence objective. In: 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 755–758 (2017). https://doi.org/10.1109/IGARSS.2017.8127062
Ruiz-Garcia, A., Elshaw, M., Altahhan, A., Palade, V.: Stacked deep convolutional auto-encoders for emotion recognition from facial expressions. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1586–1593 (2017). https://doi.org/10.1109/IJCNN.2017.7966040
Su, Y., Li, J., Plaza, A., Marinoni, A., Gamba, P., Chakravortty, S.: Daen: deep autoencoder networks for hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 57(7), 4309–4321 (2019). https://doi.org/10.1109/TGRS.2018.2890633
Su, Y., Xu, X., Li, J., Qi, H., Gamba, P., Plaza, A.: Deep autoencoders with multitask learning for bilinear hyperspectral unmixing. IEEE Trans. Geosci. Remote Sens. 59(10), 8615–8629 (2021). https://doi.org/10.1109/TGRS.2020.3041157
Winter, M.E.: N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data. In: Descour, M.R., Shen, S.S. (eds.) Imaging Spectrometry V, vol. 3753, pp. 266–275. International Society for Optics and Photonics, SPIE (1999). https://doi.org/10.1117/12.366289
Zhao, M., Wang, M., Chen, J., Rahardja, S.: Hyperspectral unmixing for additive nonlinear models with a 3-D-CNN autoencoder network. IEEE Trans. Geosci. Remote Sens., pp. 1–15 (2021). https://doi.org/10.1109/TGRS.2021.3098745
Zhu, F.: Hyperspectral unmixing: Ground truth labeling, datasets, benchmark performances and survey. Computer Vision and Pattern Recognition (2017)
Acknowledgements
B.G. acknowledges funding from the budget funds for science in the years 2018–2022, as a scientific project ”Application of transfer learning methods in the problem of hyperspectral images classification using convolutional neural networks” under the ”Diamond Grant” program, no. DI2017 013847. K.K. acknowledges funding from the European Union through the European Social Fund (grant POWR.03.02.00-00-I029). We would like to thank the anonymous reviewers for their suggestions and comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Grabowski, B., Głomb, P., Książek, K., Buza, K. (2022). Improving Autoencoders Performance for Hyperspectral Unmixing Using Clustering. In: Szczerbicki, E., Wojtkiewicz, K., Nguyen, S.V., Pietranik, M., Krótkiewicz, M. (eds) Recent Challenges in Intelligent Information and Database Systems. ACIIDS 2022. Communications in Computer and Information Science, vol 1716. Springer, Singapore. https://doi.org/10.1007/978-981-19-8234-7_9
Download citation
DOI: https://doi.org/10.1007/978-981-19-8234-7_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8233-0
Online ISBN: 978-981-19-8234-7
eBook Packages: Computer ScienceComputer Science (R0)