Abstract
Remote sensing data has shown tremendous potential for applications in various fields like land use mapping and detection, geologic mapping, water resource applications, wetland mapping, urban and regional planning, environment inventory, natural disaster assessment, archaeological applications, and others. Every day, thousands of gigabytes of memory are involved in capturing the hyperspectral remote sensing datasets. The compelling information present in these hyperspectral images (HSIs) is very minimal due to redundancy. Spatial and spectral correlations monopolize the acquired HSI data sets. Therefore, an algorithm that exploits these correlations and compresses the HSI tensors is proposed in this paper. First, the acquired HSI image (reflectance data) is subjected to the removal of geometric and radiometric errors. Second, spectral bands of interest affiliated to the underlying application are exclusively processed for principal component analysis (PCA). Results of this PCA are scrutinized to identify the absolute dependent components. Further, these components are exposed to a non-iterative factorized compression technique. As a result, HSI 3D tensors are disintegrated into 1D tensors. This tensor breakdown leads to a compression ratio as high as 3747:1 while the total encoding time observed is 332 s and RMSE is as low as 0.0017. Later, the original HSI is reconstructed back by the product of decomposed individual tensors and its PSNR is 53.03 dB. The proposed compression method targets the tucker decomposition-based HSI compression technique which is computationally complex and time consuming, and hence, a breakthrough is achieved with the technique introduced.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Yang, C., Everitt, J.H.: . Precision Agric 13, 62 (2012). https://doi.org/10.1007/s11119-011-9248-z
Cao, X., Li, R., Wen, L., Feng, J., Jiao, L.: Deep multiple feature fusion for hyperspectral image classification. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 11(10), 3880–3891 (2018)
Marinoni, A., Clenet, H.: Higher order nonlinear hyperspectral unmixing for mineralogical analysis over extraterrestrial bodies. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 10(8), 3722–3733 (2017)
Park, B., Yoon, S.C., Windham, W.R., et al.: . Sens. Instrumen. Food Qual. 5, 25 (2011). https://doi.org/10.1007/s11694-011-9107-7
Moriya, E.́A.S., Imai, N.N., Tommaselli, A.M.G., Miyoshi, G.T.: Mapping mosaic virus in sugarcane based on hyperspectral images. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 10(2), 740–748 (2017)
Aviris.jpl.nasa.gov.: AVIRIS - airborne visible / infrared imaging spectrometer. [online] Available at: https://aviris.jpl.nasa.gov/index.html (2018)
Aviris.jpl.nasa.gov.: AVIRIS - airborne visible / infrared imaging spectrometer - concept. [online] Available at: https://aviris.jpl.nasa.gov/aviris/concept.html (2018)
Lee, C.M., et al.: An introduction to the NASA Hyperspectral InfraRed Imager (HyspIRI) mission and preparatory activities. Remote Sens. Environ. 167, 6–19 (2015)
Huo, C., Zhang, R., Peng, T.: Lossless compression of hyperspectral images based on searching optimal multibands for prediction. IEEE Geosci. Remote Sens. Lett. 6(2), 339–343 (2009)
Licciardi, G.A., Chanussot, J., Piscini, A.: Spectral compression of hyperspectral images by means of nonlinear principal component analysis decorrelation. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 5092–5096, Paris (2014), https://doi.org/10.1109/ICIP.2014.7026031
Ertürk, A., Ertürk, S.: Seam carving for hyperspectral image size reduction and unmixing. In: 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1752–1755, Fort Worth (2017)
Ryan, M.J., Arnold, J.F. : Lossy compression of hyperspectral data using vector quantization. Remote Sens. Environ. 61(3), 419–436 (1997)
Settle, J.: On the dimensionality of multi-view hyperspectral measurements of vegetation. Remote Sens. Environ. 90(2), 235–242 (2004)
Warner, T.A., Shank, M.C.: Spatial autocorrelation analysis of hyperspectral imagery for feature selection. Remote Sens. Environ. 60(1), 58–70 (1997)
Senay, S., Erives, H.: Low complexity dimensionality reduction for hyperspectral images. In: 2014 48th Asilomar Conference on Signals, Systems and Computers, pp. 1551–1554, Pacific Grove (2014), https://doi.org/10.1109/ACSSC.2014.7094724
Falco, N., Bruzzone, L., Benediktsson, J.A.: A comparative study of different ICA algorithms for hyperspectral image analysis. In: 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), pp. 1–4, Gainesville (2013)
Falco, N., Benediktsson, J.A., Bruzzone, L.: Spectral and spatial classification of hyperspectral images based on ICA and reduced morphological attribute profiles. IEEE Trans. Geosci. Remote Sens. 53(11), 6223–6240 (2015)
Hou, Y., Liu, G.: Lossy-to-lossless compression of hyperspectral image using the improved AT-3D SPIHT algorithm. In: 2008 International Conference on Computer Science and Software Engineering, pp. 963–966, Wuhan (2008)
Christophe, E., Mailhes, C., Duhamel, P.: Hyperspectral image compression: Adapting SPIHT and EZW to anisotropic 3-D wavelet coding. IEEE Trans. Image Process. 17(12), 2334–2346 (2008)
Lee, S., Lee, E., Choi, H., Lee, C.: Compression of hyperspectral images with 2D wavelet transform using adjacent information and SPIHT slgorithm, Proceedings. In: 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS ’05, p. 3 (2005), https://doi.org/10.1109/IGARSS.2005.1526118
Du, Q., Fowler, J.E.: Hyperspectral image compression using JPEG2000 and principal component analysis. IEEE Geosci. Remote Sensing Lett. 4(2), 201–205 (April 2007)
Zemliachenko, A., Lukin, V., Vozel, B.: Lossy compression of hyperspectral images based on JPEG2000. In: 2017 4th International Scientific-Practical Conference Problems of Infocommunications, Science and Technology (PIC SandT), pp. 600–603, Kharkov (2017)
Menon, V., Du, Q., Fowler, J.E.: Fast SVD with random Hadamard projection for hyperspectral dimensionality reduction. IEEE Geosci. Remote Sensing Lett. 13(9), 1275–1279 (2016)
Bai, X., Xu, F., Zhou, L., Xing, Y., Bai, L., Zhou, J.: Nonlocal similarity based nonnegative Tucker decomposition for hyperspectral image denoising. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 11(3), 701–712 (2018)
Wang, Y., Lin, L., Zhao, Q., Yue, T., Meng, D., Leung, Y.: Compressive sensing of hyperspectral images via joint tensor tucker decomposition and weighted total variation regularization. IEEE Geosci. Remote Sens. Lett. 14(12), 2457–2461 (2017)
Karami, A., Yazdi, M., Mercier, G.: Compression of hyperspectral images using discerete wavelet transform and Tucker decomposition. IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 5(2), 444–450 (2012)
Karami, A, Yazdi, M., Asli, A.Z.: Hyperspectral image compression based on Tucker decomposition and discrete cosine transform. In: 2010 2nd International Conference on Image Processing Theory, Tools and Applications, pp. 122–125, Paris (2010)
Bentley, P.M., McDonnell, J.T.E.: Wavelet transforms: an introduction. Electron. Commun. Eng. J. 6(4), 175–186 (1994)
Chun-Lin, L.: A Tutorial of the Wavelet Transform. Taipei (2010)
Lerma, M.A.: Principal Components Analysis in 2D. Evanston (2017)
Jolliffe, I.T.: Principal Component Analysis, 2nd edn. Springer (2002)
Mudrová, M., Procházka, A.: Principal component analysis in image processing. In: Proceedings of International Conference Technical Computing, Prague (2005)
Jauregui, J.: Principal Component Analysis with Linear Algebra. Penn Arts and Sciences, Philadelphia (2012)
Richardson, M.: Principal component analysis, Special topic essay, M.Sc. Mathematical Modelling and Scientific Computing, University of Oxford (2009)
Golub, G.H., Van Loan, C.F.: The Singular Value Decomposition and Unitary Matrices. § 2.5.3 and 2.5.6 in Matrix Computations, 3rd edn., pp. 70–71 and 73. Johns Hopkins University Press, Baltimore (1996)
Jeyakumar, S., Sudha, S.: A unique method to decompose hyperspectral images with transformed pixel data. Int. J. Appl. Eng. Res., 10(17). ISSN 0973–4562 (2015)
Jeyakumar, S., Sudha, S.: Tensor decomposition based compression and analysis for 2D image data. Int. J. Appl. Eng. Res., 10(87). ISSN 0973–4562 (2015)
Foster, D.H., Amano, K., Nascimento, S.M.C., Foster, M.J.: Frequency of metamerism in natural scenes. J. Optical So. Am. A 23, 2359–2372 (2006)
Abdullatif, H.: You don’t know SVD (singular value decomposition), Towards Data Science, 21-Feb-2019. [Online]. Available: https://towardsdatascience.com/svd-8c2f72e264f
A gentle introduction to singular-value decomposition (SVD) for machine learning, Machine Learning Mastery, 19-Apr-2019. [Online]. Available: https://machinelearningmastery.com/singular-value-decomposition-for-machine-learning/
Fernández, J.A., Moreno, M.D.: A block size optimization algorithm for parallel image processing. In: 2014 International Conference on Computer Vision Theory and Applications (VISAPP), pp. 138–144, Lisbon (2014)
Raju, U.S.N., Kumar, K.S., Mehta, V., Sharma, R., Kuli, S.: Cluster based block processing for gigantic images: dimension and size. In: 2017 Fourth International Conference on Image Information Processing (ICIIP), pp. 1–5, Shimla (2017)
In.mathworks.com.: Distinct block processing- MATLAB and Simulink- MathWorks India. [online] Available at: https://in.mathworks.com/help/images/distinct-block-processing.html (2018)
Acknowledgments
The authors wish to acknowledge with thanks the help rendered by Thiru Ashok Kumar Das, IPS., ADGP (Technical Services), Tamil Nadu and Tmt N.Z Asiammal, IPS., DIG (Technical Services), Tamil Nadu Dr. C. V. Jayakumar, Principal, Sri Sairam Engg. College, Chennai, and Prof. A. R. Rajini, Head of the ECE Department, and all others in Sri Sairam Engg. College, Chennai, and Dr. N. Nithiyanandam, Professor, ECE Department, B. S. Abdur Rahman University, Chennai.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
S, J., S, S. Hybrid hyperspectral image compression technique for non-iterative factorized tensor decomposition and principal component analysis: application for NASA’s AVIRIS data. Comput Geosci 23, 969–979 (2019). https://doi.org/10.1007/s10596-019-09855-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-019-09855-2