Abstract
One of the most important tasks in hyperspectral imaging is the estimation of the number of endmembers in a scene, where the endmembers are the most spectrally pure components. The high dimensionality of hyperspectral data makes this calculation computationally expensive. In this paper, we present several new real-time implementations of the well-known Harsanyi–Farrand–Chang method for virtual dimensionality estimation. The proposed solutions exploit multi-core processors and graphic processing units for achieving real-time performance of this algorithm, together with better performance than other works in the literature. Our experimental results are obtained using both synthetic and real images. The obtained processing times show that the proposed implementations outperform other hardware-based solutions.
Similar content being viewed by others
References
Lillesand, T.M., Kiefer, R.W., Chipman, J.W.: Remote Sensing and Image Interpretation, 5th edn. Wiley, Hoboken (2004)
Keshava, N., Mustard, J.: Spectral unmixing. IEEE Signal Process. Mag. 19(1), 44–57 (2002)
Scharf, L.L.: Statistical Signal Processing, Detection Estimation and Time Series Analysis. Addison-Wesley, Boston (1991). Reading
Chang, C.-I., Wang, S.: Constrained band selection for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 44(6), 1575–1585 (2006)
Nascimento, J.M.P., Bioucas-Dias, J.M.: Hyperspectral subspace identification. IEEE Trans. Geosci. Remote Sens. 46(8), 1445–2435 (2008)
Chang, C.-I.: Hyperspectral Imaging: Techniques for Spectral Detection and Classification. Kluwer/Plenum Academic Publishers, New York (2003)
Harsanyi, J.C., Farrand, W., Chang, C.-I.: Detection of subpixel spectral signatures in hyperspectral image sequences, In: Proceedings of the American Society for Photogrammetry and Remote Sensing, pp. 236–247. Reno (1994)
Patel, A., Kosko, B.: Optimal noise benefits in Neyman-pearson signal detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3889–3892. Las Vegas (2008)
Lopez, S., Vladimirova, T., Gonzales, C., Resano, J., Mozos, D., Plaza, A.: The promise of reconfigurable computing for hyperspectral imaging onboard systems: a review and trends. Proc. IEEE 101(3), 698–722 (2013)
Torti, E., Acquistapace, M., Danese, G., Leporati, F., Plaza, A.: Real-time identification of hyperspectral subspaces. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 7(6), 2680–2687 (2014)
Plaza, A., Valencia, D., Plaza, J., Chang, C.-I.: Parallel implementation of endmember extraction algorithms for hyperspectral data. IEEE Geosci. Remote Sens. Lett. 3(3), 334–338 (2006)
Barberis, A., Danese, G., Leporati, F., Plaza, A., Torti, E.: Real-time implementation of the vertex component analysis algorithm on GPUs. IEEE Geosci. Remote Sens. Lett. 10(2), 251–255 (2013)
Wu, X., Huang, B., Wang, L., Zhang, J.: GPU-based parallel design of the hyperspectral signal subspace identification by minimum error (HySime). IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 9(9), 4400–4406 (2016)
Torti, E., Danese, G., Leporati, F., Plaza, A.: A hybrid CPU-GPU real-time hyperspectral unmixing chain. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 10(2) 945–951 (2016)
Gonzales, C., Lopez, S., Mozos, D., et al.: A novel FPGA-based architecture for the estimation of the virtual dimensionality in remotely sensed hyperspectral images. J. Real-Time Imag. Proc. 1–12 (2015). doi:10.1007/s11554-014-0482-2
Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical recipes in C: the art of scientific computing, 2nd edn. Cambridge University Press, Cambridge (2007)
http://docs.nvidia.com/cuda/cublas/. Last access: Jan 2017
http://www.numpy.org/. Last access: Jan 2017
https://documen.tician.de/pycuda/. Last access: Jan 2017
https://pypi.python.org/pypi/reikna. Last access: Jan 2017
Sanchez, S., Plaza, A.: Fast determination of the number of endmembers for real-time hyperspectral unmixing on GPUs. J. Real-Time Image Process. 9(3), 397–405 (2014)
Sanchez, S., Ramalho, R., Sousa, L., Plaza, A.: Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs. J. Real-Time Image Process. 10(3), 469–483 (2015)
Acknowledgements
The authors gratefully thank NVIDIA Corporation for the donation of the GPU Tesla K40 used for this research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Torti, E., Fontanella, A. & Plaza, A. Parallel real-time virtual dimensionality estimation for hyperspectral images. J Real-Time Image Proc 14, 753–761 (2018). https://doi.org/10.1007/s11554-017-0703-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-017-0703-6