Skip to main content

Adaptation of an Iterative PCA to a Manycore Architecture for Hyperspectral Image Processing

Abstract

This paper presents a study of the adaptation of a Non-Linear Iterative Partial Least Squares (NIPALS) algorithm applied to Hyperspectral Imaging to a Massively Parallel Processor Array manycore architecture, which assembles 256 cores distributed over 16 clusters. This work aims at optimizing the internal communications of the platform to achieve real-time processing of large data volumes with limited computational resources and memory bandwidth. As hyperspectral images are composed of extensive volumes of spectral information, real-time requirements, which are upper-bounded by the image capture rate of the hyperspectral sensor, are a challenging objective. To address this issue, the image size is usually reduced prior to the processing phase, which is itself a computationally intensive task. Consequently, this paper proposes an analysis of the intrinsic parallelism and the data dependency within the NIPALS algorithm and its subsequent implementation on a manycore architecture. Furthermore, this implementation has been validated against three hyperspectral images extracted from both remote sensing and medical datasets. As a result, an average speedup of 17× has been achieved when compared to the sequential version. Finally, this approach has been compared with other state-of-the-art implementations, outperforming them in terms of performance.

This is a preview of subscription content, access via your institution.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6

Notes

  1. http://aviris.jpl.nasa.gov

  2. http://speclab.cr.usgs.gov/wtc

References

  1. Chang, C. I. (2003). Hyperspectral imaging: Techniques for spectral detection and classification (Vol. 1). Baltimore: Springer Science & Business Media, University of Maryland.

    Book  Google Scholar 

  2. Gomez, C., Rossel, R. A. V., & McBratney, A. B. (2008). Soil organic carbon prediction by hyperspectral remote sensing and field Vis-NIR spectroscopy: An Australian case study. Geoderme, 146(3), 403–411.

    Article  Google Scholar 

  3. Edelman, G. J., Gaston, E., Van Leeuwen, T. G., Cullen, P. J., & Aalders, M. C. G. (2012). Hyperspectral imaging for non-contact analysis of forensics traces. Forensic Science International, 223(1), 28–39.

    Article  Google Scholar 

  4. Fabelo, H., Ortega, S., Lazcano, R., Madroñal, D., M. Callicó, G., Juárez, E., Salvador, R., Bulters, D., Bulstrode, H., Szolna, A., Piñeiro, J., Sosa, C., J. O’Shanahan, A., Bisshopp, S., Hernández, M., Morera, J., Ravi, D., Kiran, B., Vega, A., Báez-Quevedo, A., Yang, G. Z., Stanciulescu, B., & Sarmiento, R. (2018). An Intraoperative Visualization System Using Hyperspectral Imaging to Aid in Brain Tumor Delineation. Sensors, 18(2), 430. https://doi.org/10.3390/s18020430.

    Article  Google Scholar 

  5. Castro, M., Dupros, F., Francesquini, E., Méhautk, J. F., & Navaux, P. O. A. (2014) Energy efficient seismic wave propagation simulation on a low-power manycore processor. 26th International Symposium on Computer Architecture and High Performance Computing, p. 8.

  6. Francesquini, E., Castro, M., Penna, P. H., Dupros, F., Freitas, H. C., Navaux, P. O. A., & Méhaut, J. F. (2015). On the energy efficiency and performance of irregular application executions on multicore, NUMA and manycore platforms. Journal of Parallel and Distributed Computing, 76, 32–48.

    Article  Google Scholar 

  7. Madroñal, D., et al. (2017) Energy consumption characterization of a Massively Parallel Processor Array (MPPA) platform running a hyperspectral SVM classifier. Design and Architectures for Signal and Image Processing (DASIP), 2017 Conference on, IEEE.

  8. Rodarmel, C., & Shan, J. (2002). Pincipal component analysis for hyperspectral image classification. Surveying and Land Information Science, 62(2), 115.

    Google Scholar 

  9. Jolliffe, I. T. (2002). Principal component analysis. NY: Springer.

    MATH  Google Scholar 

  10. Lazcano, R., et al. (2016) Parallelism exploitation of a dimensionality reduction algorithm applied to hyperspectral images. Design and Architectures for Signal and Image Processing (DASIP), 2016 Conference on.

  11. Lazcano, R., et al. (2017) Parallel implementation of an iterative PCA algorithm for hyperspectral images on a manycore platform. Design and Architectures for Signal and Image Processing (DASIP), 2017 Conference on, IEEE.

  12. Andrecut, M. (2009). Parallel GPU implementation of iterative PCA algorithms. Journal of Computational Biology, 16(11), 1593–1599.

    MathSciNet  Article  Google Scholar 

  13. Huang, K., Li, S., Kang, X., & Fang, L. (2016). Spectral-spatial hyperspectral image classification based on KNN. Sensing and Imaging, 17(1), 1–13.

    Article  Google Scholar 

  14. de Dinechi, B. D., et al. (2013) A clustered manycore processor architecture for embedded and accelerated applications. High Performance Extreme Computing Conference (HPEC), pp. 1–6.

  15. de Dinechi, B. D., & Graillat, A. (2017) Network-on-chip service guarantees on the Kalray MPPA-256 Bostan processor. Proceedings of the 2nd international workshop on advanced interconnect solutions and technologies for emerging computing systems, pp. 35–40.

  16. Lazcano, R., Madroñal, D., Salvador, R., Desnos, K., Pelcat, M., Guerra, R., Fabelo, H., Ortega, S., Lopez, S., Callico, G. M., Juarez, E., & Sanz, C. (2017). Porting a PCA-based hyperspectral image dimensionality reduction algorithm for brain cancer detection on a manycore architecture. Journal of Systems Architecture, 77, 101–111.

    Article  Google Scholar 

  17. Fabelo, H., et al. (2016) A novel use of hyperspectral images for human brain canscer detection using in-vivo samples. Proceedings of the 9th international joint conference on biomedical engineering systems and technologies, pp. 311–320.

  18. Fernandez, D., Gonzalez, C., Mozos, D., & Lopez, S. (2016) FPGA implementation of the principal component analysis algorithm for dimensionality reduction of hyperspectral images. Journal of Real-Time Image Processing, 1–12. https://doi.org/10.1007/s11554-016-0650-7.

  19. Sanchez, S., et al. (2015). Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs. Journal of Real-Time Image Processing, 10(3), 469–483.

    MathSciNet  Article  Google Scholar 

  20. Vapnik, V. (2013). The nature of statistical learning theory. New York: Springer Science & Business Media.

    MATH  Google Scholar 

  21. Madroñal, D., et al. (2017) Implementation of a spatial-spectral classification algorithm using medical hyperspectral images. XXXII Design of Circuits and Integrated Systems Conference (DCIS).

Download references

Acknowledgements

This research has been funded by the EU FET HELICoiD (HypErspectraL Imaging Cancer Detection) project (FP7-ICT-2013.9.2 (FET Open) 618080).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to R. Lazcano.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lazcano, R., Madroñal, D., Fabelo, H. et al. Adaptation of an Iterative PCA to a Manycore Architecture for Hyperspectral Image Processing. J Sign Process Syst 91, 759–771 (2019). https://doi.org/10.1007/s11265-018-1380-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-018-1380-9

Keywords

  • NIPALS-PCA
  • Hyperspectral imaging
  • Massively parallel processing
  • Real-time processing
  • Parallel programming