Advertisement

Optimizing CNN-Based Hyperspectral Image Classification on FPGAs

  • Shuanglong LiuEmail author
  • Ringo S. W. Chu
  • Xiwei Wang
  • Wayne Luk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11444)

Abstract

Hyperspectral image (HSI) classification has been widely adopted in remote sensing imagery analysis applications which require high classification accuracy and real-time processing speed. Convolutional neural networks (CNNs)-based methods have been proven to achieve state-of-the-art accuracy in classifying HSIs. However, CNN models are often too computationally intensive to achieve real-time response due to the high dimensional nature of HSI, compared to traditional methods such as Support Vector Machines (SVMs). Besides, previous CNN models used in HSI are not specially designed for efficient implementation on embedded devices such as FPGAs. This paper proposes a novel CNN-based algorithm for HSI classification which takes into account hardware efficiency and thus is more hardware friendly compared to prior CNN models. An optimized and customized architecture which maps the proposed algorithm on FPGA is then proposed to support real-time on-board classification with low power consumption. Implementation results show that our proposed accelerator on a Xilinx Zynq 706 FPGA board achieves more than 70\(\times \) faster than an Intel 8-core Xeon CPU and 3\(\times \) faster than an NVIDIA GeForce 1080 GPU. Compared to previous SVM-based FPGA accelerators, we achieve comparable processing speed but provide a much higher classification accuracy.

Keywords

Hyperspectral image classification Deep learning Convolution neural network Field-programmable gate array 

Notes

Acknowledgement

The support of the UK EPSRC (EP/I012036/1, EP/L00058X/1, EP/L016796/1 and EP/N031768/1), the European Union Horizon 2020 Research and Innovation Programme under grant agreement number 671653, Altera, Corerain, Intel, Maxeler, SGIIT, and the China Scholarship Council is gratefully acknowledged.

References

  1. 1.
    Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/
  2. 2.
    Bioucas-Dias, J.M., et al.: Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci. Remote Sens. Mag. 1(2), 6–36 (2013)CrossRefGoogle Scholar
  3. 3.
    Chen, Y., Lin, Z., Zhao, X., Wang, G., Gu, Y.: Deep learning-based classification of hyperspectral data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7(6), 2094–2107 (2014)CrossRefGoogle Scholar
  4. 4.
    Grahn, H., Geladi, P.: Techniques and Applications of Hyperspectral Image Analysis. Wiley, Hoboken (2007)CrossRefGoogle Scholar
  5. 5.
    Lee, H., Kwon, H.: Going deeper with contextual CNN for hyperspectral image classification. IEEE Trans. Image Process. 26(10), 4843–4855 (2017)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Leng, J., et al.: Cube-CNN-SVM: a novel hyperspectral image classification method. In: 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1027–1034 (2016)Google Scholar
  7. 7.
    Liu, S., Bouganis, C.S.: Communication-aware MCMC method for big data applications on FPGAs. In: IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 9–16 (2017)Google Scholar
  8. 8.
    Liu, S., Mingas, G., Bouganis, C.S.: Parallel resampling for particle filters on FPGAs. In: IEEE International Conference on Field-Programmable Technology (FPT), pp. 191–198 (2014)Google Scholar
  9. 9.
    Liu, S., Mingas, G., Bouganis, C.S.: An exact MCMC accelerator under custom precision regimes. In: IEEE International Conference on Field Programmable Technology (FPT), pp. 120–127 (2015)Google Scholar
  10. 10.
    Liu, S., Mingas, G., Bouganis, C.S.: An unbiased mcmc FPGA-based accelerator in the land of custom precision arithmetic. IEEE Trans. Comput. 66(5), 745–758 (2017)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Liu, S., et al.: Optimizing CNN-based segmentation with deeply customized convolutional and deconvolutional architectures on FPGA. ACM Trans. Reconfigurable Technol. Syst. (TRETS) 11, 19 (2018)Google Scholar
  12. 12.
    Lopez, S., et al.: The promise of reconfigurable computing for hyperspectral imaging onboard systems: a review and trends. Proc. IEEE 101(3), 698–722 (2013)CrossRefGoogle Scholar
  13. 13.
    Luo, Y., et al.: HSI-CNN: a novel convolution neural network for hyperspectral image. In: 2018 International Conference on Audio, Language and Image Processing (ICALIP), pp. 464–469. IEEE (2018)Google Scholar
  14. 14.
    Martin, M.E., et al.: Development of an advanced hyperspectral imaging (HSI) system with applications for cancer detection. Ann. Biomed. Eng. 34(6), 1061–1068 (2006)CrossRefGoogle Scholar
  15. 15.
    Martin, M.E., Wabuyele, M.B., et al.: Development of an advanced hyperspectral imaging (HSI) system with applications for cancer detection. Ann. Biomed. Eng. 34(6), 1061–1068 (2006).  https://doi.org/10.1007/s10439-006-9121-9CrossRefGoogle Scholar
  16. 16.
    Salem, F., et al.: Hyperspectral image analysis for oil spill detection. In: Summaries of NASA/JPL Airborne Earth Science Workshop, Pasadena, CA, pp. 5–9 (2001)Google Scholar
  17. 17.
    Santara, A., et al.: BASS net: band-adaptive spectral-spatial feature learning neural network for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 55(9), 5293–5301 (2017)CrossRefGoogle Scholar
  18. 18.
    Tajiri, K., Maruyama, T.: FPGA acceleration of a supervised learning method for hyperspectral image classification. In: 2018 International Conference on Field-Programmable Technology (FPT). IEEE (2018)Google Scholar
  19. 19.
    Wang, S., Niu, X., Ma, N., Luk, W., Leong, P., Peng, Y.: A scalable dataflow accelerator for real time onboard hyperspectral image classification. In: Bonato, V., Bouganis, C., Gorgon, M. (eds.) ARC 2016. LNCS, vol. 9625, pp. 105–116. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-30481-6_9CrossRefGoogle Scholar
  20. 20.
    Zhang, L., Zhang, L., Du, B.: Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE Geosci. Remote Sens. Mag. 4(2), 22–40 (2016)CrossRefGoogle Scholar
  21. 21.
    Zhao, R., Niu, X., Wu, Y., Luk, W., Liu, Q.: Optimizing CNN-based object detection algorithms on embedded FPGA platforms. In: Wong, S., Beck, A.C., Bertels, K., Carro, L. (eds.) ARC 2017. LNCS, vol. 10216, pp. 255–267. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-56258-2_22CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of ComputingImperial College LondonLondonUK
  2. 2.Department of Computer ScienceUniversity College LondonLondonUK
  3. 3.China Academy of Space TechnologyBeijingChina

Personalised recommendations