access icon openaccess Spectral–spatial classification of hyperspectral remote sensing image based on capsule network

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 21/02/2019, Accepted 07/05/2019, Published 11/07/2019

Hyperspectral image (HSI) classification is a hot topic in remote sensing community; many researchers have made a great deal of effort in this domain. Recently, deep learning-based manner paves a new way to better classification accuracy. However, the flow of information between layers and layers (e.g. max-pooling) in traditional deep architecture turns out to be ineffective. In this study, a novel spectral–spatial classification framework for HSI based on Capsule Network (CapsNet) and dynamic routing algorithm is introduced. The proposed architecture is composed of a hybrid of 1D and 2D convolutional layers and two capsule layers for better and effective mining and combining features. Consequently, experiments on two popular dataset indicate that CapsNet-based framework outperforms traditional CNN-based counterparts. Moreover, this study reveals great potential for CapsNet model in the field of HSI classification.

Inspec keywords: feature extraction; convolutional neural nets; geophysical image processing; image classification; hyperspectral imaging; remote sensing; learning (artificial intelligence)

Other keywords: dynamic routing algorithm; HSI classification; capsule layers; CNN-based counterparts; spectral–spatial classification framework; deep architecture; CapsNet-based framework; 1D convolutional layers; hyperspectral image classification; hyperspectral remote sensing image; deep learning-based manner; capsule network; 2D convolutional layers

Subjects: Optical, image and video signal processing; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Geophysical techniques and equipment; Geography and cartography computing; Computer vision and image processing techniques; Neural computing techniques

References

    1. 1)
      • 3. Chang, C.-I.: ‘Hyperspectral data exploitation: theory and applications’ (Wiley–Interscience, New York, NY, USA, 2007).
    2. 2)
      • 7. Benediktsson, J.A., Palmason, J.A., Sveinsson, J.R.: ‘Classification of hyperspectral data from urban areas based on extended morphological profiles’, IEEE Trans. Geosci. Remote Sens., 2005, 43, (3), pp. 480–491.
    3. 3)
      • 12. Chen, Y., Zhao, X., Jia, X.: ‘Spectral-spatial classification of hyperspectral data based on deep belief network’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2015, 8, (6), pp. 2381–2392.
    4. 4)
      • 11. Chen, Y., Lin, Z., Zhao, X., et al: ‘Deep learning-based classification of hyperspectral data’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, 7, (6), pp. 2094–2107.
    5. 5)
      • 10. He, Z., Wang, Q., Shen, Y., et al: ‘Kernel sparse multitask learning for hyperspectral image classification with empirical mode decomposition and morphological wavelet-based features’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (8), pp. 5150–5163.
    6. 6)
      • 19. Sabour, S., Frosst, N., Hinton, G.E.: ‘Dynamic routing between capsules’. Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 3857–3867.
    7. 7)
      • 14. Romero, A., Gatta, C., Camps-Valls, G.: ‘Unsupervised deep feature extraction for remote sensing image classification’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (3), pp. 1349–1362.
    8. 8)
      • 6. Camps-Valls, G., Gomez-Chova, L., Munoz-Mari, J., et al: ‘Composite kernels for hyperspectral image classification’, IEEE Geosci. Remote Sens. Lett., 2006, 3, (1), pp. 93–97.
    9. 9)
      • 16. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Advances in Neural Information Processing Systems, Lake Tahoe, CA, USA, 2012, pp. 1097–1105.
    10. 10)
      • 9. Fauvel, M., Benediktsson, J.A., Chanussot, J., et al: ‘Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles’, IEEE Trans. Geosci. Remote Sens., 2008, 46, (11), pp. 3804–3814.
    11. 11)
      • 18. Glorot, X., Bengio, Y.: ‘Understanding the difficulty of training deep feedforward neural networks’. AISTATS, Sardinia, Italy, 2010.
    12. 12)
      • 8. Quesada-Barriuso, P., Argüello, F., Heras, D.B.: ‘Spectral-spatial classification of hyperspectral images using wavelets and extended morphological profiles’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, 7, (4), pp. 1177–1185.
    13. 13)
      • 2. Zheng, W., Hu, J., Zhang, W., et al: ‘Potential of geosynchronous SAR interferometric measurements in estimating three-dimensional surface displacements’, Sci. China, Inf. Sci., 2017, 60, p. 060304.
    14. 14)
      • 13. Chen, Y., Jiang, H., Li, C., et al: ‘Deep feature extraction and classification of hyperspectral images based on convolutional neural networks’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (10), pp. 6232–6251.
    15. 15)
      • 4. Landgrebe, D.: ‘Hyperspectral image data analysis’, IEEE Signal Process. Mag., 2002, 19, (1), pp. 17–28.
    16. 16)
      • 15. LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, (7553), pp. 436–444.
    17. 17)
      • 17. Ioffe, S., Szegedy, C.: ‘Batch normalization: accelerating deep network training by reducing internal covariate shift’. International Conference on Machine Learning, Lille, France, 2015.
    18. 18)
      • 1. Guarnieri, A.M., Rocca, F.: ‘Options for continuous radar earth observations’, Sci. China, Inf. Sci., 2017, 60, p. 060301.
    19. 19)
      • 5. Jia, X., Kuo, B.-C., Crawford, M.M.: ‘Feature mining for hyperspectral image classification’, Proc. IEEE, 2013, 101, (3), pp. 676–697.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2019.0526
Loading

Related content

content/journals/10.1049/joe.2019.0526
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading