access icon openaccess Compressed spatial–spectral feature representation for hyperspectral ground classification

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 20/02/2019, Accepted 02/05/2019, Published 13/08/2019

The difficulty of classification tasks in hyperspectral imagery (HSI) strongly depends on the representation of spectral or spatial information. Vast amounts of approaches have been proposed to deal with spectral and spatial feature extraction, respectively. However, most of the methods neglect the inherent relationships between them. Inspired by the extreme learning machine (ELM) theory, the authors propose a new fusion-ELM framework for multiple sources representation learning and fusion. The resultant features are utilised to deal with HSI classification. With the multiple network channels and aggregation layers, the presented scheme could achieve spatial and spectral feature representations of inputs, respectively, and obtain optimal joint feature. Experimental results show that their fusion-model leads to decent improvements in classification accuracy over spectral-only, spatial–spectral-joint model and deep learning framework on two hyperspectral benchmarks.

Inspec keywords: pattern classification; geophysical image processing; image classification; hyperspectral imaging; feature extraction; learning (artificial intelligence); image representation

Other keywords: classification accuracy; methods neglect; classification tasks; spatial information; spatial–spectral-joint model; HSI classification; spatial feature extraction; optimal joint feature; spectral feature extraction; extreme learning machine; compressed spatial–spectral feature representation; deep learning framework; multiple network channels; spectral information; hyperspectral imagery; hyperspectral ground classification; inherent relationships; multiple sources representation learning; fusion-ELM framework; hyperspectral benchmarks; fusion-model; resultant features

Subjects: Optical, image and video signal processing; Computer vision and image processing techniques; Other topics in statistics; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Knowledge engineering techniques; Geophysical techniques and equipment

References

    1. 1)
      • 13. Tang, J., Deng, C., Huang, G.-B., et al: ‘Extreme learning machine for multilayer perceptron’, IEEE Trans. Neural Netw. Learn. Syst., 2016, 27, pp. 809–821.
    2. 2)
      • 7. Green, A.A., Berman, M., Switzer, P., et al: ‘A transformation for ordering multispectral data in terms of image quality with implications for noise removal’, IEEE Trans. Geosci. Remote Sens., 1988, 26, pp. 65–74.
    3. 3)
      • 17. Li, W., Chen, C., Su, H., et al: ‘Local binary patterns and extreme learning machine for hyperspectral imagery classification’, IEEE Trans. Geosci. Remote Sens., 2015, 53, pp. 1–13.
    4. 4)
      • 11. 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, pp. 6232–6251.
    5. 5)
      • 10. Chen, Y., Lin, J., Zhao, X., et al: ‘Deep learning-based classification of hyperspectral data’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, 7, pp. 2094–2107.
    6. 6)
      • 12. Li, J., Brozzone, L., Liu, S., et al: ‘Deep feature representation for hyperspectral image classification’. IEEE Geoscience and Remote Sensing Symp., Milan, Italy, 2015, pp. 4951–4954.
    7. 7)
      • 4. Malthus, T., Mumby, P.: ‘Remote sensing of the coastal zone: an overview and priorities for future research’, Int. J. Remote Sens., 2003, 24, pp. 2805–2815.
    8. 8)
      • 14. Huang, G., Zhu, Q.Y., Siew, C.K., et al: ‘Extreme learning machine: theory and applications’, Neurocomputing, 2006, 70, pp. 489–501.
    9. 9)
      • 9. Tarabalka, Y.: ‘Classification of hyperspectral data using spectral–spatial approaches’, Numerical and experimental investigation of plasticity (slip) evolution in notched single crystal superalloy specimens, 2010.
    10. 10)
      • 15. Kasun, L.L.C., Yang, Y., Huang, G.B., et al: ‘Dimension reduction with extreme learning machine’, IEEE Trans. Image Process., 2016, 25, pp. 3906–3918.
    11. 11)
      • 16. Amir, B., Teboulle, M.: ‘A fast iterative shrinkage-thresholding algorithm for linear inverse problems’, SIAM J. Imaging Sci., 2009, 2, pp. 183–202.
    12. 12)
      • 8. Fauvel, M., Chanussot, J., Benediktsson, J.A., 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.
    13. 13)
      • 3. Meer, F.V.D.: ‘Analysis of spectral absorption features in hyperspectral imagery’, Int. J. Appl. Earth Obs. Geoinf., 2004, 5, pp. 55–68.
    14. 14)
      • 1. Chang, C.I: ‘Hyperspectral data exploitation: theory and applications’ (Wiley-Interscience, Hoboken, NJ, USA, 2007).
    15. 15)
      • 6. Bruzzone, L., Persello, C.: ‘A novel approach to the selection of spatially invariant features for the classification of hyperspectral images with improved generalization capability’, IEEE Trans. Geosci. Remote Sens., 2009, 47, pp. 3180–3191.
    16. 16)
      • 2. Lacar, F.M., Lewis, M.M., Grierson, I.T.: ‘Use of hyperspectral imagery for mapping grape varieties in the Barossa Valley, South Australia’. IEEE Int. Geoscience and Remote Sensing Symp., Sydney, Australia, 2001, vol. 6, pp. 2875–2877.
    17. 17)
      • 5. Bioucas-Dias, J.M., Plaza, A., Camps-Valls, G., et al: ‘Hyperspectral remote sensing data analysis and future challenges’, IEEE Geosci. Remote Sens. Mag., 2013, 1, pp. 6–36.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2019.0320
Loading

Related content

content/journals/10.1049/joe.2019.0320
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading