Advertisement

Stacked Autoencoder Based Feature Extraction and Superpixel Generation for Multifrequency PolSAR Image Classification

  • Tushar GadhiyaEmail author
  • Sumanth Tangirala
  • Anil K. Roy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11942)

Abstract

In this paper we are proposing classification algorithm for multifrequency Polarimetric Synthetic Aperture Radar (PolSAR) image. Using PolSAR decomposition algorithms 33 features are extracted from each frequency band of the given image. Then, a two-layer autoencoder is used to reduce the dimensionality of input feature vector while retaining useful features of the input. This reduced dimensional feature vector is then applied to generate superpixels using simple linear iterative clustering (SLIC) algorithm. Next, a robust feature representation is constructed using both pixel as well as superpixel information. Finally, softmax classifier is used to perform classification task. The advantage of using superpixels is that it preserves spatial information between neighboring PolSAR pixels and therefore minimizes the effect of speckle noise during classification. Experiments have been conducted on Flevoland dataset and the proposed method was found to be superior to other methods available in the literature.

Keywords

Polarimetric Synthetic Aperture Radar (PolSAR) Multifrequency PolSAR image classification Autoencoder Superpixels Simple linear iterative clustering (SLIC) Optimized Wishart Network (OWN) 

References

  1. 1.
    Chen, K.S., Huang, W.P., Tsay, D.H., Amar, F.: Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network. IEEE Trans. Geosci. Remote Sens. 34, 814–820 (1996)CrossRefGoogle Scholar
  2. 2.
    De, S., Ratha, D., Ratha, D., Bhattacharya, A., Chaudhuri, S.: Tensorization of multifrequency PolSAR data for classification using an autoencoder network. IEEE Geosci. Remote Sens. Lett. 15, 542–546 (2018)CrossRefGoogle Scholar
  3. 3.
    Gadhiya, T., Roy, A.K.: Optimized wishart network for an efficient classification of multifrequency PolSAR data. IEEE Geosci. Remote Sens. Lett. 15, 1720–1724 (2018)CrossRefGoogle Scholar
  4. 4.
    Hou, B., Kou, H., Jiao, L.: Classification of polarimetric SAR images using multilayer autoencoders and superpixels. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9, 3072–3081 (2016)CrossRefGoogle Scholar
  5. 5.
    Guo, Y., Jiao, L., Wang, S., Wang, S., Liu, F., Hua, W.: Fuzzy superpixels for polarimetric SAR images classification. IEEE Trans. Fuzzy Syst. 26, 2846–2860 (2018)CrossRefGoogle Scholar
  6. 6.
    Hou, B., Yang, C., Ren, B., Jiao, L.: Decomposition-feature-iterative-clustering-based superpixel segmentation for PolSAR image classification. IEEE Geosci. Remote Sens. Lett. 15, 1239–1243 (2018)CrossRefGoogle Scholar
  7. 7.
    Hu, Y., Fan, J., Wang, J.: Classification of PolSAR images based on adaptive nonlocal stacked sparse autoencoder. IEEE Geosci. Remote Sens. Lett. 15, 1050–1054 (2018)CrossRefGoogle Scholar
  8. 8.
    Freeman, A., Durden, S.L.: A three-component scattering model for polarimetric SAR data. IEEE Trans. Geosci. Remote Sens. 36, 963–973 (1998)CrossRefGoogle Scholar
  9. 9.
    Huynen, J.R.: Phenomenological theory of radar targets. Electronmagnetic Scattering (1970)Google Scholar
  10. 10.
    Cloude, S.R., Pottier, E.: An entropy based classification scheme for land applications of polarimetric SAR. IEEE Trans. Geosci. Remote Sens. 35, 68–78 (1997)CrossRefGoogle Scholar
  11. 11.
    Krogager, E.: New decomposition of the radar target scattering matrix. Electron. Lett. 26, 1525–1527 (1990)CrossRefGoogle Scholar
  12. 12.
    Yamaguchi, Y., Moriyama, T., Ishido, M., Yamada, H.: Four-component scattering model for polarimetric SAR image decomposition. IEEE Trans. Geosci. Remote Sens. 43, 1699–1706 (2005)CrossRefGoogle Scholar
  13. 13.
    Zhou, Y., Wang, H., Xu, F., Jin, Y.: Polarimetric SAR image classification using deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 13, 1935–1939 (2016)CrossRefGoogle Scholar
  14. 14.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012)CrossRefGoogle Scholar
  15. 15.
    Dataset: AIRSAR, NASA 1991. Retrieved from ASF DAAC on 7 December 2018Google Scholar
  16. 16.
    Yang, F., Gao, W., Xu, B., Yang, J.: Multi-frequency polarimetric SAR classification based on riemannian manifold and simultaneous sparse representation. Remote Sens. 7(7), 8469–8488 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Tushar Gadhiya
    • 1
    Email author
  • Sumanth Tangirala
    • 1
  • Anil K. Roy
    • 1
  1. 1.Dhirubhai Ambani Institute of Information and Communication TechnologyGandhinagarIndia

Personalised recommendations