[go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Regression layer-based convolution neural network for synthetic aperture radar images: de-noising and super-resolution

  • Original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Nowadays, the increasing demands for synthetic aperture radar images are of great importance in both marine and terrestrial applications, due to their availability day and night and in all-weather conditions. Moreover, synthetic aperture radar images are characterized by much more important information than that introduced by optical images. The single image super-resolution is considered a challenging process, especially for synthetic aperture radar images which are usually degraded by high level of speckle noise. Due to the success of convolutional neural networks in many super-resolution optical image applications, a proposed regression layer-based framework is exploited for synthetic aperture radar image enhancement. The proposed regression layer is used during the learning phase to drive the back-propagation error based on the structure similarity index loss function. The structure similarity index is a quality assessment based on comparing the structural information. Consequently, the proposed loss function compares the statistical values of the network output images with that of the optimal target images. Moreover, the proposed framework introduces the concept of adjusting the proportions of the structure similarity index components (luminance, contrast and structure) according to their impacts, by changing their exponents. In addition to that, the proposed layer modifies the statistical properties of the target images, in such a way that drives learning to enhance the resulting image structure and eliminate the speckle noise. This layer is useful for noise reduction and super-resolution applications, especially for those dedicated to synthetic aperture radar images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Chen, S.-W., Wang, X.-S., Sato, M.: Urban damage level mapping based on scattering mechanism investigation using fully polarimetric SAR data for the 3.11 East Japan Earthquake. IEEE Trans. Geosci. Remote Sens. 54(12), 6919–6929 (2016). https://doi.org/10.1109/TGRS.2016.2588325

    Article  Google Scholar 

  2. Chen, S.-W., Wang, X.-S., Xiao, S.-P.: Urban damage level mapping based on co-polarization coherence pattern using multitemporal polarimetric SAR data. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 11(8), 2657–2667 (2018). https://doi.org/10.1109/JSTARS.2018.2818939

    Article  Google Scholar 

  3. Chen, S.-W., Tao, C.-S.: PolSAR image classification using polarimetric-feature-driven deep convolutional neural network. IEEE Geosci. Remote Sens. Lett. 15(4), 627–631 (2018). https://doi.org/10.1109/LGRS.2018.2799877

    Article  Google Scholar 

  4. Massinas, B.A., Doulamis, A., Doulamis, N., Paradissis, D.: Ensemble classifiers in optimal estimation for ionospheric disturbances behavior on spaceborne interferometric SAR systems. Proceedings SPACE Conf., AIAA, Long Beach, California, USA 5353, 1–11 (2016). https://doi.org/10.2514/6.2016-5353

    Article  Google Scholar 

  5. Penna, P.A., Mascarenhas, N.D.: SAR speckle nonlocal filtering with statistical modeling of haar wavelet coefficients and stochastic distances. IEEE Trans. Geosci. Remote Sens. 57(9), 7194–7208 (2019). https://doi.org/10.1109/TGRS.2019.2912153

    Article  Google Scholar 

  6. Yahia, M., Ali, T., Mortula, M.M., Abdelfattah, R., El Mahdy, S., Arampola, N.S.: Enhancement of SAR speckle denoising using the improved iterative filter. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 13, 859–871 (2020). https://doi.org/10.1109/JSTARS.2020.2973920

    Article  Google Scholar 

  7. Yang, Y., Ding, Z., Liu, J., Gao, Q., Yuan, X., and Lu, X.: An adaptive SAR image speckle reduction algorithm based on wavelet transform and diffusion equations for marine scenes. Proceedings of the International Geoscience and Remote Sensing Symposium, IEEE, Fort Worth, TX, USA, 2017, pp. 3082–3085. https://doi.org/10.1109/IGARSS.2017.8127650

  8. Li, H.-C., Hong, W., Wu, Y.-R., Fan, P.-Z.: Bayesian wavelet shrinkage with heterogeneity-adaptive threshold for SAR image despeckling based on generalized gamma distribution. IEEE Trans. Geosci. Remote Sens. 51(4), 2388–2402 (2013). https://doi.org/10.1109/TGRS.2012.2211366

    Article  Google Scholar 

  9. Abergel, R., Denis, L., Tupin, F., Ladjal, S., Deledalle, C-A., and Almansa, A.: Resolution-preserving speckle reduction of SAR images: the benefits of speckle decorrelation and targets extraction. Proceedings of the International Symposium on Geoscience and Remote Sensing (IGARSS), IEEE, Japan, 2019, pp. 608–611. https://doi.org/10.1109/IGARSS.2019.8900036

  10. Rohith, G., Kumar, L.S.: Paradigm shifts in super-resolution techniques for remote sensing applications. Vis. Comput. 37(7), 1965–2008 (2021). https://doi.org/10.1007/s00371-020-01957-8

    Article  Google Scholar 

  11. Mikaeli, E., Aghagolzadeh, A., Azghani, M.: Single-image super-resolution via patch-based and group-based local smoothness modeling. Vis. Comput. 36(8), 1573–1589 (2020). https://doi.org/10.1007/s00371-019-01756-w

    Article  Google Scholar 

  12. Timofte, R., De Smet, V., and Van Gool, L.: A+: Adjusted anchored neighborhood regression for fast super-resolution. Proceedings of the 12th Asian Conference on Computer Vision (ACCV), Springer, Singapore, 2014, pp. 111–126. https://doi.org/10.1007/978-3-319-16817-3_8

  13. Yang, C.-Y., and Yang, M.-H.: fast direct super-resolution by simple functions. Proceedings of the International Conference on Computer Vision, IEEE, Sydney, NSW, Australia, 2013, pp. 561–568. https://doi.org/10.1109/ICCV.2013.75

  14. Zhou, D., Liu, Y., Li, X., Zhang, C.: Single-image super-resolution based on local biquadratic spline with edge constraints and adaptive optimization in transform domain. Vis. Comput. (2020). https://doi.org/10.1007/s00371-020-02007-z

    Article  Google Scholar 

  15. Zhang, Y., Liu, J., Yang, W., Guo, Z.: Image super-resolution based on structure-modulated sparse representation. IEEE Trans. Image Process. 24(9), 2797–2810 (2015). https://doi.org/10.1109/TIP.2015.2431435

    Article  MathSciNet  MATH  Google Scholar 

  16. Ahmed, A., Kun, S., Memon, R.A., Ahmed, J., Tefera, G.: Convolutional sparse coding using wavelets for single image super-resolution. IEEE Access 7, 121350–121359 (2019). https://doi.org/10.1109/ACCESS.2019.2936455

    Article  Google Scholar 

  17. Dong, C., Loy, C. C., He, K., and Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV Lecture Notes in Computer Science, Vol. 8692, Springer, Cham., 2014, pp. 184–199. https://doi.org/10.1007/978-3-319-10593-2_13

  18. Mei, S., Jiang, R., Li, X., Du, Q.: Spatial and spectral joint super-resolution using convolutional neural network. IEEE Trans. Geosci. Remote Sens. 58(7), 4590–4603 (2020). https://doi.org/10.1109/TGRS.2020.2964288

    Article  Google Scholar 

  19. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., and Fu, Y.: Residual dense network for image super-resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Salt Lake City, UT, USA, 2018, pp. 2472–2481. https://doi.org/10.1109/CVPR.2018.00262

  20. Tai, Y., Yang, J., and Liu, X.: Image super-resolution via deep recursive residual network. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Honolulu, HI, USA, 2017, pp. 2790–2798. https://doi.org/10.1109/CVPR.2017.298

  21. Johnson, J., Alahi, A., and Fei-Fei, L.: perceptual losses for real-time style transfer and super-resolution. In: Leibe B., Matas J., Sebe N., and Welling M. (eds) Computer Vision – Proceedings of the European Conference on Computer Vision (ECCV), 2016, Lecture Notes in Computer Science, Vol. 9906, Springer, Cham. https://doi.org/10.1007/978-3-319-46475-6_43

  22. Dosovitskiy, A., and Brox, T.: Generating images with perceptual similarity metrics based on deep networks. Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS), ACM, Barcelona, Spain, 2016, pp. 658–666

  23. Yuan, Y., Liu, S., Zhang, J., Zhang, Y., Dong, C., and Lin, L.: Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE/CVF, Salt Lake City, UT, USA, 2018, pp. 81400–81409. https://doi.org/10.1109/CVPRW.2018.00113

  24. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., and Shi, W.: Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Honolulu, HI, USA, 2017, pp. 105–114. https://doi.org/10.1109/CVPR.2017.19

  25. Ma, T., Tian, W.: Back-projection-based progressive growing generative adversarial network for single image super-resolution. Vis. Comput. 37(5), 925–938 (2021). https://doi.org/10.1007/s00371-020-01843-3

    Article  Google Scholar 

  26. Song, H., Wang, M., Zhang, L., Li, Y., Jiang, Z., Yin, G.: S2RGAN: Sonar-image super-resolution based on generative adversarial network. Vis. Comput. 37(8), 2285–2299 (2021). https://doi.org/10.1007/s00371-020-01986-3

    Article  Google Scholar 

  27. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004). https://doi.org/10.1109/TIP.2003.819861

    Article  Google Scholar 

  28. Yue, L., Shen, H., Li, J., Yuan, Q., Zhang, H., Zhang, L.: Image super-resolution: The techniques, applications, and future. Signal Process. 128, 389–408 (2016). https://doi.org/10.1016/j.sigpro.2016.05.002

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Egyptian Armed Forces, Cairo, Egypt

    Aiman Mousa, Yasser Badran, Gouda Salama & Tarek Mahmoud

Authors
  1. Aiman Mousa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yasser Badran
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gouda Salama
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tarek Mahmoud
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tarek Mahmoud.

Ethics declarations

Conflict of interest

The authors have no conflicts of interest to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mousa, A., Badran, Y., Salama, G. et al. Regression layer-based convolution neural network for synthetic aperture radar images: de-noising and super-resolution. Vis Comput 39, 1295–1306 (2023). https://doi.org/10.1007/s00371-022-02405-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-022-02405-5

Keywords