Skip to main content
SpringerLink
Log in

Image deconvolution for optical small satellite with deep learning and real-time GPU acceleration

  • Special Issue Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

In-orbit optical-imaging instruments may suffer from degradations due to space environment impacts or long-time operation. The degradation causes blurring on the image received from the ground. Degradations come from defocus and spherical aberrations cause blurring on the received image. Image deblurring should be done in pre-processing step to compensate the sensor bad impacts. The aberrations are modeled by Zernike polynomials and treated by deep learning in deblurring method. This paper presents a method to deconvolve the acquired data to improve the image quality. A convolution neural network is trained to estimate the point spread function (PSF) parameters using acquired images over satellite calibration site with specific pattern. Image deconvolution is performed to obtain image signal-to-noise (SNR) and modulation transfer function (MTF) improvement. Technical and image data used for modeling and experiment are used from VNREDSat-1 satellite (the first operational Vietnam Earth observation optical small satellite). The experiment is performed on computers accelerated by graphics processing units (GPU) to ensure fast computation.

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

Access this article

Log in via an institution

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Availability of data and material

The involved data that support the findings of this article can be shared. Requests for relevant information or data on the study can be sent to the corresponding author.

References

  1. John, R.S.: Remote sensing: the image chain approach, pp.360-368. Oxford Press (2007)

    Google Scholar 

  2. European Space Agency. https://earth.esa.int/web/eoportal/satellite-missions/v-w-x-y-z/vnredsat-1. Accessed 01 Jan 2021

  3. Jacques, B., Didier, C., Michel, B.: All Sic telescope technology at EADS-Astrium. ICSO (2012). https://doi.org/10.1117/12.2552106

    Google Scholar 

  4. Tan, D.N., Tuyen, T.B., Tuan, M.P.: Radiometric calibration for Earh observation satellite optical instrument. Commun. Phys. 29, 870 (2019)

    Article  Google Scholar 

  5. Philippe, B., Lucien, W.: A review of earth-viewing methods for in-flight assessment of modulation transfer function and noise of optical spaceborne sensors. Working paper (2009). https://hal-mines-paristech.archives-ouvertes.fr/hal-00745076

  6. Steven, W.S.: The scientist and engineer's guide to digital signal processing, chapter 25: special imaging techniques, pp. 423-450. (1999)

  7. Dennis, D., Hans, K.: Design and end-to-end modelling of a deployable telescope. In: Int. Conf. on Space Optics (2016). https://doi.org/10.1117/12.2296169

  8. Steven, V.: The scientist and engineer’s guide to digital signal processing, pp. 209-224. California Technical Publishing San Diego (1999)

    Google Scholar 

  9. VEGA Group: Calibration test sites selection and characterisation. VEGA Group (2008)

    Google Scholar 

  10. Daniel, R.S., Johannes, W.K., Jason, B., Michael, E.S., Klaus, I.I.: Calibration concept for potential optical aberrations of the APEX pushbroom imaging spectrometer. In: Proc. SPIE 5234, Sensors, Systems, and Next-Generation Satellites VII (2004). https://doi.org/10.1117/12.510640

  11. Goodman, J.W.: Introduction to Fourier optics. McGraw Hill (1968)

    Google Scholar 

  12. Gaskill, J.D.: Linear systems Fourier transforms. Optics. Wiley (1978)

    Google Scholar 

  13. Thibos, L. N.: Handbook of visual optics, draft chapter on standards for reporting aberrations of the eye. J Refract Surg, 18. s652-s660. (1999)

  14. Lebegue, L., Pascal, V., Meygret, A., Leger, D.: SPOT5 radiometric image quality. In: IEEE International Geoscience and Remote Sensing Symposium (2003). https://doi.org/10.1109/IGARSS.2003.1293758

  15. Ngoc, V.B.P., Tu, N.N., Tan, D.N., Anh, T.T., Giang, L.N.: A novel approach for pivot-based sensor fusion of small satellites. Phys. Commun. 45, 101261 (2021)

    Article  Google Scholar 

  16. Chahira, S., Youcef, G.: Dynamic MTF estimate of the optical imager onboard Alsat-1B satellite. In: Int. Conf. on Space Optics (2008). https://doi.org/10.1117/12.2536199

  17. Issam, B., Redouane, M., Bachir, T., Mohamed, H., Kamel H.: Rigorous geometrical modeling of ALSAT-2A Algerian satellite. In: SPIE Proceedings 8533 (2012). https://doi.org/10.1117/12.974613

  18. Yuriy, B., Olga, S., Roman, K.: Blind PSF estimation and methods of deconvolution optimization. (2012). arXiv:1206.3594

  19. Patrizio, C., Karen, E.: Blind image deconvolution: theory and applications, pp. 1–31. CRC Press (2007)

    MATH  Google Scholar 

  20. Dietrich, K.: Anastigmatic three-mirror telescope. Appl. Opt. 16(8), 2074 (1977)

    Article  Google Scholar 

  21. Jian, S., Wenfei, C., Zongben, X., Jean, P.: Learning a convolutional neural network for non-uniform motion blur removal. In: IEEE Conference on Com. Vision and Pattern Recog (2015). https://doi.org/10.1109/CVPR.2015.7298677

  22. Alex, K., Ilya, S., Geoffrey, E. H.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inform. Process. Syst. (2012). https://doi.org/10.1145/3065386

  23. Daniel, S., Klaus, K., Stefan, P.: Performance and scalability of GPU-based convolutional neural networks. In: 18th Euromicro Conf. on Parallel, Distributed and Network-based Processing (2010). https://doi.org/10.1109/PDP.2010.43

  24. Patrick, Y. M.: Zernike polynomials and their use in describing the wavefront aberrations of the human eye. Appl. Vis. Imaging Syst. (2003)

  25. Mahajan, V.N.: Optical imaging and aberrations, part I ray geometrical optics. SPIE Press (1998). https://doi.org/10.1117/3.265735

    Book  Google Scholar 

Download references

Funding

The paper was funded by Research Projects under the grant number VAST01.06/18-19 , Vietnam Academy of Science and Technology.

Author information

Authors and Affiliations

  1. Space Technology Institute, Vietnam Academy of Science and Technology, Hanoi, Vietnam

    Tan D. Ngo, Tuyen T. Bui & Tuan M. Pham

  2. Institute of Science and Technology, Ministry of Public Security, Hanoi, Vietnam

    Hong T. B. Thai

  3. Institute of Information Technology, Vietnam Academy of Science and Technology, Hanoi, Vietnam

    Giang L. Nguyen

  4. Department of Computer Science, Purdue University Fort Wayne, Fort Wayne, IN, 46805, USA

    Tu N. Nguyen

Authors
  1. Tan D. Ngo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tuyen T. Bui
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tuan M. Pham
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hong T. B. Thai
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Giang L. Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Tu N. Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization TMP and TDN. Methodology TDN, GLN and HTBT. Software TDN, GLN and HTBT. Validation TTB and TNN. Investigation HTBT and TTB. Resources TDN and TMP. Writing—original draft preparation. TNN, TDN and HTBT. Writing—review and editing. TNN, TDN and HTBT. Project administration TMP. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Tu N. Nguyen.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interests regarding the publication of this article.

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

Ngo, T.D., Bui, T.T., Pham, T.M. et al. Image deconvolution for optical small satellite with deep learning and real-time GPU acceleration. J Real-Time Image Proc 18, 1697–1710 (2021). https://doi.org/10.1007/s11554-021-01113-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-021-01113-y

Keywords

Search

Navigation