Skip to main content
SpringerLink
Log in

A hidden Markov model method for non-stationary noise reduction: case study on Sentinel data for mowing detection

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

We propose a method for reducing the non-stationary noise in signal time series of Sentinel data, based on a hidden Markov model. Our method is applied on interferometric coherence from Sentinel-1 and the normalized difference vegetation index (NDVI) from Sentinel-2, for detecting the mowing events based on long short-term memory (LSTM). With integrating our noise reduction step to the LSTM neural network architecture, we improved the \(F_1\)-score from 0.69 to 0.76.

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

Similar content being viewed by others

Notes

  1. https://kappazeta.ee/.

  2. https://www.pria.ee.

References

  1. Audhkhasi, K., Osoba, O., Kosko, B.: Noisy hidden Markov models for speech recognition. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2013)

  2. Beck, P.S., Atzberger, C., Høgda, K.A., Johansen, B., Skidmore, A.K.: Improved monitoring of vegetation dynamics at very high latitudes: a new method using MODIS NDVI. Remote Sens. Environ. 100(3), 321–334 (2006)

    Article  Google Scholar 

  3. De Vroey, M., Radoux, J., Defourny, P.: Grassland mowing detection using sentinel-1 time series: potential and limitations. Remote Sens. 13(3), 348 (2021)

    Article  Google Scholar 

  4. Garioud, A., Giordano, S., Valero, S., Mallet, C.: Challenges in grassland mowing event detection with multimodal sentinel images. In: 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), pp. 1–4 (2019). https://doi.org/10.1109/Multi-Temp.2019.8866914

  5. Ghabeli, L., Amindavar, H.: Image denoising using hidden Markov models. In: EurAsia-ICT 2002: Information and Communication Technology: First EurAsian Conference Shiraz, Iran, October 29–31, 2002 Proceedings, pp. 402–409. Springer (2002)

  6. Hird, J.N., McDermid, G.J.: Noise reduction of NDVI time series: an empirical comparison of selected techniques. Remote Sens. Environ. 113(1), 248–258 (2009)

    Article  Google Scholar 

  7. Jonsson, P., Eklundh, L.: Seasonality extraction by function fitting to time-series of satellite sensor data. IEEE Trans. Geosci. Remote Sens. 40(8), 1824–1832 (2002)

    Article  Google Scholar 

  8. Khabbazan, S., Vermunt, P., Steele-Dunne, S., Ratering Arntz, L., Marinetti, C., van der Valk, D., Iannini, L., Molijn, R., Westerdijk, K., van der Sande, C.: Crop monitoring using sentinel-1 data: a case study from the Netherlands. Remote Sens. 11(16), 1887 (2019)

    Article  Google Scholar 

  9. Kolecka, N., Ginzler, C., Pazur, R., Price, B., Verburg, P.H.: Regional scale mapping of grassland mowing frequency with sentinel-2 time series. Remote Sens. 10(8), 1221 (2018)

    Article  Google Scholar 

  10. Nilsson, M., Dahl, M., Claesson, I.: HMM-based speech enhancement applied in non-stationary noise using cepstral features and log-normal approximation. In: 2003-12-08 (2003)

  11. Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H.G., Ogata, T.: Audio-visual speech recognition using deep learning. Appl. Intell. 42, 722–737 (2015)

  12. Sameti, H., Deng, L.: Nonstationary-state hidden Markov model representation of speech signals for speech enhancement. Signal Process. 82(2), 205–227 (2002)

    Article  MATH  Google Scholar 

  13. Sammut, C., Webb, G.I. (eds.): Baum-Welch Algorithm, p. 74. Springer US, Boston (2010)

  14. Stendardi, L., Karlsen, S.R., Niedrist, G., Gerdol, R., Zebisch, M., Rossi, M., Notarnicola, C.: Exploiting time series of sentinel-1 and sentinel-2 imagery to detect meadow phenology in mountain regions. Remote Sens. 11(5), 542 (2019)

    Article  Google Scholar 

  15. Tamm, T., Zalite, K., Voormansik, K., Talgre, L.: Relating sentinel-1 interferometric coherence to mowing events on grasslands. Remote Sens. 8(10), 802 (2016)

    Article  Google Scholar 

  16. Taravat, A., Wagner, M.P., Oppelt, N.: Automatic grassland cutting status detection in the context of spatiotemporal sentinel-1 imagery analysis and artificial neural networks. Remote Sens. 11(6), 711 (2019)

    Article  Google Scholar 

  17. Vaseghi, S.V.: Advanced Digital Signal Processing and Noise Reduction. Wiley (2008)

    Book  Google Scholar 

  18. Vaseghi, S.V., Milner, B.P.: Noise-adaptive hidden Markov models based on Wiener filters. In: Third European Conference on Speech Communication and Technology (1993)

  19. Veisi, H., Sameti, H.: Speech enhancement using hidden Markov models in Mel-frequency domain. Speech Commun. 55(2), 205–220 (2013)

    Article  Google Scholar 

  20. Voormansik, K., Zalite, K., Sünter, I., Tamm, T., Koppel, K., Verro, T., Brauns, A., Jakovels, D., Praks, J.: Separability of mowing and ploughing events on short temporal baseline sentinel-1 coherence time series. Remote Sens. 12(22), 3784 (2020)

  21. Zhao, D.Y., Kleijn, W.B.: HMM-based gain modeling for enhancement of speech in noise. IEEE Trans. Audio Speech Lang. Process. 15(3), 882–892 (2007)

    Article  Google Scholar 

Download references

Acknowledgements

This research work was supported by Kappazeta under the project “Noise Modelling for Refining Farming Activities Recognition Based on Sentinel Data” and the European Social Fund via IT Academy program.

Author information

Authors and Affiliations

  1. ITS Lab, Institute of Computer Science, University of Tartu, 51009, Tartu, Estonia

    Kaveh Khoshkhah, Kyrylo Medianovskyi, Dmitry Kolesnykov & Amnir Hadachi

  2. KappaZeta Ltd, Tartu, Estonia

    Kaupo Voormansik

Authors
  1. Kaveh Khoshkhah
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kyrylo Medianovskyi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dmitry Kolesnykov
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Amnir Hadachi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kaupo Voormansik
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kaveh Khoshkhah.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Khoshkhah, K., Medianovskyi, K., Kolesnykov, D. et al. A hidden Markov model method for non-stationary noise reduction: case study on Sentinel data for mowing detection. SIViP 17, 3477–3483 (2023). https://doi.org/10.1007/s11760-023-02571-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-023-02571-6

Keywords

Search

Navigation