Skip to main content
Springer Nature Link
Log in

Fusion of UNet and ResNet decisions for change detection using low and high spectral resolution images

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

Abstract

Image change detection is an active research topic in the field of remote sensing, as it allows monitoring environmental changes that occur on temporal and spatial scales. However, most of the existing change detection methods suffer from a lack of adaptability to different image types and lack of large-scale validation. In this study, we propose an automatic change detection method, called "CD-ResUNet," based on multi-spectral NDVI imagery. It is an end-to-end deep learning method based on the fusion of two complementary deep learning networks: UNet and residual networks (ResNet). Extensive experiments have been conducted on low-resolution as well as high-resolution datasets using four represented geographical areas, which are Colombia, California, Brazil, and Duluth, each containing 145,161 patches, and the Change Detection Dataset containing 16,000 patches. For all the investigated regions, the proposed method outperforms many relevant state-of-the-art methods with an accuracy up to 99.5% and an F1-score of 99.40%.

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
Fig. 6
Fig. 7

Similar content being viewed by others

Availability of data and materials

The used datasets are available from the authors.

References

  1. Khelifi, L., Mignotte, M.: Deep learning for change detection in remote sensing images: comprehensive review and meta-analysis. Ieee Access 8, 126385–126400 (2020). https://doi.org/10.1109/ACCESS.2020.3008036

    Article  Google Scholar 

  2. Shi, J., et al.: Unsupervised Multiple Change Detection in Remote Sensing Images via Generative Representation Learning Network. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021). https://doi.org/10.1109/LGRS.2021.3085022

    Article  Google Scholar 

  3. Fang, H., Du, P., Wang, X.: A novel unsupervised binary CD method for VHR optical remote sensing imagery over urban areas. J. Appl. Earth Observ. Geoinform. 108, 102749 (2022). https://doi.org/10.1016/j.jag.2022.102749

    Article  Google Scholar 

  4. Shi, J., et al.: Fine object change detection based on vector boundary and deep learning with high-resolution remote sensing images. IEEE J. Appl. Earth Observ. Remote Sens. 15, 4094–4103 (2022). https://doi.org/10.1109/JSTARS.2022.3168691

    Article  Google Scholar 

  5. Pati, C., et al.: A novel hybrid machine learning approach for change detection in remote sensing images. Eng. Sci. Technol. 23(5), 973–981 (2020). https://doi.org/10.1016/j.jestch.2020.01.002

    Article  Google Scholar 

  6. Daudt, et al.: Urban change detection for multi-spectral earth observation using convolutional neural networks. IEEE International Geoscience and Remote Sensing Symposium (pp. 2115–2118) (2018). https://doi.org/10.48550/arXiv.1810.08468

  7. Jing, W., et al.: Remote sensing change detection based on unsupervised multi-attention slow feature analysis. Remote Sensing 14(12), 2834 (2022). https://doi.org/10.3390/rs14122834

    Article  Google Scholar 

  8. Dhaya, R.: Hybrid machine learning approach to detect the changes in SAR images for salvation of spectral constriction problem. J. Innov. Image Process. 3(02), 118–130 (2021). https://doi.org/10.36548/jiip.2021.2.004

    Article  Google Scholar 

  9. Han, T., et al.: Change detection for heterogeneous remote sensing images with improved training of hierarchical extreme learning machine. Remote Sens. 13(23), 4918 (2021). https://doi.org/10.3390/rs13234918

    Article  Google Scholar 

  10. Zulfiqar, et al.: AI-ForestWatch: semantic segmentation based end-to-end framework for forest estimation and change detection using multi-spectral remote sensing imagery. Journal of Applied Remote Sensing 15(2), 024518–024518 (2021). https://doi.org/10.1117/1.JRS.15.024518

  11. Gharbi, W., Chaari, L., Benazza-Benyahia, A.: Unsupervised Bayesian change detection for remotely sensed images. Signal Image Video Process. 15(1), 205–213 (2021). https://doi.org/10.1007/s11760-020-01738-9

  12. Adil, E.: Cascaded U-Net with training wheel attention module for change detection in satellite images. Remote Sensing 14(24), 6361 (2022). https://doi.org/10.3390/rs14246361

    Article  Google Scholar 

  13. Lv.: Simple multiscale unet for change detection with heterogeneous remote sensing images. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2022). https://doi.org/10.1109/LGRS.2022.3173300

  14. Liu, et al.: Building footprint extraction from unmanned aerial vehicle images via PRU-Net. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 14, 2236–2248 (2021). https://doi.org/10.1109/JSTARS.2021.3052495

  15. Alexakis, E.B., Armenakis, C.: Evaluation of UNet and UNet++ architectures in high resolution image change detection applications. Int. Arch. of Photogramm. Remote Sens. Spat. Inform. Sci. 43, 1507–1514 (2020). https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1507-2020

    Article  Google Scholar 

  16. Amri, et al.: Offshore oil slick detection: From photo-interpreter to explainable multi-modal deep learning models using SAR images and contextual data. Remote Sens. 14(15), 3565 (2022). https://doi.org/10.3390/rs14153565

  17. Wang, J.: An MLC and U-Net integrated method for land use/land cover change detection based on time series NDVI-composed image from PlanetScope satellite. Water 14(21), 3363 (2022). https://doi.org/10.3390/w14213363

  18. Lebedev: Change detection in remote sensing images using conditional adversarial networks. Remote Sens. Spatial Inform. Sci. 42, 565–571 (2018). https://doi.org/10.5194/isprs-archives-XLII-2-565-2018

  19. Brahim, E., Bouzidi, S., Barhoumi, W.: Change detection in optical remote sensing images using shearlet transform and convolutional neural networks. Conference on Computer Systems and Applications (1-7) (2021) https://doi.org/10.1109/AICCSA53542.2021.9686924

  20. Wang, J., et al.: Change detection from synthetic aperture radar images via dual path denoising network. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 15, 2667–2680 (2022). https://doi.org/10.1109/JSTARS.2022.3159619

    Article  Google Scholar 

  21. Li: Change detection from SAR images based on convolutional neural networks guided by saliency enhancement. Remote Sens. 13(18), 3697 (2021). https://doi.org/10.3390/rs13183697

  22. Yang, et al.: Novel Spatial-Spectral Channel Attention Neural Network for Land Cover Change Detection with Remote Sensed Images. Remote Sensing 15(1), 87 (2022). https://doi.org/10.3390/rs15010087

  23. Bain, R.: Visualizing the loss landscape of winning lottery tickets (2021). https://doi.org/10.48550/arXiv.2112.08538

Download references

Funding

We acknowledge that this article was produced without external funding.

Author information

Authors and Affiliations

  1. Laboratoire de Recherche en Informatique, Modelisation et Traitement de l’Information et de la Connaissance (LIMTIC), LR16ES06, Institut Supérieur d’Informatique, Université de Tunis El Manar, Tunis, Tunisia

    Emna Brahim, Emna Amri, Walid Barhoumi & Sonia Bouzidi

  2. Ecole Nationale d’Ingénieurs de Carthage, Université de Carthage, Tunis, Tunisia

    Walid Barhoumi

  3. Institut National des Sciences Appliquées et de Technologie, Université de Carthage, Tunis, Tunisia

    Sonia Bouzidi

Authors
  1. Emna Brahim
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Emna Amri
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Walid Barhoumi
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Sonia Bouzidi
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

All authors have contributed equally to this work.

Corresponding author

Correspondence to Walid Barhoumi.

Ethics declarations

Ethical approval

Not applicable.

Conflict of interest

The authors declare no conflict of interest.

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

Brahim, E., Amri, E., Barhoumi, W. et al. Fusion of UNet and ResNet decisions for change detection using low and high spectral resolution images. SIViP 18 (Suppl 1), 695–702 (2024). https://doi.org/10.1007/s11760-024-03185-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-024-03185-2

Keywords