Skip to main content
SpringerLink
Log in

Cloud Detection from Remote Sensing Images by Cascaded U-shape Attention Networks

  • Conference paper
  • First Online:
Image and Graphics (ICIG 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14355))

Included in the following conference series:

Abstract

Cloud is an important meteorological information in remote sensing applications as it plays a significant role in the Earth’s climate and weather patterns, but it also brings difficulties to the information extraction from optical images, especially when the underlying surface features to be analyzed are obscured. Therefore, cloud detection is an indispensable step in optical remote sensing image processing. Different from low-spatial resolution images, medium and high-resolution images contain richer geographical features, and the distribution of clouds is more scattered, which makes it necessary to enhance the network’s ability on detailed features extraction. Therefore, the two cascaded U-shape attention networks (CUA-Net) model is proposed to detect the cloud in Landsat 8 images. In the first U-shape network, the up-sampling layers in path expansion integrate the information from all previous layers to make full use of multi-scale features. Additionally, the attention modules in the skip connection are added to detect the position and edges of cloud accurately. After that, the second U-shape network is utilized to optimize the preliminary segmentations from the first network, thus obtaining results closer to the ground truth. In the experiments, CUA-Net was evaluated on 38-Cloud Dataset and compared with current mainstream networks, showing significant improvements both on visual effects and quantitative indicators.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Long, C., Li, X., Jing, Y., Shen, H.: Bishift networks for thick cloud removal with multitemporal remote sensing images. Int. J. Intell. Syst.Intell. Syst. 2023, 9953198 (2023)

    Google Scholar 

  2. Gupta, R., Nanda, S.J.: Cloud detection in satellite images with classical and deep neural network approach: a review. Multimed. Tools Appl. 81(22), 31847–31880 (2022)

    Article  Google Scholar 

  3. Irish, R.R., Barker, J.L., Goward, S.N., Arvidson, T.: Characterization of the Landsat-7 ETM+ automated cloud-cover assessment (ACCA) algorithm. Photogramm. Eng. Remote Sens.. Eng. Remote Sens. 72(10), 1179–1188 (2006)

    Article  Google Scholar 

  4. Zhu, Z., Woodcock, C.E.: Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sens. Environ. 118, 83–94 (2012)

    Article  Google Scholar 

  5. Sun, L., et al.: A universal dynamic threshold cloud detection algorithm (UDTCDA) supported by a prior surface reflectance database. J. Geophys. Res. Atmospheres 121(12), 7172–7196 (2016)

    Article  Google Scholar 

  6. Xu, L., Wong, A., Clausi, D.A.: A novel bayesian spatial-temporal random field model applied to cloud detection from remotely sensed imagery. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 55(9), 4913–4924 (2017)

    Article  Google Scholar 

  7. Başeski, E., Cenaras, Ç.: Texture and color based cloud detection. In: 7th International Conference on Recent Advances in Space Technologies, pp. 311–315. Istanbul, Turkey (2015)

    Google Scholar 

  8. He, X.Y., Hu, J.B., Chen, W., Li, X.Y.: Haze removal based on advanced haze-optimized transformation (AHOT) for multispectral imagery. Int. J. Remote Sens. 31(20), 5331–5348 (2010)

    Article  Google Scholar 

  9. Gómez-Chova, L., et al.: Cloud detection for CHRIS/Proba hyperspectral images. In: 10th Remote Sensing of Clouds and the Atmosphere, pp. 508–519. International Society for Optics and Photonics, Bruges, Belgium (2005)

    Google Scholar 

  10. Surya, S., Simon, P.: Automatic cloud detection using spectral rationing and fuzzy clustering. In: 2nd International Conference on Advanced Computing, Networking and Security, pp. 90-95. Mangalore, India (2013)

    Google Scholar 

  11. Bo, P., Fenzhen, S., Yunshan, M.: A cloud and cloud shadow detection method based on fuzzy c-means algorithm. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 13, 1714–1727 (2020)

    Article  Google Scholar 

  12. Li, P., Dong, L., Xiao, H., Xu, M.: A cloud image detection method based on SVM vector machine. Neurocomputing 169, 34–42 (2015)

    Article  Google Scholar 

  13. Sui, Y., He, B., Fu, T.: Energy-based cloud detection in multispectral images based on the SVM technique. Int. J. Remote Sens. 40(14), 5530–5543 (2019)

    Article  Google Scholar 

  14. Latry, C., Panem, C., Dejean, P.: Cloud detection with SVM technique. In: International Geoscience and Remote Sensing Symposium, pp. 448–451. Barcelona Spain (2007)

    Google Scholar 

  15. Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: 18th International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234–241. Springer, Munich, Germany (2015)

    Google Scholar 

  16. Mohajerani, S., Krammer, T.A., Saeedi, P.: A cloud detection algorithm for remote sensing images using fully convolutional neural networks. In: 20th International Workshop on Multimedia Signal Processing, pp. 1–5. Vancouver, Canada (2018)

    Google Scholar 

  17. Kushnure, D.T., Talbar, S.N.: MS-UNet: a multi-scale UNet with feature recalibration approach for automatic liver and tumor segmentation in CT images. Comput. Med. Imaging Graph.. Med. Imaging Graph. 89, 101885 (2021)

    Article  Google Scholar 

  18. Mohajerani, S., Saeedi, P.: Cloud-Net: An end-to-end cloud detection algorithm for Landsat 8 imagery. In: 39th International Geoscience and Remote Sensing Symposium, pp. 1029–1032. IEEE, Yakohama, Japan (2019)

    Google Scholar 

  19. Huang, H., et al.: Unet 3+: a full-scale connected unet for medical image segmentation. In: 45th International Conference on Acoustics, Speech and Signal Processing, pp. 1055–1059. Barcelona, Spain (2020)

    Google Scholar 

  20. Li, X., Yang, X., Li, X., Lu, S., Ye, Y., Ban, Y.: GCDB-UNet: a novel robust cloud detection approach for remote sensing images. Knowl.-Based Syst..-Based Syst. 238, 107890 (2022)

    Article  Google Scholar 

  21. Lu, C., Xia, M., Qian, M., Chen, B.: Dual-branch network for cloud and cloud shadow segmentation. IEEE Trans. Geosci. Remote Sens.Geosci. Remote Sens. 60, 1–12 (2022)

    Google Scholar 

  22. Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: 15th European Conference on Computer Vision, pp. 3–19. Munich, Germany (2018)

    Google Scholar 

Download references

Acknowledgement

The authors are grateful to the reviewers for their attention and comments on our paper. This research is supported by the National Natural Science Foundation of China (NSFC) under Grant no. 42171302 and the Key R&D Program of Hubei Province, China (2021BAA185).

Author information

Authors and Affiliations

  1. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China

    Ao Li & Xinghua Li

  2. CCCC Second Highway Consultants Co, Ltd, Wuhan, China

    Jing Yang

Authors
  1. Ao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jing Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xinghua Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xinghua Li .

Editor information

Editors and Affiliations

  1. Dalian University of Technology, Dalian, China

    Huchuan Lu

  2. University of Sydney, Sydney, NSW, Australia

    Wanli Ouyang

  3. Shenzhen University, Shenzhen, China

    Hui Huang

  4. Tsinghua University, Beijing, China

    Jiwen Lu

  5. Dalian University of Technology, Dalian, China

    Risheng Liu

  6. Institute of Automation, CAS, Beijing, China

    Jing Dong

  7. University of Technology Sydney, Sydney, NSW, Australia

    Min Xu

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, A., Yang, J., Li, X. (2023). Cloud Detection from Remote Sensing Images by Cascaded U-shape Attention Networks. In: Lu, H., et al. Image and Graphics. ICIG 2023. Lecture Notes in Computer Science, vol 14355. Springer, Cham. https://doi.org/10.1007/978-3-031-46305-1_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-46305-1_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-46304-4

  • Online ISBN: 978-3-031-46305-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation