Advertisement

Cloud Detection in High-Resolution Remote Sensing Images Using Multi-features of Ground Objects

  • Jing ZhangEmail author
  • Qin Zhou
  • Xiao Shen
  • Yunsong Li
Article

Abstract

The existence of clouds in high-resolution remote sensing images influences target recognition and feature classification. Therefore, finding areas covered with clouds is an important preprocessing step in remote sensing image applications. This paper proposes a cloud detection method for satellite images with high resolution using ground objects’ multi-features, such as color, texture, and shape. First, the highly reflective areas are extracted from the image using the minimum cross entropy threshold method. Second, the multi-scale image decomposition based on domain transform filter extracts the texture features of ground objects. Finally, based on the shape features, regular-shaped artificial ground objects are removed to further improve cloud detection accuracy. The experimental results show that the proposed method not only improves the overall accuracy rate but also reduces the false positive rate compared to the classical traditional cloud detection methods. The method is suitable for cloud detection in high-resolution remote sensing images with complex ground objects.

Keywords

Cloud detection Multi-scale decomposition Domain transform filter Regular-shaped artificial ground objects 

Notes

Funding

This work is supported in part by the National Nature Science Foundation of China under Grants 61571345, Yangtse Rive Scholar Bonus Schemes and Ten Thousand Talent Program.

Compliance with Ethical Standards

All authors have participated in (a) conception and design, or analysis and interpretation of the data and (b) drafting the article or revising it critically for important intellectual content.

Conflict of Interest

The authors have no affiliation with any organization with a direct or indirect financial interest in the subject matter discussed in the manuscript.

References

  1. An Z, Shi Z (2017) Scene learning for cloud detection on remote-sensing images. IEEE J Sel Top Appl 8(8):4206–4222Google Scholar
  2. Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal 24(5):603–606CrossRefGoogle Scholar
  3. Filonchyk M, Yan H, Zhang Z et al (2019) Combined use of satellite and surface observations to study aerosol optical depth in different regions of China. Sci Rep 9(1):2019CrossRefGoogle Scholar
  4. Frey RA, Ackerman SA, Liu Y et al (2008) Cloud detection with MODIS. Part I: Improvements in the MODIS cloud mask for collection 5. J Atmos Ocean Technol 25(7):1057–1072CrossRefGoogle Scholar
  5. Gastal ES, Oliveira M (2011) Domain transform for edge-aware image and video processing. ACM Trans Graph 30(2011):69Google Scholar
  6. Hou S, Sun W, Zheng X (2014) Summary of cloud detection methods for remote sensing images. Space Electron Technol 2014(3):68–76Google Scholar
  7. Jedlovec G, Haines S (2007) Spatial and temporal varying thresholds for cloud detection in satellite imagery geoscience and remote sensing symposium, 2007. IGARSS 2007. IEEE Int 2007:3329–3332Google Scholar
  8. Kang Y, Pan L, Sun M, Chen Q, Wang Y et al (2017) Gaussian mixture model based cloud detection for Chinese high resolution satellite imagery. Geomat Inf Sci Wuhan Univ 42(6):782–788Google Scholar
  9. Li CH, Lee C (1993) Minimum cross entropy thresholding. Pattern Recogn 26(4):617–625CrossRefGoogle Scholar
  10. Li Y, Yu R, Xu Y et al (2004) Spatial distribution and seasonal variation of cloud over China based on ISCCP data and surface observations. J Meteorol Soc Jpn, Ser. II 82(2):761–773CrossRefGoogle Scholar
  11. Lin WT, Lin CH, Wu TH et al (2010) Image segmentation using the K-means algorithm for texture features. World Acad Sci Eng Technol 38(5):434–435Google Scholar
  12. Luo Y, Trishchenko AP, Khlopenkov KV (2008) Developing clear-sky, cloud and cloud shadow mask for producing clear-sky composites at 250-meter spatial resolution for the seven MODIS land bands over Canada and North America. Remote Sens Environ 112(12):4167–4185CrossRefGoogle Scholar
  13. Mohajerani S, Krammer T A, Saeedi P (2018) Cloud detection algorithm for remote sensing images using fully convolutional neural networks.  https://doi.org/10.1109/MMSP.2018.8547095
  14. Ozkan S, Efendioglu M, Demirpolat C (2018) Cloud detection from RGB color remote sensing images with deep pyramid network. arXiv:1801.08706v1Google Scholar
  15. Rongali G, Keshari AK, Gosain AK et al (2018) Split-window algorithm for retrieval of land surface temperature using Landsat 8 thermal infrared data. J Geovis Spat Anal 2(2):2018CrossRefGoogle Scholar
  16. Shi M, Xie F, Zi Y, et al (2016) Cloud detection of remote sensing images by deep learning. IGARSS 2016–2016 IEEE international geoscience and remote sensing symposium. IEEEGoogle Scholar
  17. Shi C, Wang Y, Wang C et al (2017) Ground-Based Cloud Detection Using Graph Model Built Upon Superpixels. IEEE Geosci Remote Sens Lett 14(5):719–723CrossRefGoogle Scholar
  18. Wang H, Zhang R, Kuang J et al (2016) A progressive refinement scheme for cloud detection of aerial images. J Wuhan Univ (Nat Sci Edn) 62(6):525–530Google Scholar
  19. Xie F, Shi M, Shi Z et al (2017) Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning. IEEE J Sel Top Appl 2017:1–10Google Scholar
  20. Zhang Q, Xiao C (2014) Cloud detection of RGB color aerial photographs by progressive refinement scheme. IEEE Trans Geosci Remote Sens 52(11):7264–7275CrossRefGoogle Scholar
  21. Zhu H (2005) Digital image processing foundation. Science Press, BeijingGoogle Scholar
  22. Zhu Z, Woodcock CE (2012) Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sens Environ 118:83–94CrossRefGoogle Scholar
  23. Zhu Z, Wang S, Woodcock CE (2015) Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and sentinel 2 images. Remote Sens Environ 159:269–277CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Integrated Service Networks, Xidian UniversityXi’anChina

Personalised recommendations