The Development of a Hybrid Solution to Replacement of Clouds and Shadows in Remote Sensing Images

  • Ana Carolina Siravenha
  • Danilo Sousa
  • Evaldo Pelaes
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 15)


Nowadays, many works are dedicated to improve the research results, previously achieved manually, by computational solutions. On light of this, the presented work aims to overcome a common problem in many satellite images, which is the presence of undesirable atmospheric components such as clouds and shadows at the time of scene capture. The presence of such elements hinders the identification of meaningful information for applications like urban and environmental monitoring, exploration of natural resources, etc. Thus, it is presented a new way to perform a hybrid approach toward removal and replacing of these elements. The authors propose a method of regions decomposition using a nonlinear median filter, in order to map regions of structure and texture. These types of regions will explain which method will be applied to region redefinition. At structure region, will be applied the method of inpainting by a smoothing based on DCT, and at texture one, will be applied the exemplar-based texture synthesis. To measure the effectiveness of this proposed technique, a qualitative assessment was presented, at the same time that a discussion about quantitative analysis was made.


Inpainting Texture synthesis Replacement of clouds and shadows 



This work was supported by the Amazon Research Foundation/Vale S/A [grant number 021/2010]; and the National Council of Technological and Scientific Development [grant number 142404/2011-0].


  1. 1.
    Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. In: Proceedings of the 27th annual conference on computer graphics and interactive techniques. ACM Press/Addison-Wesley Publishing Co, New York, pp 417–424Google Scholar
  2. 2.
    Bertalmio M, Vese L, Sapiro G, Osher S (2003) Simultaneous structure and texture image inpainting. IEEE Trans Image Process 12(8):882–889CrossRefGoogle Scholar
  3. 3.
    Buckley M (1994) Fast computation of a discretized thin-plate smoothing spline for image data. Oxf Biometrika 81:247–258CrossRefMATHMathSciNetGoogle Scholar
  4. 4.
    Bugeau A, Bertalmio M (2009) Combining texture synthesis and diffusion for image inpainting. In: Ranchordas A, Araújo H (eds) VISAPP 2009—Proceedings of the fourth international conference on computer vision theory and applications, vol 1. INSTICC Press, Lisboa, pp 26–33Google Scholar
  5. 5.
    Criminisi A, Perez P, Toyama K (2004) Region filling and object removal by exemplar-based image inpainting. IEEE Trans On Image Process 13(9):1200–1212, IEEE Computer SocietyGoogle Scholar
  6. 6.
    Efros A, Leung T (1999) Texture synthesis by non-parametric sampling. In: International conference on computer vision. IEEE Computer Society, Washington, pp 1033–1038Google Scholar
  7. 7.
    Garcia D (2010) Robust smoothing of gridded data in one and higher dimensions with missing values. Comput Stat Data Anal 54(4):1167–1178 (Elsevier, Maryland Heights)Google Scholar
  8. 8.
    Hau CY, Liu CH, Chou TY, Yang LS (2008) The efficacy of semi-automatic classification result by using different cloud detection and diminution method. The international archives of the photogrammetry, remote sensing and spatial information sciencesGoogle Scholar
  9. 9.
    Helmer E, Ruefenacht B (2005) Cloud-free satellite images mosaics with regression trees and histgram matching. Photogram Eng Remote Sens 32(9):1079–1089CrossRefGoogle Scholar
  10. 10.
    Hoan NT, Tateishi R (2008) Cloud removal of optical image using SAR data for ALOS applications. Experimenting on simulated ALOS data. The international archives of the photogrammetry, remote sensing and spatial information sciences, BeijingGoogle Scholar
  11. 11.
    Liu H, Wang W, Bi X (2010) Study of image inpainting based on learning. In: proceedings of the international multi conference of engineers and computer scientists. Newswood Limited, Hong Kong, pp 1442–1445Google Scholar
  12. 12.
    Liu Y, Wong A, Fieguth P (2010) Remote sensing image synthesis. In: Geoscience and remote sensing symposium (IGARSS). IEEE International, Honolulu, pp 2467–2470Google Scholar
  13. 13.
    Maalouf A, Carre P, Augereau B, Fernandez Maloigne C (2009) A bandelet-based inpainting technique for clouds removal from remotely sensed images. IEEE Trans Geosci Remote Sens 47(7):2363–2371CrossRefGoogle Scholar
  14. 14.
    Rudin LI, Osher S, Fatemi E (1992) North-Holland nonlinear total variation based noise removal algorithms. Phys D 60:259–268Google Scholar
  15. 15.
    Sarkar S, Healey G (2010) Hyperspectral texture synthesis using histogram and power spectral density matching. IEEE Trans Geosci Remote Sens 48(5):2261–2270CrossRefGoogle Scholar
  16. 16.
    Siravenha A (2011) Um método para classificação de imagens de satélite usando Transformada Cosseno Discreta com detecção e remoção de nuvens e sombras. Universidade Federal do Pará, In Dissertação de mestradoGoogle Scholar
  17. 17.
    Taschler M (2006) A comparative analysis of image inpainting techniques. Technical report. The University of York, New YorkGoogle Scholar
  18. 18.
    Vese LA, Osher SJ (2002) Modeling textures with total variation minimization and oscillating patterns in image processing. J Sci Comput 19:553–572 (Plenum Press, New York)Google Scholar
  19. 19.
    Webster R, Oliver M (2007) Geostatistics for environmental scientists, 2nd edn. Wiley, West SussexCrossRefMATHGoogle Scholar
  20. 20.
    Zhang X, Qin F, Qin Y (2010) Study on the thick cloud removal method based on multi-temporal remote sensing images. In: Conference international on multimedia technology (ICMT). IEEE, Ningbo, pp 1–3Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ana Carolina Siravenha
    • 1
  • Danilo Sousa
    • 1
  • Evaldo Pelaes
    • 1
  1. 1.Federal University of ParaBelémBrazil

Personalised recommendations