Shadow Removal in High-Resolution Satellite Images Using Conditional Generative Adversarial Networks

  • Giorgio MoralesEmail author
  • Samuel G. Huamán
  • Joel Telles
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 898)


In satellite image processing, obscure zones that were affected by shadows are normally discarded from further processing. Nevertheless, for specific applications, such as surveillance, it is desirable to remove shadows despite the fact that reconstructed zones do not necessarily have real reflectance values. In that sense, we propose a shadow removal method in high-resolution satellite images using conditional Generative Adversarial Networks (cGANs). The generator network is trained to produce shadow-free RGB images with condition on a satellite image patch altered with artificial shadows and concatenated with its respective binary shadow mask, while the discriminator is adversely trained to discern if a given shadow-free image comes from the generator or if it is an original RGB image without artificial alteration. The method is tested in the proposed dataset achieving an error ratio comparable with the state of the art. Finally, we confirm the feasibility of the proposed network using real shadowed images.


Generative Adversarial Networks Shadow removal Satellite imagery 



The authors would like to thank the National Commission for Aerospace Research and Development (CONIDA) and the National Institute of Research and Training in Telecommunications of the National University of Engineering (INICTEL-UNI) for the support provided. The training of all the networks was carried out by the High Performance Computational Center of the Peruvian Amazon Research Institute (IIAP). For more information please visit


  1. 1.
    Wang, B., Ono, A., Muramatsu, K., Fujiwara, N.: Automated detection and removal of clouds and their shadows from landsat TM images. IEICE Trans. Inf. Syst. E82–D2, 453–460 (1999)Google Scholar
  2. 2.
    Sah, A.K., Sah, B.P., Honji, K., Kubo, N., Senthil, S.: Semi-automated cloud/shadow removal and land cover change detection using satellite imagery. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 39–B7, 335–340 (2012)CrossRefGoogle Scholar
  3. 3.
    Candra, D.S., Phinn, S., Scarth, P.: Cloud and cloud shadow removal of landsat 8 images using Multitemporal Cloud Removal method. In: 6th International Conference on Agro-Geoinformatics, Fairfax, VA, USA (2017)Google Scholar
  4. 4.
    Murali, S., Govindan, V.K.: Shadow detection and removal from a single image using LAB color space. Cybern. Inf. Technol. 13(1), 95–103 (2013)MathSciNetGoogle Scholar
  5. 5.
    Zigh, E., Belbachir, M.F., Kadiri, M., Djebbouri, M., Kouninef, B.: New shadow detection and removal approach to improve neural stereo correspondence of dense urban VHR remote sensing images. Eur. J. Remote. Sens. 48(1), 447–463 (2015)CrossRefGoogle Scholar
  6. 6.
    Deb, K., Suny, A.H.: Shadow detection and removal based on YCbCr color space. Smart Comput. Rev. 4(1), 23–33 (2014)Google Scholar
  7. 7.
    Finlayson, G.D., Hordley, S.D., Lu, C., Drew, M.S.: On the removal of shadows from images. TPAMI 28(1), 59–68 (2006)CrossRefGoogle Scholar
  8. 8.
    Liu, F., Gleicher, M.: Texture-consistent shadow removal. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 437–450. Springer, Heidelberg (2008). Scholar
  9. 9.
    George, G.E.: Cloud shadow detection and removal from aerial photo mosaics using light detection and ranging (LIDAR) reflectance images. Ph.D. thesis, The University of Southern Mississippi, Mississippi, USA (1996)Google Scholar
  10. 10.
    Khan, S.H., Bennamoun, M., Sohel, F., Togneri, R.: Automatic shadow detection and removal from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 6(1), 431–446 (2015)Google Scholar
  11. 11.
    Kwatra, V., Han, M., Dai, S.: Shadow removal for aerial imagery by information theoretic intrinsic image analysis. In: IEEE International Conference on Computational Photography, pp. 1–8. IEEE, Seattle (2012)Google Scholar
  12. 12.
    Gong, H., Cosker, D.: Interactive shadow removal and ground truth for variable scene categories. In: Proceedings of the British Machine Vision Conference. BMVA Press, Nottingham (2014)Google Scholar
  13. 13.
  14. 14.
    Perlin, K.: Improving noise. ACM Trans. Graph. 21(3), 681–682 (2002)CrossRefGoogle Scholar
  15. 15.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
  16. 16.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu (2017)Google Scholar
  17. 17.
    Cao, Y., Zhou, Z., Zhang, W., Yu, Y.: Unsupervised diverse colorization via generative adversarial networks. arXiv preprint arXiv:1702.06674v2 (2017)CrossRefGoogle Scholar
  18. 18.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  19. 19.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), San Diego (2015)Google Scholar
  20. 20.
    Morales, G., Arteaga, D., Huamán, S., Telles, J.: Shadow detection in high-resolution multispectral satellite imagery using generative adversarial networks. In: 2018 IEEE XXV International Conference on Electronics, Electrical Engineering and Computing (INTERCON), pp. 1–4. IEEE, Lima (2018).

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.National Institute of Research and Training in Telecommunications (INICTEL-UNI)National University of EngineeringLimaPeru

Personalised recommendations