Research on Remote Sensing Image De‐haze Based on GAN

Abstract

Commonly used remote sensing image de-haze methods include: the image enhancement method and a physical model-based. However, when the above methods are applied to high-resolution remote sensing images, problems with texture information loss and insufficient enhancement often occur. These problems affect further analysis and application of high-resolution remote sensing images. This paper proposes a new single-image de-haze method called texture attention GAN. In this network, in order to solve the problem of texture information loss in the process of de-haze, a texture attention-based generator is adopted. When design the network discriminator, the global and local discriminators are used to improve the distortion of image details. In comparison with several common methods, this method has achieved better results.

This is a preview of subscription content, access via your institution.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7

References

  1. 1.

    Gong, J., & Zhong, Y. (2016). Survey of intelligent optical remote sensing image processing. Journal of Remote Sensing, 20(5), 733–747.

    Google Scholar 

  2. 2.

    Chen, C. H., Liu, Y., & Cui, Q. (2018). Remote sensing image defogging algorithm based on saturation operation and dark channel theory. Computer Engineering and Application, 5, 174–179.

    Google Scholar 

  3. 3.

    Tan, W., Cao, S. X., Qi, W. W., & He, H. Y. (2019). A haze removal method for high-resolution remote sensing images. Acta Optica Sinica, 39(3), 1–17.

    Google Scholar 

  4. 4.

    Yuan, W., Q. (2016). Research on some key technologies of high resolution remote sensing image statistical processing and analysis. Xi’an Electronic and Science University.

  5. 5.

    Hou, J., Ning, L., Ling, Y., et al. (2018). Single image de-haze for visible remote sensing based on tagged haze thickness maps. Remote Sensing Letters, 9(7), 627–635.

    Article  Google Scholar 

  6. 6.

    Kim, T. K., Paik, J. K., & Kang, B. S. (1998). Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering. IEEE Transactions on Consumer Electronics, 44(1), 82–87.

    Article  Google Scholar 

  7. 7.

    Li, L., Jin, W. Q., & Xu, C. (2013). Local nonlinear transform enhancement algorithm for haze weather color image. Journal of Beijing University of Technology, 33(5), 516–522.

    Google Scholar 

  8. 8.

    Wei, Y. H., Zhang, Y. E., Mei, S. L., et al. (2017). Image de-haze method based on dark channel prior and interval interpolation wavelet transform. Journal of Agricultural Engineering, 33(z1), 281–287.

    Google Scholar 

  9. 9.

    Kaplan, N. H. (2018). Remote sensing image enhancement using hazy image model. Optik. https://doi.org/10.1016/j.ijleo.2017.10.132.

    Article  Google Scholar 

  10. 10.

    Zhang, H. Y. (2018). Research on the model and method of visual effect enhancement of satellite remote sensing image. Wuhan: China University of Geosciences.

    Google Scholar 

  11. 11.

    Li, Z. Q., Chen, X. F., Ma, L. Y., et al. (2018). Review on atmospheric correction of optical remote sensing satellite. Journal of Nanjing University of Information Engineering (Natural Science Edition), 10(01), 6–15.

    Google Scholar 

  12. 12.

    Jiang, H., Lu, N., & Yao, L. (2016). A high-fidelity haze removal method based on hot for visible remote sensing images. Remote Sensing, 8(10), 1–18.

    Article  Google Scholar 

  13. 13.

    Zhao, C. L., & Dong, J. W. (2018). Enhancement algorithm of haze weather image based on dark channel and multi-scale Retinex. Laser Journal, 1, 104–109.

    Google Scholar 

  14. 14.

    Moro, G. D.. & Halounova, L. (2007). Haze removal for high-resolution satellite data: a case study. International Journal of Remote Sensing, 28(10), 2187–2205.

    Article  Google Scholar 

  15. 15.

    Tan, R. T. (2008). Visibility in bad weather from a single image. IEEE Conference on Computer Vision & Pattern Recognition. https://doi.org/10.1109/CVPR.2008.4587643.

    Article  Google Scholar 

  16. 16.

    Fattal, R. (2008). Single image de-haze. ACM Transactions on Graphics. https://doi.org/10.1145/1399504.1360671.

    Article  Google Scholar 

  17. 17.

    Tarel, J. P., Hautiere, N., Caraffa, L., et al. (2012). Vision enhancement in homogeneous and heterogeneous fog. IEEE Intelligent Transportation Systems Magazine, 4(2), 6–20.

    Article  Google Scholar 

  18. 18.

    He, K., Jian, S., & Tang, X. (2009). Single image haze removal using dark channel prior. IEEE Conference on Computer Vision & Pattern Recognition. https://doi.org/10.1109/TPAMI.2010.168.

    Article  Google Scholar 

  19. 19.

    Jiang, Z. Y., Hu, Y., & Song, W. T. (2018). Improvement of fog removal method and effect analysis of dark channel remote sensing image. Shanghai Aerospace Journal, 35(04), 78–84.

    Google Scholar 

  20. 20.

    Wang, J. B., He, N., Zhang, L. L., et al. (2015). Single image de-haze with a physical model and dark channel prior. Neurocomputing. 149(PB), 718–728.

  21. 21.

    Long, J., Shi, Z. W., Tang, W., et al. (2013). Single remote sensing image de-haze. IEEE Geoscience & Remote Sensing Letters, 11(1), 59–63.

    Article  Google Scholar 

  22. 22.

    Li, Y., Miao, Q. G., Song, J. F., et al. (2016). Single image haze removal based on haze physical characteristics and adaptive sky region detection. Neurocomputing, 182(C), 221–234.

    Article  Google Scholar 

  23. 23.

    Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., et al. (2014). Generative adversarial nets. International Conference on Neural Information Processing Systems. MIT Press, 2014:2672-2680.

  24. 24.

    Creswell, A., White, T., Dumoulin, V., et al. (2017). Generative adversarial networks: an overview. IEEE Signal Processing Magazine, 35(1), 53–65.

    Article  Google Scholar 

  25. 25.

    Du, Y., & Li, X. (2018). Perceptually optimized generative adversarial network for single image de-haze. Computer Vision and Pattern Recognition, https://arxiv.org/abs/1805.01084. Accessed May 2018.

  26. 26.

    Isola, P., Zhu, J. Y., & Zhou, T. H. (2017). Image-to-image translation with conditional adversarial networks. Computer Vision and Pattern Recognition, 9(v3), 1125–1134.

    Google Scholar 

  27. 27.

    Qian, R., Tan, R. T., Yang, W. H., et al. (2018). Attentive generative adversarial network for raindrop removal from a single image. 2018 IEEE/CVFConference on Computer Vision and Pattern Recognition (CVPR), Meeting time: 01 June 2018. 

  28. 28.

    Fortuna, L., Manganaro, G., Muscato, G., & Nunnari, G. (1996). Parallel Simulation of Cellular Neural Networks. Computers & Electrical Engineering, 22(1), 61–84.

    Article  Google Scholar 

  29. 29.

    Horia, P., Bruls, T., & Newman, P. (2019). I can see clearly now: Image restoration via de-rainin. 2019 International Conference on Robotics and Automation (ICRA), Meeting time:12 August 2019.

  30. 30.

    He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision & Pattern Recognition.

  31. 31.

    Engin, D., Genç, A., & Ekenel, H. K. (2018). Cycle-dehaze: Enhanced cyclegan for single image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops  (pp. 825–833).

  32. 32.

    Ren, W. Q., Si, L., Hua, Z., et al. (2016). Single image dehazing via multi-scale convolutional neural networks. European conference on computer vision (pp. 154–169). Cham: Springer.

  33. 33.

    Korhonen, J., & You, J. (2012). Peak signal-to-noise ratio revisited: Is simple is beautiful? IEEE 4th Int. Quality of Multimedia Experience: Works.

    Google Scholar 

  34. 34.

    Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600–612.

    Article  Google Scholar 

Download references

Funding

This study was funded by [Doctoral Research Fund Project of Heilongjiang Institute of Technology (2017BJ15), Heilongjiang Science Foundation Project (LH2020F047), Heilongjiang Institute of Technology Innovation Team Project (2020CX07)]

Author information

Affiliations

Authors

Corresponding author

Correspondence to Xianhong Zhang.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhang, X. Research on Remote Sensing Image De‐haze Based on GAN. J Sign Process Syst (2021). https://doi.org/10.1007/s11265-021-01638-2

Download citation

Keywords

  • Machine learning
  • Deep learning
  • GAN
  • De‐haze