Skip to main content
Springer Nature Link
Log in

Visible light polarization image desmogging via Cycle Convolutional Neural Network

  • Regular Paper
  • Published:
Multimedia Systems Aims and scope Submit manuscript

Abstract

Visible light polarization image desmogging aims to recover the clear image solely from an input visible light polarization image with smog. It is a challenging research topic due to desmogging is an ill-posed problem. Most of existing methods effort to build desmogging physical model based on classical atmospheric scattering principle. However, compared with natural image dehazing task, the smog in visible light polarization image is very complex and diverse, which makes it hard to find accurate desmogging physical model. To address this issue, we propose a Cycle Convolutional Neural Network (CCNN), which exploits polarization characteristics explicitly to learn a visible light polarization image desmogging model in an end-to-end way. To be specific, the model computes polarization information of the visible light polarization image via Stokes equation. Object detection sub-network is utilized to detect smog regions according to the polarization information. Then an encoder–decoder sub-network with feature converter structure is proposed to generate smog-free regions. The coarse clear image is obtained by fusing the generated smog-free regions with original smog visible light polarization image. More importantly, to obtain the final clear image, the coarse clear image is considered as the input data to our model again, which makes our model in a cycle topology. Moreover, we contribute the first large-scale dataset for visible light polarization image desmogging evaluation, which contains 17,216 visible light polarization images, to validate our proposed method. On this dataset, extensive experiments demonstrate that our method can achieve the best performance in comparison with the state-of-the-art baselines.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. Data is available at https://pan.baidu.com/s/1Z-imyNuL6sNIS8OoiHHVNg (passwd: iy2q).

References

  1. Wang, J., Wang, W., Wang, R., Gao, W.: Csps: An adaptive pooling method for image classification. IEEE Trans. Multimedia 18(6), 1000–1010 (2016)

    Article  Google Scholar 

  2. He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2010)

    Google Scholar 

  3. Zhang, W., Man, Z., Ge, X., Xing, F.: Fast dehazing method based on polarization optics. Laser Optoelectron. Prog. 56(14), 141103–1–141103–6 (2019)

    Google Scholar 

  4. Zhao, L., Gao, J., Bi, R., Fan, Z.: Polarization defogging method based on maximum and minimum intensity images. J. Appl. Opt. 38(3), 415–420 (2017)

    Google Scholar 

  5. Dai, Q., Fan, Z., Song, Q., Chen, Y.: Polarization and desmogging of color image based on automatic estimation of global parameters. J. Appl. Opt. 39(4), 511–517 (2015)

    Google Scholar 

  6. Shen, L., Zhao, Y., Peng, Q., Chan, J.C.-W., Kong, S.G.: An iterative image dehazing method with polarization. IEEE Trans. Multimedia 21(5), 1093–1107 (2018)

    Article  Google Scholar 

  7. Xia, P., Liu, X.-B.: Study on the polarization spectral image dehazing. Spectrosc. Spect. Anal. 37(8), 2331–2338 (2017)

    Google Scholar 

  8. Zhang, W., Ren, L., Xing, F., Zhang, F., Ge, X., Guomei, W., Shenggui, F.: Novel polarimetric dehazing method using discrete cosine transform based laplacian pyramid. Laser Optoelectron. Prog. 57(6), 061102–1–061102–7 (2020)

    Google Scholar 

  9. Xiao-ning, L., Yang-yang, L., Zheng, T., Qun-bo, L.: A polarizing universal multi-scale and real-time image defogging algorithm. Acta Photonica Sinica 48(8), 810003–0810003 (2019)

    Article  Google Scholar 

  10. Zhao, C., Duan, J., Li, G., Peng, J.: Polarization image defogging algorithm based on atmosphere scattering model. J. Changchun Univ. Sci. Technol. (Natural Science Edition) 03, 111–115 (2015)

  11. Narasimhan, S.G., Nayar, S.K.: Vision and the atmosphere. Int. J. Comput. Vis. 48(3), 233–254 (2002)

    Article  Google Scholar 

  12. Mei, K., Jiang, A., Li, J., Wang, M.: Progressive feature fusion network for realistic image dehazing, in: Asian conference on computer vision, Springer, pp. 203–215 (2018)

  13. Yu-Long, Y., Sun, X.-B., Song, M.-X., Chen, W., Chen, F.-N.: Phase delay error analysis of wave plate of division-of-amplitude full stokes simultaneous polarization imaging system. Acta Physica Sinica 68(2), 024203–1–024203–12 (2019)

    Google Scholar 

  14. McCartney, E.J.: Optics of the atmosphere: scattering by molecules and particles. Physics Today 30(5), 76 (1977).

  15. Zhang, S., Zhan, J., Fu, Q., Duan, J.: Polarization detection defogging technology based on multi-wavelet fusion. Laser Optoelectron. Prog. 55(12), 122602–1–122602–7 (2018)

    Google Scholar 

  16. Hu, H., Zhao, L., Li, X., Wang, H., Yang, J., Li, K., Liu, T.: Polarimetric image recovery in turbid media employing circularly polarized light. Opt. Express 26(19), 25047–25059 (2018)

    Article  Google Scholar 

  17. Ju, H., Liang, J., Zhang, W., Bai, Z., Ren, L., Qu, E.: Simultaneous, real-time, chromatic polarimetric imaging technology with full-polarization-state detection. J. Infrared Millim. Waves 36(6), 744–748 (2017)

    Google Scholar 

  18. Hui, W., Jin, W., Xiaobo, L., Haofeng, H., Tiegen, L.: Optimization for a polarimetic dehazing imaging method based on the circularly polarized light. Infrared Laser Eng. 48(11), 1126001–1126001 (2019)

    Article  Google Scholar 

  19. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012)

    Google Scholar 

  20. Gao, J., Xu, C.: Ci-gnn: Building a category-instance graph for zero-shot video classification. IEEE Trans. Multimedia 22(12), 3088–3100 (2020)

    Article  MathSciNet  Google Scholar 

  21. Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., Yang, M.-H.: Multi-scale boosted dehazing network with dense feature fusion, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2157–2167 (2020)

  22. Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2016)

    Article  Google Scholar 

  23. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016)

  24. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. IEEE Conf. Comput. Vis. Pattern Recogn. 2009, 248–255 (2009)

    Google Scholar 

  25. Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., Sun, J.: You only look one-level feature, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2021)

  26. Romano, Y., Elad, M.: Boosting of image denoising algorithms. SIAM J. Imaging Sci. 8(2), 1187–1219 (2015)

    Article  MathSciNet  Google Scholar 

  27. Afouras, T., Chung, J. S., Zisserman, A.: My lips are concealed: Audio-visual speech enhancement through obstructions, arXiv preprint arXiv:1907.04975

  28. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980

  29. Jun, G., Bi, R., Zhao, L., Fan, Z.: Global optimized hazed image reconstruction based onpolarization information. Opt. Precis. Eng. 25(8), 2212–2220 (2017)

    Article  Google Scholar 

  30. Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: Aod-net: All-in-one dehazing network, in: Proceedings of the IEEE international conference on computer vision, pp. 4770–4778 (2017)

  31. Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., Yang, M.-H.: Gated fusion network for single image dehazing, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3253–3261 (2018)

  32. Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: Dehazenet: an end-to-end system for single image haze removal. IEEE Trans. Image Process. 25(11), 5187–5198 (2016)

    Article  MathSciNet  Google Scholar 

  33. Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks, In: Proceedings of the IEEE international conference on computer vision, pp. 2223–2232 (2017)

  34. Liu, X., Ma, Y., Shi, Z., Chen, J.: Griddehazenet: Attention-based multi-scale network for image dehazing, In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7314–7323 (2019)

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

Download references

Acknowledgements

This work was partially supported by the National Natural Science Foundation (NSF) of China (No. 61902104), the University Synergy Innovation Program of Anhui Province (No. GXXT-2019-048), the Anhui Provincial Natural Science Foundation (No. 2008085QF295) and the Talent Research Foundation of Hefei University (No. 18-19RC54), the Anhui Provincial Natural Science Foundation of China (No. 1908085J25), Key Laboratory of Polarization Imaging Detection Technology Anhui Province (No. 2019KJS030009), and Natural Science Foundation of Anhui Province (No. 1808085MF209).

Author information

Author notes

  1. Jingjing Zhang and Xin Zhang these authors contributed equally to the paper as first authors.

Authors and Affiliations

  1. Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China

    Jingjing Zhang, Xin Zhang, Teng Li, Yuzhou Zeng & Fudong Nian

  2. Key Laboratory of Polarized Light Imaging and Detection Technology in Anhui Province, Hefei, China

    Jingjing Zhang & Teng Li

  3. School of Advanced Manufacturing Engineering, Hefei University, Hefei, China

    Gang Lv & Fudong Nian

Authors
  1. Jingjing Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xin Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Teng Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yuzhou Zeng
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Gang Lv
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Fudong Nian
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Fudong Nian.

Additional information

Communicated by J. Gao.

Publisher's Note

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

Appendix (Additional qualitative examples)

Appendix (Additional qualitative examples)

To demonstrate that our model achieves robust and superior performance on different scenes, we visualize more examples (Fig. 9) on the constructed dataset using the proposed method.

Fig. 9
figure 9

Visible light polarization image desmogging results in our dataset

Full size image

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, J., Zhang, X., Li, T. et al. Visible light polarization image desmogging via Cycle Convolutional Neural Network. Multimedia Systems 28, 45–55 (2022). https://doi.org/10.1007/s00530-021-00802-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00530-021-00802-9

Keywords