Skip to main content
SpringerLink
Log in

Semi-supervised dehazing network using multiple scattering model and fuzzy image prior

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

In haze scenes, light is scattered and absorbed thus affecting the acquisition of information. However, existing image enhancement methods have limited capabilities and it is challenging to truly eliminate haze. As a result, their application to advanced vision is seriously hindered. The advantages of a prior based methods and physical models are ignored by existing deep learning-based methods. To address this problem, a novel semi-supervised learning architecture is proposed. Supervised and unsupervised branches are used simultaneously by this semi-supervised defogging network and trained on both labelled and unlabeled datasets. The contribution of this algorithm is the use of atmospheric multiple scattering model in the semi-supervised de-fogging network, which can well solve the blurring and haloing caused by multiple scattering of light. A blurred image prior is proposed for the first time, and the blurring kernel of the fogged image is solved by this prior information, which simplified the application of atmospheric multiple scattering models. In the semi-supervised defogging algorithm, a supervised loss function is used to constrain the supervised branch and an unsupervised loss is used to constrain the unsupervised branch. Some weights in the supervised and unsupervised branches are shared in order for the network model to learn the feature information of both synthetic and real images. The experiment shows that compared with the latest nine algorithms, the proposed method achieves better results on synthetic and real images.

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

Access this article

Log in via an institution

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
Algorithm 1
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Data availability

Data will be made available on request.

References

  1. Bekkerman I, Tabrikian J (2006) Target detection and localization using MIMO radars and sonars. IEEE Trans Signal Process 54(10):3873–3883

    Google Scholar 

  2. Gevers T, Smeulders AWM (1999) Color-based object recognition. Pattern Recogn 32(3):453–464

    Google Scholar 

  3. Minaee S, Boykov Y, Porikli F et al (2021) Image segmentation using deep learning: A survey [J]. IEEE transactions on pattern analysis and machine intelligence 44(7):3523–3542

    Google Scholar 

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

    Google Scholar 

  5. Zhu Q, Mai J, Shao L (2015) A fast single image haze removal algorithm using color attenuation prior. IEEE Trans Image Process 24(11):3522–3533

    MathSciNet  Google Scholar 

  6. Cai B, Xu X, Jia K (2016) Dehazenet: An end-to-end system for single image haze removal. IEEE Trans Image Process 25(11):5187–5198

    MathSciNet  Google Scholar 

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

  8. Chen D, He M, Fan Q (2019) Gated context aggregation network for image dehazing and deraining, in 2019 IEEE winter conference on applications of computer vision (WACV). IEEE 2019:1375–1383

    Google Scholar 

  9. Qin X, Wang Z, Bai Y, Xie X, Jia H (2020) FFA-Net: Feature fusion attention network for single image dehazing. In Proceedings of the AAAI conference on artificial intelligence 34(07):11908–11915

    Google Scholar 

  10. Nayar SK, Narasimhan SG (1999) Vision in bad weather. In: Proceedings of the seventh IEEE international conference on computer vision. IEEE 2:820–827

  11. Narasimhan SG, Nayar SK (2003) Shedding light on the weather. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. IEEE 1:I–I

  12. Li C, Guo C, Guo J, Han P, Fu H, Cong R (2019) PDR-Net: Perception-inspired single image dehazing network with refinement. IEEE Transn Multimedia 22(3):704–716

    Google Scholar 

  13. Fang F, Wang T, Wang Y, Zeng T, Zhang G (2019) Variational single image dehazing for enhanced visualization. IEEE Trans Multimedia 22(10):2537–2550

    Google Scholar 

  14. Li J, Li Y, Zhuo L, Kuang L, Yu T (2022) USID-Net: unsupervised single image dehazing network via disentangled representations. IEEE Trans Multimedia

  15. Lin C, Rong X, Yu X (2022) Msaff-net: multiscale attention feature fusion networks for single image dehazing and beyond. IEEE Trans Multimedia

  16. Yi Q, Li J, Fang F, Jiang A, Zhang G (2021) Efficient and accurate multi-scale topological network for single image dehazing. IEEE Trans Multimedia 24:3114–3128

    Google Scholar 

  17. Golts A, Freedman D, Elad M (2019) Unsupervised single image dehazing using dark channel prior loss. IEEE Trans Image Process 29:2692–2701

    Google Scholar 

  18. Li L, Dong Y, Ren W, Pan J, Gao C, Sang N, Yang MH (2019) Semi-supervised image dehazing. IEEE Trans Image Process 29:2766–2779

    Google Scholar 

  19. Chen Y, Xia R, Zou K et al (2023) FFTI: Image inpainting algorithm via features fusion and two-steps inpainting[J]. J Vis Commun Image Represent 91:103776

    Google Scholar 

  20. Chen Y, Xia R, Yang K, Zou K (2024) MFFN: image super-resolution via multi-level features fusion network. Vis Comput 40(2):489–504

  21. Chen Y, Xia R, Zou K, Yang K (2023) RNON: image inpainting via repair network and optimization network. Int J Mach Learn Cybern 14(9):2945–2961

  22. Chen Y, Xia R, Yang K, Zou K (2023) DGCA: high resolution image inpainting via DR-GAN and contextual attention. Multimed Tools Appl 82(30):47751–47771

    Google Scholar 

  23. Chen Y, Xia R, Yang K et al (2023) DARGS: Image inpainting algorithm via deep attention residuals group and semantics[J]. J King Saud Univ Comput Inf Sci 35(6):101567

    Google Scholar 

  24. An S, Huang X, Wang L et al (2022) Semi-supervised image dehazing network[J]. Vis Comput 38(6):2041–2055

    Google Scholar 

  25. An S, Huang X, Zheng Z et al (2021) An end-to-end sea fog removal network using multiple scattering model[J]. PLoS ONE 16(5):e0251337

    Google Scholar 

  26. Song Y, He Z, Qian H et al (2023) Vision transformers for single image dehazing[J]. IEEE Trans Image Process 32:1927–1941

    Google Scholar 

  27. Yang Y, Wang C, Liu R, Zhang L, Guo X, Tao D (2022) Self-augmented unpaired image dehazing via density and depth decomposition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2037–2046

  28. Liu H, Wu Z, Li L, Salehkalaibar S, Chen J, Wang K (2022) Towards multi-domain single image dehazing via test-time training. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5831–5840

  29. Wang R, Li R, Sun H (2016) Haze removal based on multiplescattering model with superpixel algorithm. Signal Process 127:24–36

    Google Scholar 

  30. Yin JL, Huang YC, Chen BH, Ye SZ (2019) Color transferred convolutional neural networks for image dehazing. IEEE Trans Circuits Syst Video Technol 30(11):3957–3967

    Google Scholar 

  31. Zhao D, Xu L, Ma L, Li J, Yan Y (2020) Pyramid global context network for image dehazing. IEEE Trans Circuits Syst Video Technol 31(8):3037–3050

    Google Scholar 

  32. Nie J, Pang Y, Xie J, Pan J, Han J (2021) Stereo refinement dehazing network. IEEE Trans Circuits Syst Video Technol 32(6):3334–3345

    Google Scholar 

  33. Wang P, Zhu H, Huang H, Zhang H, Wang N (2021) TMSGAN: a twofold multi-scale generative adversarial network for single image dehazing. IEEE Trans Circuits Syst Video Technol 32(5):2760–2772

    Google Scholar 

  34. Zhou Y, Chen Z, Li P et al (2022) FSAD-Net: feedback spatial attention dehazing network[J]. IEEE Trans Neural Networks Learn Syst

  35. Liu R, Fan X, Hou M, Jiang Z, Luo Z, Zhang L (2018) Learning aggregated transmission propagation networks for haze removal and beyond. IEEE Trans Neural Networks Learn Syst 30(10):2973–2986

    Google Scholar 

  36. Chen BH, Huang SC, Li CY (2017) Haze removal using radial basis function networks for visibility restoration applications. IEEE IEEE Trans Neural Networks Learn Syst 29(8):3828–3838

    Google Scholar 

  37. Protas E, Bratti JD, Gaya JFO (2018) Visualization methods for image transformation convolutional neural networks. IEEE Trans. Neural Networks Learn Syst 30(7):2231–2243

    Google Scholar 

  38. Song Y, Li J, Wang X (2017) Single image dehazing using ranking convolutional neural network. IEEE Trans Multimedia 20(6):1548–1560

    Google Scholar 

  39. Zhang J, Tao D (2020) FAMED-Net: a fast and accurate multi-scale end-to-end Dehazing Network. IEEE Trans Image Process 29:72–84

    MathSciNet  Google Scholar 

  40. Zhang S, Ren W, Yao J (2018) Feed-Net: fully End-to-End Dehazing In: IEEE International Conference on Multimedia and Expo (ICME) 2018:1–6

    Google Scholar 

  41. Zhang H, Sindagi V (2019) Patel V M. Joint transmission map estimation and dehazing using deep networks. IEEE Trans Circuits Syst Video Technol 30(7):1975–1986

    Google Scholar 

  42. Li R, Pan J, Li Z, Tang J (2018) Single image dehazing via conditional generative adversarial network. In: Proc IEEE Conf Comput Vis Pattern Recognit pp 8202–8211

  43. Liu W, Hou X, Duan J (2020) End-to-end single image fog removal using enhanced cycle consistent adversarial networks. IEEE Trans Image Process 29:7819–7833

    Google Scholar 

  44. Wei W, Meng D, Zhao Q, Xu Z, Wu Y (2019) Semi-supervised transfer learning for image rain removal. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3877–3886

  45. Yang X, Xu Z, Luo J (2018) Towards perceptual image dehazing by physics-based disentanglement and adversarial training. In: Proceedings of the AAAI conference on artificial intelligence 32(1)

  46. Bilgic B, Chatnuntawech I, Fan AP et al (2014) Fast image reconstruction with L2-regularization[J]. J Magn Reson Imaging 40(1):181–191

    Google Scholar 

  47. Allen DM (1971) Mean square error of prediction as a criterion for selecting variables. Technometrics 13(3):469–475

    Google Scholar 

  48. Wang Y, Zhuo S, Tao D (2013) Automatic local exposure correction using bright channel prior for under-exposed images. Signal Process 93(11):3227–3238

    Google Scholar 

  49. PRIOR IUBC (2013) Single image de-haze under non-uniformillumination using bright channel prior. J Theor Appl Inf Technol 48(3):1843–1848

    Google Scholar 

  50. Li B, Ren W, Fu D (2018) Benchmarking single-image dehazing and beyond. IEEE Trans Image Process 28(1):492–505

    MathSciNet  Google Scholar 

  51. Prasad NGN, Rao JNK (1990) The estimation of the mean squared error of small-area estimators. J Am Stat Assoc 85(409):163–171

    MathSciNet  Google Scholar 

  52. Fienup JR (1997) Invariant error metrics for image reconstruction. Appl Opt 36(32):8352–8357

    Google Scholar 

  53. Huynh-Thu Q, Ghanbari M (2008) Scope of validity of PSNR in image/video quality assessment. Electron Lett 44(13):800–801

    Google Scholar 

  54. Wang Z, Bovik AC, Sheikh HR (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612

    Google Scholar 

  55. Zhang L, Zhang L, Mou X (2011) FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process 20(8):2378–2386

    MathSciNet  Google Scholar 

  56. Choi LK, You J, Bovik AC (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans Image Process 24(11):3888–3901

    MathSciNet  Google Scholar 

  57. Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708

    MathSciNet  Google Scholar 

  58. Venkatanath N, Praneeth D, Bh MC, Channappayya SS, Medasani SS (2015) Blind image quality evaluation using perception based features. In: 2015 twenty first national conference on communications (NCC), pp 1–6. IEEE

  59. Mittal A, Soundararajan R, Bovik AC (2012) Making a “completely blind” image quality analyzer. IEEE Signal Process Lett 20(3):209–212

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China

    Shunmin An

  2. Shanghai Engineering Research Center of Intelligent Maritime Search and Rescue and Underwater Vehicles, Shanghai Maritime University, Shanghai, China

    Linling Wang

  3. Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai, China

    Le Wang

Authors
  1. Shunmin An
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Linling Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Le Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Shunmin An: Conceptualization, Methodology, Software, Investigation, Formal Analysis, Writing; Linling Wang: Data Curation, Writing; Le Wang: Visualization, Investigation.

Corresponding author

Correspondence to Shunmin An.

Ethics declarations

Ethics approval and consent to participate

This articlsse does not contain any studies with human participants or animals performed by any of the authors.

Conflict of interests

All the authors certify that there is no conflict of interest with any individual or organization for the present work.

Additional information

Publisher's note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

An, S., Wang, L. & Wang, L. Semi-supervised dehazing network using multiple scattering model and fuzzy image prior. Appl Intell 54, 5794–5812 (2024). https://doi.org/10.1007/s10489-024-05443-9

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-024-05443-9

Keywords

Search

Navigation