Skip to main content
SpringerLink
Log in

Dynamic Feature Attention Network for Remote Sensing Image Dehazing

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In recent years, deep learning-based methods for remote sensing image dehazing have achieved remarkable progress, especially with the incorporation of attention mechanisms to enhance feature learning. However, the channel attention method uses global average pooling to aggregate feature information, which makes it sensitive to specific points of influence. In particular, remote sensing images are captured in a wide range, and are more likely to have special points such as abrupt color changes and confusing landscapes within the images. This paper proposes a dynamic feature attention network (DFA-Net) that includes a dynamic channel module and a pixel attention module to address this challenge. The dynamic channel attention module adds a network branche to learn the weight of spatial information and dynamically aggregates features to reduce the influence from outliers such as color mutations and improve the defogging effect. The pixel attention module is also added to learn the importance of different pixels and enhance the feature extraction capability. Experiments on several datasets have shown that DFA-Net is suitable for remote sensing image dehazing in various scenes, and has achieved the best dehazing performance.

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

Similar content being viewed by others

References

  1. Berman D, Treibitz T, Avidan S (2016) Non-local image dehazing. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR)

  2. Bi G, Ren J, Tianjiao F, Nie T, Chen C, Zhang N (2017) Image dehazing based on accurate estimation of transmission in the atmospheric scattering model. IEEE Photonics J 9(4):1–18

    Article  Google Scholar 

  3. Chen D, He M, Fan Q, Liao J, Zhang L, Hou D, Yuan L, Hua G (2019) Gated context aggregation network for image dehazing and deraining. In: 2019 IEEE winter conference on applications of computer vision (WACV), pp 1375–1383

  4. Chen X, Li Y, Dai L, Kong C (2021) Hybrid high-resolution learning for single remote sensing satellite image dehazing. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  5. Cox LJ (1977) Optics of the atmosphere-scattering by molecules and particles. Optica Acta Int J Optics 24:779–779

    Article  Google Scholar 

  6. Dharejo FA, Zhou Y, Deeba F, Jatoi MA, Khan MA, Mallah GA, Ghaffar A, Chhattal M, Du Y, Wang X (2021) A deep hybrid neural network for single image dehazing via wavelet transform. Optik 231:166462

    Article  Google Scholar 

  7. Dong H, Pan J, Xiang L, Hu Z, Yang MH (2020) Multi-scale boosted dehazing network with dense feature fusion. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR)

  8. Dong P, Wang B (2022) Transra: transformer and residual attention fusion for single remote sensing image dehazing. Multidimens Syst Signal Process 33(4):1119–1138

    Article  Google Scholar 

  9. Duan Y, Luo F, Fu M, Niu Y, Gong X (2023) Classification via structure preserved hypergraph convolution network for hyperspectral image. IEEE Trans Geosci Remote Sens 61:1–3

    Article  Google Scholar 

  10. Grohnfeldt C, Schmitt M, Zhu X (2018) A conditional generative adversarial network to fuse SAR and multispectral optical data for cloud removal from sentinel-2 images. In: IGARSS 2018-2018 ieee international geoscience and remote sensing symposium, pp 1726–1729

  11. Gu Z, Zhan Z, Yuan Q, Yan L (2019) Single remote sensing image dehazing using a prior-based dense attentive network. Remote Sens 11(24):3008

    Article  Google Scholar 

  12. Guo J, Yang J, Yue H, Tan H, Hou C, Li K (2020) Rsdehazenet: Dehazing network with channel refinement for multispectral remote sensing images. IEEE Trans Geosci Remote Sens 59(3):2535–2549

    Article  Google Scholar 

  13. He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33:2341–2353

    Article  Google Scholar 

  14. Hu A, Xie Z, Xu Y, Xie M, Qiu Q (2020) Unsupervised haze removal for high-resolution optical remote-sensing images based on improved generative adversarial networks. Remote Sens 12(24):4162

    Article  Google Scholar 

  15. Jiang B, Chen G, Wang J, Ma H, Wang L, Wang Y, Chen X (2021) Deep dehazing network for remote sensing image with non-uniform haze. Remote Sens 3(21):4443

    Article  Google Scholar 

  16. Jiang H, Ning L (2018) Multi-scale residual convolutional neural network for haze removal of remote sensing images. Remote Sens 10(6):945

    Article  Google Scholar 

  17. Hu J, Shen L, Sun G (2019) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023

    Article  Google Scholar 

  18. Kussul N, Lavreniuk M, Skakun S, Shelestov A (2017) Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci Remote Sens Lett 14(5):778–782

    Article  Google Scholar 

  19. Li B, Peng X, Wang Z, Xu J, Dan F (2017) Aod-net: All-in-one dehazing network. In: 2017 IEEE international conference on computer vision (ICCV)

  20. Liu Q, Gao X, He L, Wen L (2017) Haze removal for a single visible remote sensing image. Signal Process 137:33–43

    Article  Google Scholar 

  21. Liu X, Ma Y, Shi Z, Chen J (2020) Griddehazenet: Attention-based multi-scale network for image dehazing. In: 2019 IEEE/CVF international conference on computer vision (ICCV)

  22. Luo F, Zhou T, Liu J, Guo T, Gong X, Ren J (2023) Multiscale diff-changed feature fusion network for hyperspectral image change detection. IEEE Trans Geosci Remote Sens 61:1–13

    Article  Google Scholar 

  23. Mehta A, Sinha H, Mandal M, Narang P (2021) Domain-aware unsupervised hyperspectral reconstruction for aerial image dehazing. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 413–422

  24. 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 34:11908–11915

  25. Qin Z, Ni L, Tong Z, Qian W (2015) Deep learning based feature selection for remote sensing scene classification. IEEE Geosci Remote Sens Lett 12:1–5

    Google Scholar 

  26. Rong Z, Jun WL (2014) Improved wavelet transform algorithm for single image dehazing. Optik 125(13):3064–3066

    Article  Google Scholar 

  27. Shrivastava A, Jain S (2016) Single image dehazing based on one dimensional linear filtering and adoptive histogram equalization method. In: 2016 international conference on electrical, electronics, and optimization techniques (ICEEOT), IEEE, pp 4074–4078

  28. Song Y, He Z, Qian H, Du X (2022) Vision transformers for single image dehazing. In arXiv preprint arXiv:2204.03883,

  29. Thanh DN, Hue NM, Prasath VS (2019) Single image dehazing based on adaptive histogram equalization and linearization of gamma correction. In: 2019 25th Asia-Pacific conference on communications (APCC), pp 36–40

  30. Yixuan T, Jia K, Wei X, Yunjun Yao M, Xia XZ, Jiang B (2020) A time-efficient fractional vegetation cover estimation method using the dynamic vegetation growth information from time series glass fvc product. IEEE Geosci Remote Sens Lett 17(10):1672–1676

    Article  Google Scholar 

  31. Tu Z, Talebi H, Zhang H, Yang F, Milanfar P, Bovik A, Li Y (2022) Maxim: Multi-axis mlp for image processing. In: CVPR conference on computer vision and pattern recognition

  32. Tufail Z, Khurshid K, Salman A, Nizami IF, Khurshid K, Jeon B (2018) Improved dark channel prior for image defogging using RGB and YcbCr color space. IEEE Access 6:32576–32587

    Article  Google Scholar 

  33. Wang H, Cao H, Kai Y, Bai H, Chen X, Yang Y, Xing L, Zhou C (2022) Multi-source remote sensing intelligent characterization technique-based disaster regions detection in high-altitude mountain forest areas. IEEE Geosci Remote Sens Lett 19:1–5

    Google Scholar 

  34. Woo S, Park J, Lee JY, Kweon IS (2018) Cbam: Convolutional block attention module. In: European conference on computer vision

  35. Xu X, Ma Y, Sun W (2020) Learning factorized weight matrix for joint filtering. In: International conference on machine learning, PMLR, pp 10587–10596

  36. Xiangyu X, Ma Y, Sun W, Yang M-H (2020) Exploiting raw images for real-scene super-resolution. IEEE Trans Pattern Anal Mach Intell 44(4):1905–1921

    Google Scholar 

  37. Zhang L, Song L, Bo D, Zhang Y (2019) Nonlocal low-rank tensor completion for visual data. IEEE Trans Cybern 51(2):673–685

    Article  Google Scholar 

  38. Zhang QL, Yang YB (2021) Sa-net: Shuffle attention for deep convolutional neural networks. In: ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 2235–2239

  39. Zhang X, Wang T, Wang J, Tang G, Zhao L (2020) Pyramid channel-based feature attention network for image dehazing. Comput Vis Image Underst 197:103003

    Article  Google Scholar 

  40. Zhao L, Tang P, Huo L (2016) Feature significance-based multibag-of-visual-words model for remote sensing image scene classification. J Appl Remote Sens 10(3):035004–035004

    Article  Google Scholar 

  41. Zhao L, Zhang Y, Cui Y (2022) An attention encoder-decoder network based on generative adversarial network for remote sensing image dehazing. IEEE Sens J 22(11):10890–10900

    Article  Google Scholar 

  42. Zheng M, Qi G, Zhu Z, Li Y, Wei H, Liu Yu (2020) Image dehazing by an artificial image fusion method based on adaptive structure decomposition. IEEE Sens J 20(14):8062–8072

    Article  Google Scholar 

  43. Zheng Y, Jia S, Zhang S, Tao M, Wang L (2022) Dehaze-aggan: unpaired remote sensing image dehazing using enhanced attention-guide generative adversarial networks. IEEE Trans Geosci Remote Sens 60:1–13

    Article  Google Scholar 

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

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Control Science and Engineering, China University of Petroleum (East China), Qingdao, China

    Yang Hao, Weifeng Liu & Baodi Liu

  2. College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao, China

    Wenzong Jiang

  3. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China

    Weijia Cao

Authors
  1. Yang Hao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wenzong Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Weifeng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Weijia Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Baodi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Yang Hao, Wenzong Jiang, and Baodi Liu wrote the main manuscript parts. Weifeng Liu and Weijia Cao made comments and changes. All authors reviewed the manuscript.

Corresponding author

Correspondence to Baodi Liu.

Ethics declarations

Conflict of Interest

The authors declare no conflict of interests.

Additional information

Publisher's Note

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

The work was supported by the Natural Science Foundation of Shandong Province, China (Grant No. ZR2019MF073), the Fundamental Research Funds for the Central Universities, China University of Petroleum (East China) (Grant No. 20CX05001A), the Major Scientific and Technological Projects of CNPC (No. ZD2019-183-008), the Creative Research Team of Young Scholars at Universities in Shandong Province (No. 2019KJN019).

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

Hao, Y., Jiang, W., Liu, W. et al. Dynamic Feature Attention Network for Remote Sensing Image Dehazing. Neural Process Lett 55, 8081–8094 (2023). https://doi.org/10.1007/s11063-023-11301-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-023-11301-5

Keywords

Search

Navigation