Home
 > 
ijmdsa
 > 
Review Article
—
Subscription Review Article

Artificial Intelligence Techniques for Image Dehazing: A Review

by 
   Gobinda Bauri,    Arun Kumar Jhapate,    Ritu Shrivastava,
Volume :  01 | Issue :  02 | Received :  March 15, 2024 | Accepted :  March 28, 2024 | Published :  April 30, 2024
DOI :  10.37591/IJMDSA

[This article belongs to International Journal of Mechanical Dynamics and Systems Analysis(ijmdsa)]

Keywords

Artificial Intelligence, Dehazing, Image, Blur, Deep learning, Multi-Scale

Abstract

This review explores the application of artificial intelligence (AI) techniques for image dehazing, addressing the pervasive challenge of enhancing image quality in hazy or foggy conditions. Traditional dehazing methods and their role as a foundation for AI-based approaches are discussed. Deep learning-based methods, including single-image and multi-image dehazing, are examined, highlighting their strengths and limitations. Data-driven approaches, leveraging large-scale datasets and domain adaptation, are also investigated. Furthermore, the review outlines the challenges in real-time processing, robustness, explainability, and real-world deployment of AI-based dehazing solutions. As AI technology advances, it is expected that image dehazing will find practical applications across various domains, making it essential to overcome the existing challenges to fully unlock its potential.

Full Text

References

  1. Zhao, L. Zhang, Y. Shen and Y. Zhou, “RefineDNet: A Weakly Supervised Refinement Framework for Single Image Dehazing,” in IEEE Transactions on Image Processing, vol. 30, pp. 3391-3404, 2021, doi: 10.1109/TIP.2021.3060873.
  2. Purkayastha, M. Choudhry and M. Kumar, “A Retinex Prior to Multi-Scale Fusion for Single Image Dehazing,” 2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON), New Delhi, India, 2023, pp. 646-651, doi: 10.1109/REEDCON57544.2023.10150567.
  3. Ling, H. Chen, X. Tan, Y. Jin and E. Chen, “Single Image Dehazing Using Saturation Line Prior,” in IEEE Transactions on Image Processing, vol. 32, pp. 3238-3253, 2023, doi: 10.1109/TIP.2023.3279980.
  4. P. Ajith, G. King and V. K, “Color Attenuation Prior Based Single Image Dehazing,” 2023 10th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India, 2023, pp. 654-658, doi: 10.1109/SPIN57001.2023.10116746.
  5. Qasim and G. Raja, “SPIDE-Net: Spectral Prior-Based Image Dehazing and Enhancement Network,” in IEEE Access, vol. 10, pp. 120296-120311, 2022, doi: 10.1109/ACCESS.2022.3221992.
  6. Li, C. Zheng, H. Shu and S. Wu, “Dual-Scale Single Image Dehazing via Neural Augmentation,” in IEEE Transactions on Image Processing, vol. 31, pp. 6213-6223, 2022, doi: 10.1109/TIP.2022.3207571.
  7. Imai and M. Ikehara, “Enhanced Multiscale Attention Network for Single Image Dehazing,” in IEEE Access, vol. 10, pp. 93626-93635, 2022, doi: 10.1109/ACCESS.2022.3204026.
  8. -H. Sheu, S. M. S. Morsalin, S. -H. Wang, Y. -T. Shen, S. -C. Hsia and C. -Y. Chang, “FIBS-Unet: Feature Integration and Block Smoothing Network for Single Image Dehazing,” in IEEE Access, vol. 10, pp. 71764-71776, 2022, doi: 10.1109/ACCESS.2022.3188860.
  9. Bie, S. Yang and Y. Huang, “Single Remote Sensing Image Dehazing Using Gaussian and Physics-Guided Process,” in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 3512405, doi: 10.1109/LGRS.2022.3177257.
  10. Li, H. Shu and C. Zheng, “Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids,” in IEEE Transactions on Image Processing, vol. 30, pp. 9270-9279, 2021, doi: 10.1109/TIP.2021.3123551.