A Survey of Image Dehazing Algorithms

10.6919/ICJE.202205_8(5).0062

Ting Liu；Hejin Yuan

Image Dehazing ； Histogram Equalization ； Dark Channel Prior ； Atmospheric Scattering Model ； Convolutional Neural Network ； Generative Adversarial Network

International Core Journal of Engineering

8卷5期（2022 / 05 / 01）

485 - 492

英文

Image dehazing, as an important aspect in the field of image processing, is mainly aimed at restoring image details, improving image contrast, and improving recognizability. This paper mainly starts from two aspects: traditional defogging methods and deep learning dehazing methods. Traditional algorithms mainly include image enhancement algorithm and physical model algorithm, while deep learning dehazing algorithm mainly includes convolutional neural network based dehazing algorithm and generative adversative network dehazing algorithm. According to the developed algorithms, the advantages and disadvantages of each algorithm will be discussed and the future prospects will be pointed out.

1. Tan RT.Visibility in bad weather from a single image[C].Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2008. 1-8.
   連結：
2. He K, Sun J, Tang X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
   連結：
3. Zhu Q, Mai J, Shao L. A fast single image haze removal algorithm using color attenuation prior [J]. IEEE Transactions on Image Processing, 2015, 24(11): 3522-3533.
   連結：
4. Pizer S M, Amburn E P, Austin J D, et al. Adaptive histogram equalization and its variations[J]. Computer vision, graphics, and image processing, 1987, 39(3):355-368.
   連結：
5. Stark J A. Adaptive image contrast enhancement using generalizations of histogram equalization[J].IEEE Transactions on Image Processing, 2000, 9(5):889-896.
   連結：
6. Wang Hao, Zhang Ye, Shen Honghai, et al. Summary of image enhancement algorithms [J]. China Optics, 2017, 10 (4): 438-448.
   連結：
7. Cai B, Xu X, Jia K, et al. DehazeNet: An End-to-End System for Single Image Haze Removal[J]. IEEE Transactions on Image Processing,2016, 25(11):5187-5198.
   連結：
8. Zhang H, Patel V M. Densely connected pyramid dehazing network[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 3194-3203.
   連結：
9. Ren W, Liu S, Zhang H, et al. Single image dehazing via multi-scale convolutional neural networks[C]. Proceedings of the European Conference on Computer Vision, Cham: Springer, 2016. 15 4-169.
   連結：
10. Li B, Peng X, Wang Z, et al. AOD_Net: All-in-One Dehazing Network[C]. Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway, NJ: IEEE, 2017. 4770-4778.
    連結：
11. Dong H ,Pan J ,Xiang L , et al. Multi-Scale Boosted Dehazing Network with Dense Feature Fusion[J]. arXiv, 2020.
    連結：
12. Engin D, Genç A, Ekenel H K. Cycle-Dehaze: enhanced CycleGAN for single image dehazing[C], Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018: 825-833.
    連結：
13. Y. Dong, Y. Liu, H. Zhang, S. Chen, Y. Qiao. Fd-gan:generative adversarial networks with fusion-discriminator for single image dehazing. AAAI Conference on Artificial Intelligence, 2020, New York: 10729~10736.
    連結：
14. Ren W, Ma L, Zhang J,et al. Gated fusion network for single image dehazing[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018. 3253-3261.
    連結：
15. Narasimhan S G, Nayar S K. Interactive (de) weathering of an image using physical models[C]. Proceedings of the IEEE Workshop on color and photometric Methods in computer Vision. France, 2003, 6(6.4): 1.
16. LI G, YANG W n, WENG T. A method of removing thin cloud in remote sensing image based on the homomorphic filter algorithm[J]. Science of Surveying and Mapping, 2007, 3.
17. Journal of Computer Application Research] 2005, 22 (2): 235-237, Based on Retinex Theory.