Abstract
Underwater images often suffer from blurry details, color distortion, and low contrast due to light absorption and scattering in water. Existing restoration technologies use a fixed attenuation coefficient value, which fails to account for the uncertainty of the water body and leads to suboptimal restoration results. To address these issues, we propose a scene depth fusion model that considers underwater light attenuation to obtain a more accurate attenuation coefficient for image restoration. Our method employs the quadtree decom-position method and a depth map to estimate the background light. We then fuse and refine the depth map, compute the attenuation coefficient of the water medium for a more precise transmission map, and apply a reversed underwater imaging model to restore the image. Experiments demonstrate that our method effectively enhances the details and colors of underwater images while improving the contrast. Moreover, our method outperforms several state-of-the-art methods in terms of both accuracy and quality, showing its superior performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lu, H., Li, Y., Zhang, L., et al.: Contrast enhancement for images in turbid water. JOSA A 32(5), 886–893 (2016)
Serikawa, S., Lu, H.: Underwater image dehazing using joint trilateral filter. Comput. Electr. Eng. 40(1), 41–50 (2014)
Zhou, J., Zhang, D., Zhang, W.: A multifeature fusion method for the color distortion and low contrast of underwater images. In: Multimedia Tools and Applications, pp. 17515–41 (2021)
Jerlov, N.G.: Marine Optics, vol. 14. Elsevier, Amsterdam (1976)
Zhou, J., Zhang, D., Zhang, W.: Underwater image enhancement method via multi-feature prior fusion. Appli. Intell., 16435–16457 (2022)
Ancuti, C.O., Ancuti, C., De Vleeschouwer, C., Bekaert, P.: Color balance and fusion for underwater image enhancement. IEEE Trans. Image Process. 27(1), 379–393 (2018)
Zhang, W., Zhuang, P., Sun, H.H., et al.: Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement. IEEE Trans. Image Process., 3997–4010 (2022)
McCartney, E.J.: Optics of the Atmosphere: Scattering by Molecules and Particles. Wiley, New York, USA (1976)
He, K., Sun, J., Tang X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell., 2341–53 (2010)
Song, W., Wang, Y,, Huang, D., Tjondronegoro D.: A rapid scene depth estimation model based on underwater light attenuation prior for underwater image restoration. In: Pacific Rim Conference on Multimedia, pp.678–88. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00776-8_62
Akkaynak, D., Treibitz, T.: A revised underwater image formation model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6723–6732 (2018)
Lu, H., Wang, D., Li, Y., et al.: CONet: a cognitive ocean network. IEEE Wireless Commun 26(3), 90–96 (2019)
Horimachi, R., Lu, H., Zheng, Y., et al.: Underwater image super-resolution using improved SRCNN. In: International Symposium on Artificial Intelligence and Robotics 2022, vol. 12508, pp. 87–102. SPIE (2022)
Dai, C., Lin, M., Wu X.: Single underwater image restoration by decomposing curves of attenuating color. Optics Laser Technol. (2020)
Zhou, J., Yang, T., Chu, W., et al.: Underwater image restoration via backscatter pixel prior and color compensation. In: Engineering Applications of Artificial Intelligence (2022)
Onoyama, T., Lu, H., Soomro, A.A., et al.: Image quality improvement using local adaptive neighborhood-based dark channel prior. In: International Symposium on Artificial Intelligence and Robotics 2021, vol. 11884, pp. 191–195. SPIE (2021)
Gould, R.W., Arnone, R.A., Martinolich,. P.M.: Spectral dependence of the scattering coefficient in case 1 and case 2 waters. Appl. Opt., 2377–2383 (1999)
Chiang, J.Y., Chen, Y.-C.: Underwater image enhancement by wavelength compensation and dehazing. IEEE Trans. Image Process., 1756–1769 (2012)
Liu, K., Liang, Y.: Enhancement of underwater optical images based on background light estimation and improved adaptive transmission fusion. Optics Express 29(18), 28307–28328 (2021)
Chao, L., Wang, M.: Removal of water scattering. In: 2010 2nd International Conference on Computer Engineering and Technology. IEEE (2010)
Carlevaris-Bianco, N., Mohan, A., Eustice, R.M.: Initial results in underwater single image dehazing. In: OCEANS 2010 MTS/IEEE SEATTLE, USA, Seattle, WA, pp. 1–8 (2010)
Lu, H., Li, Y., Zhang, Y., et al.: Underwater optical image processing: a comprehensive review. Mobile Netw. Appli. 22, 1204–1211 (2017)
Carlevaris-Bianco, N., Mohan, A., Eustice, R.M.: Initial results in underwater single image dehazing. In: Proceedings of IEEE Oceans, pp.1–8 (Sep 2010)
Drews Jr., P., do Nascimento, E., Moraes, F., Botelho, S., Campos, M.: Transmission estimation in underwater single images. In: 2013 IEEE International Conference on Computer Vision Workshops, Australia, Sydney, NSW, pp. 825–830 (2013)
Li, Y., Lu, H., Li, J., et al. Underwater image de-scattering and classification by deep neural network. Comput. Elect. Eng. 54, 68–77 (2016)
Berman, D., Levy, D., Avidan, S., Treibitz, T.: Underwater single image color restoration using haze-lines and a new quantitative dataset. IEEE Trans. Pattern Anal. Mach. Intell. 43(8) 2822–2837 (2021)
Li, C., Guo, C., Ren, W., et al.: An underwater image enhancement benchmark dataset and beyond. IEEE Trans. Image Process. 29, 4376–4389 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, X., Li, Y., Lu, H. (2023). Underwater Image Restoration Based on Light Attenuation Prior and Scene Depth Fusion Model. In: Lu, H., Blumenstein, M., Cho, SB., Liu, CL., Yagi, Y., Kamiya, T. (eds) Pattern Recognition. ACPR 2023. Lecture Notes in Computer Science, vol 14406. Springer, Cham. https://doi.org/10.1007/978-3-031-47634-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-47634-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47633-4
Online ISBN: 978-3-031-47634-1
eBook Packages: Computer ScienceComputer Science (R0)