Underwater Image Restoration Based on Red Channel and Haze-Lines Prior
Due to the scattering and absorption of light while it propagates in the water, underwater images often suffer from low contrast and color distortion. In order to solve this problem, we propose an underwater image restoration algorithm based on red channel and haze-lines prior in this paper. Firstly, the red channel prior is used to estimate veiling-light. Secondly, according to the characteristics of red channel attenuation in water, the attenuation ratio of red-blue channel and red-green channel are introduced to estimate the transmission by using haze-lines prior. Finally, the transmission is corrected by the red channel boundary constraint. In addition, for underwater artificial illumination, we introduce saturation as the low bound of the transmission estimation to reduce the impact of artificial light. The experimental results show that the proposed algorithm can restore image color information, improve image clarity and obtain better visual quality. The quantitative analysis indicates that the proposed algorithm performs well on a wide variety of underwater images and is competitive with other state-of-the-arts.
KeywordsUnderwater image restoration Red channel Haze-lines Saturation Artificial illumination Transmission
This work was partially supported by the National Key R&D Program of China (2018YFC0406903), the National Natural Science Foundation of China (No. 41706103) and the Natural Science Foundation of Jiangsu (No. BK20170306).
- 2.Hou, W., Gray, D.J., Weidemann, A.D., et al.: Automated underwater image restoration and retrieval of related optical properties. In: IEEE International Geoscience and Remote Sensing Symposium, pp. 1889–1892 (2008)Google Scholar
- 4.Sathya, R., Bharathi, M., Dhivyasri, G.: Underwater image enhancement by dark channel prior. In: International Conference on Electronics and Communication Systems, pp. 1119–1123 (2015)Google Scholar
- 5.Wen, H., Tian, Y., Huang, T., et al.: Single underwater image enhancement with a new optical model. In: IEEE International Symposium on Circuits and Systems, pp. 753–756 (2013)Google Scholar
- 8.Berman, D., Treibitz, T., Avidan, S.: Non-local image dehazing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1674–1682 (2016)Google Scholar
- 9.Berman, D., Treibitz, T., Avidan, S.: Diving into haze-lines: color restoration of underwater images. In: Proceedings of the British Machine Vision Conference (BMVC), vol. 1, no. 2 (2017)Google Scholar
- 10.Berman, D., Levy, D., Avidan, S., et al.: Underwater single image color restoration using haze-lines and a new quantitative dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), arxiv:1811.01343 (2018)
- 15.Jiang, Z.X., Pu, Y.: Underwater image color compensation based on electromagnetic theory. Laser Optoelectron. Prog. 55(08), 237–242 (2018)Google Scholar
- 16.Xie, H.L., Peng, G.H., Wang, F., et al.: Underwater image restoration based on background light estimation and dark channel prior. Acta Opt. Sinica 38(01), 18–27 (2018)Google Scholar