Abstract
In recent years, underwater image processing has been a hot topic in machine vision, especially for underwater robots. A key part of underwater image processing is underwater image restoration. However, underwater image restoration is an essential but challenging task in the field of image processing. In this article, we propose an underwater image restoration framework based on physical priors, called PPIR-Net. The PPIR-Net combines prior knowledge with deep learning to greatly improve the structural texture and color information of underwater images. The framework estimates underwater transmission maps and underwater scattering maps through the structure restoration network (SRN). Moreover, the color correction network (CCN) is used to achieve image color correction. Extensive experimental results show that our method exceeds state-of-the-art methods on underwater image evaluation metrics.
Supported by Sichuan Science and Technology Program (No. 2021YFG0201).
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
References
Yeh, C., et al.: Lightweight deep neural network for joint learning of underwater object detection and color conversion. IEEE Trans. NNLS, 1–15 (2021)
Wu, Y., Ta, X., Xiao, R., Wei, Y., An, D., et al.: Survey of underwater robot positioning navigation. Appl. OR 90, 101845 (2019)
Hu, X., Liu, Y., Zhao, Z., Liu, J., et al.: Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network. Comput. Electron. Agric. 185, 106135 (2021)
Hummel, R.: Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network. GGIP 6(2), 184–195 (1977)
Pizer, S., Amburn, E., Austin, J., et al.: Adaptive histogram equalization and its variations. CVGIP 39(3), 355–368 (1987)
Zuiderveld, K.: Contrast limited adaptive histogram equalization. Academic, 474–485 (1994)
Drews, P., Nascimento, E., Moraes, F., et al.: Transmission estimation in underwater single images. In: ICCV Workshops, pp. 825–830 (2013)
Galdran, A., Pardo, D., Picón, A., et al.: Automatic red-channel underwater image restoration. JVCIR 26, 132–145 (2015)
Li, J., Katherine, A., Ryan, M., et al.: WaterGAN: unsupervised generative network to enable real-time color correction of monocular underwater images. IEEE Robot. AL 3(1), 387–394 (2018)
Wang, Y., Zhang, J., Cao, Y., Wang, Z.: A deep CNN method for underwater image enhancement. In: ICIP, pp. 1382–1386 (2017)
Li, C., Guo, C., Ren, W., Cong, R., et al.: An underwater image enhancement benchmark dataset and beyond. IEEE Trans. IP 29, 4376–4389 (2020)
Guo, Y., Li, H., Zhuang, P.: Underwater image enhancement using a multiscale dense generative adversarial network. IEEE J. OE 45(3), 862–870 (2020)
Li, C., Guo, J., Guo, C.: Emerging from water: underwater image color correction based on weakly supervised color transfer. IEEE Sig. Process. Lett. 25(3), 323–327 (2018)
He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. PAMI 33(12), 2341–2353 (2011)
Islam, M., Luo, P., Sattar, J.: Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception. cs. CV (2020). https://doi.org/10.48550/arXiv.2002.01155
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Song, H., Wang, R.: Underwater image enhancement based on multi-scale fusion and global stretching of dual-model. MDPI 9(6), 595 (2021)
Cho, Y., Jeong, J., Kim, A.: Model-assisted multiband fusion for single image enhancement and applications to robot vision. IEEE Robot. AL 3(4), 2822–2829 (2018)
Cosmin, A., Codruta O., Tom, H., Philippe, B.: Enhancing underwater images and videos by fusion. In: CVPR, pp. 81–88 (2012)
Islam, M., Xia, Y., Sattar, J.: Fast underwater image enhancement for improved visual perception. IEEE Robot. AL 5(2), 3227–3234 (2020)
Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: BMVC (2018). https://doi.org/10.48550/arXiv.1808.04560
Xu, J., Chae, Y., et al.: Dense Bynet: residual dense network for image super resolution. In: ICIP, pp. 71–75 (2018)
Acknowledgments
The presented work is supported by Sichuan Science and Technology Program (No. 2021YFG0201).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, C. et al. (2023). PPIR-Net: An Underwater Image Restoration Framework Using Physical Priors. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1793. Springer, Singapore. https://doi.org/10.1007/978-981-99-1645-0_54
Download citation
DOI: https://doi.org/10.1007/978-981-99-1645-0_54
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1644-3
Online ISBN: 978-981-99-1645-0
eBook Packages: Computer ScienceComputer Science (R0)