Abstract

Active underwater polarization imaging is a common underwater imaging method, which uses the polarization difference between the reflected light and the scattered light in the underwater scene to suppress the scattered light, so as to improve the imaging quality of the underwater scene. However, the implementation often requires the acquisition of multiple polarization images, which is not suitable for the restoration of images of underwater motion scenes. To address the problem, a U-AD-Net deep learning network model based on a single polarized image is proposed, taking the polarization information of the single polarized image as the feature input, based on the classic U-Net network model, and introducing Dense-Net and spatial attention module. The learning ability and generalization ability of the proposed model for deep features are enhanced, and the polarization information that is most helpful to the image restoration is extracted, so as to restore the scene image more comprehensively. IE, AG, UCIQE, and SSIM are selected as evaluation metrics to assess the quality of the restored images. Experimental results show that the images restored through this proposed method contain richer detail information, having an obvious advantage to the existing network models. Since only a single polarized image is needed for restoration, this method has dynamic adaptability to underwater moving scene restoration.

© 2023 Optica Publishing Group

Super-resolution reconstruction of underwater polarized images with a fused attention mechanism

Liying Lang, Haoyi Feng, Jinghan Zhang, and Yajun Pang
Appl. Opt. 63(6) 1590-1599 (2024)

Underwater image recovery utilizing polarimetric imaging based on neural networks

Ran Zhang, Xinyuan Gui, Haoyuan Cheng, and Jinkui Chu
Appl. Opt. 60(27) 8419-8425 (2021)

Self-attention module in a multi-scale improved U-net (SAM-MIU-net) motivating high-performance polarization scattering imaging

Bing Lin, Xueqiang Fan, and Zhongyi Guo
Opt. Express 31(2) 3046-3058 (2023)

Full scene underwater imaging with polarization and an untrained network

Yanmin Zhu, Tianjiao Zeng, Kewei Liu, Zhenbo Ren, and Edmund Y. Lam
Opt. Express 29(25) 41865-41881 (2021)

Unsupervised underwater imaging based on polarization and binocular depth estimation

Enlai Guo, Jian Jiang, Yingjie Shi, Lianfa Bai, and Jing Han
Opt. Express 32(6) 9904-9919 (2024)