Open AccessUnderwater color restoration and dehazing based on deep neural network
Author(s) -
Nan Wang
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2234/1/012016
Subject(s) - underwater , computer science , artificial intelligence , autoencoder , distortion (music) , visibility , computer vision , attenuation , image restoration , deep learning , geology , image (mathematics) , image processing , optics , telecommunications , amplifier , oceanography , physics , bandwidth (computing)
In real-world underwater environment, exploration of seabed resources, underwater archaeology, and underwater fishing rely on a variety of sensors, vision sensor is the most important one due to its high information content, non-intrusive, and passive nature. However, wavelength-dependent light attenuation and back-scattering result in color distortion and haze effect, which degrade the visibility of images. To address this problem, firstly, we proposed an underwater unsupervised generative adversarial network call UWGAN for generating realistic underwater fake images from paired images in air and their corresponding depth maps based on an improved underwater imaging model. Secondly, U-Net, which is trained efficiently using synthetic underwater dataset, is adopted for color restoration and dehazing. Our model directly reconstructs underwater clear images using end-to-end autoencoder networks, while maintaining the structural similarity of underwater scenes. The results obtained by our method were compared with existing methods qualitatively and quantitatively. Experimental results obtained by the proposed model demonstrate well performance on open real-world underwater datasets, and the processing speed can reach up to 125FPS running on one NVIDIA 1060 GPU.