Abstract
Restoring degraded underwater images is a challenging ill-posed problem. The existing prior-based approaches have limited performance in many situations due to the reliance on handcrafted features. In this paper, we propose an effective convolutional neural network (CNN) for underwater image restoration. The proposed network consists of two paralleled branches: a transmission estimation network (T-network) and a global ambient light estimation network (A-network); in particular, the T-network employs cross-layer connection and multi-scale estimation to prevent halo artifacts and to preserve edge features. The estimates produced by these two branches are leveraged to restore the clear image according to the underwater optical imaging model. Moreover, we develop a new underwater image synthesizing method for building the training datasets, which can simulate images captured in various underwater environments. Experimental results based on synthetic and real images demonstrate that our restored underwater images exhibit more natural color correction and better visibility improvement against several state-of-the-art methods.
Highlights
Underwater imaging has found important applications in diverse research areas such as marine biology and archaeology [1,2], underwater surveying and mapping [3], and underwater target detection [4,5]
On the basis of the well-known model for underwater physical imaging, we propose a deep convolutional neural network (CNN) model with two parallel branches for underwater image restoration, accompanied by a training dataset in this paper
Aiming to improve the image contrast and color cast, an underwater image restoration approach based on a parallel CNN and the underwater optical model is proposed in this paper
Summary
Underwater imaging has found important applications in diverse research areas such as marine biology and archaeology [1,2], underwater surveying and mapping [3], and underwater target detection [4,5]. Captured underwater images are generally degraded by scattering and absorption. Scattering means a change of direction of light after collision with suspended particles in water, which causes the blurring and low contrast of images. Absorption means light absorbed by suspended particles which depends on the wavelength of each light beam [6]. Because the light with shorter wavelength (i.e., green and blue light) travels longer in water, the underwater images generally have predominantly green-blue hue. Contrast loss and color deviation are the main consequences of underwater degradation processes(e.g., Figure 1), which may cause difficulties for further processing, and it is of considerable interest to remove such distortions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
