Methods based on supervised learning perform well in underwater image enhancement. However, it is difficult to obtain clear labels of underwater images, and there are domain differences among various databases due to different acquisition equipment and waters, resulting in poor generalization ability of these methods. To solve the above problems, this paper proposes an underwater image enhancement algorithm based on semi-supervised domain adaptation, which is composed of domain adaptive module and image enhancement module. A domain adaptive module based on cycle-consistent generative adversarial networks (CycleGAN) is designed to eliminate the domain differences between different datasets. An image enhancement module based on semi-supervised learning strategy is proposed to solve the training problem of unlabeled images by adding physical priors of underwater images. Consistency constraint is used to ensure the stability of training and further improve network performance. The experimental results on the public datasets show that the proposed method is superior to the existing methods. In addition, the algorithm also perform well on the self-collected offshore underwater dataset.
Coral ecosystem not only breeds abundant organisms, but also deem to be a very important fishery and tourism resources. The reduction of coral will also have a bad impact on the marine. Scattering and absorption leads to complicate the capturing process of a clear image. Aiming to the needs of marine ecological diversity research, in addition to the privilege of underwater polarization imaging, an underwater binocular polarization vision system is proposed in this paper. This system consists of underwater vehicle, vision acquisition system and image processing software. The internal image acquisition hardware module made up out of microcomputer, two polarization camera modules and information transmission module. While the dynamic systems of underwater vehicle consist of six propellers. The proposed system realizes a real-time control and transmit polarization image through cable connected to information transmission module. Due to its autonomous function, it is capable to achieve missions without diver support. After the system is designed and implemented, a large number of underwater coral images are captured and tested at the offshore of Shenzhen to build our polarization image database. This database classified into 15 different kinds of offshore coral, which provides data support for subsequent algorithms such as clear imaging algorithm based on polarization vision. Finally, clear image processing algorithm is carried out with the captured data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.