Explore the vast range of titles available.

Underwater image restoration is of significant importance in unveiling the underwater world. Numerous techniques and algorithms have been developed in recent decades. However, due to fundamental difficulties associated with imaging/sensing, lighting, and refractive geometric distortions in capturing clear underwater images, no comprehensive evaluations have been conducted with regard to underwater image restoration. To address this gap, we constructed a large-scale real underwater image dataset, dubbed Heron Island Coral Reef Dataset (‘HICRD’), for the purpose of benchmarking existing methods and supporting the development of new deep-learning based methods. We employed an accurate water parameter (diffuse attenuation coefficient) to generate the reference images. There are 2000 reference restored images and 6003 original underwater images in the unpaired training set. Furthermore, we present a novel method for underwater image restoration based on an unsupervised image-to-image translation framework. Our proposed method leveraged contrastive learning and generative adversarial networks to maximize the mutual information between raw and restored images. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method. Our code and dataset are both publicly available.

The limitations of underwater acoustic communications mean that the side-scan sonar data of an autonomous underwater vehicle (AUV) cannot be transmitted back and processed in real time, which means that targets cannot be detected in real time. To address the problem, this paper proposes an autonomous underwater vehicle-based side-scan sonar real-time detection method for underwater targets. First, the paper describes the system and operation of real-time underwater-target detection by the side-scan sonar mounted on the autonomous underwater vehicle. Next, it proposes a real-time processing method for side-scan sonar data, method for constructing a deep-learning-based underwater-target detection model, and real-time method for underwater-target detection based on navigation strip images, which, together, solve the three key technical problems of real-time data processing, deep-learning-based detection model construction, and real-time target detection based on the autonomous underwater vehicle. Finally, through sea-based experiments, the effectiveness of the proposed methods is evaluated, providing a new solution for the autonomous underwater vehicle-based side-scan sonar real-time detection of underwater targets.

Underwater adhesive proteins secreted by organisms greatly inspires the development of underwater glue. However, except for specific proteins such as mussel adhesive protein, barnacle cement proteins, curli protein and their related recombinant proteins, it is believed that abundant common proteins cannot be converted into underwater glue. Here, we demonstrate that unfolded common proteins exhibit high affinity to surfaces and strong internal cohesion via amyloid-like aggregation in water. Using bovine serum albumin (BSA) as a model protein, we obtain a stable unfolded protein by cleaving the disulfide bonds and maintaining the unfolded state by means of stabilizing agents such as trifluoroethanol (TFE) and urea. The diffusion of stabilizing agents into water exposes the hydrophobic residues of an unfolded protein and initiates aggregation of the unfolded protein into a solid block. A robust and stable underwater glue can thus be prepared from tens of common proteins. This strategy deciphers a general code in common proteins to construct robust underwater glue from abundant biomass. Underwater adhesive proteins greatly inspired the development of underwater glue but except for specific proteins it is believed that abundant common proteins cannot be converted into underwater glue. Here, the authors demonstrate, using bovine serum albumin as model protein, that unfolded common proteins exhibit high affinity to surfaces and strong internal cohesion via amyloid-like aggregation in water.

Target tracking based on sonar images plays a crucial role in underwater coordinated operations and strikes. In this paper, aiming to address the problem of underwater noise interference and target boundary blurring in sonar image, we propose an enhanced SiamMask network, SiamMask-RAM, for underwater target tracking. By combining hybrid attention and cross correlation structures, a new similarity metric branch is proposed to enhance perception of underwater target boundaries. Furthermore, by combining the confidence scores of the positive samples with the IoU, a ranking loss optimization strategy is proposed to reduce the possibility of mismatch between the classification and regression. Exceptionally, we constructed an underwater typical target dataset based on sonar images. The evaluation results on the sonar dataset demonstrate that SiamMask-RAM achieves a tracking accuracy of 0.752, an expected average overlap of 0.362, which are 22.6% and 21.9% better than the SiamRPN tracking algorithm, respectively. These findings indicate that the proposed method exhibits high accuracy and robustness in underwater tracking scenarios involving sonar images.

Background normalization is one of the hot fields in underwater acoustic signal processing. Building on the conventional two-dimensional background normalization methods, this paper extends these techniques to three dimensions, tailored for the high-dimensional characteristics of continuous active sonar detection data. The three-dimensional background normalization algorithm sets protection windows and reference windows in the azimuth, range, and Doppler directions, and then uses the data from the reference windows to estimate the background power of the test cell. This paper analyzes and verifies the performance of the three-dimensional background normalization detection algorithm using simulated continuous active sonar detection data. The result shows that, compared to traditional two-dimensional background normalization detection algorithms, the three-dimensional background normalization detection algorithm performs better in complex backgrounds.

To improve the recognition accuracy of underwater acoustic targets by artificial neural network, this study presents a new recognition method that integrates a one-dimensional convolutional neural network and a long short-term memory network. This new network framework is constructed and applied to underwater acoustic target recognition for the first time. Ship acoustic data are used as input to evaluate the network performance. A visual analysis of the recognition results is performed. The results show that this method can realize the recognition and classification of underwater acoustic targets. Compared with a single neural network, the relevant indices, such as the recognition accuracy of the joint network are considerably higher. This provides a new direction for the application of deep learning in the field of underwater acoustic target recognition.

For the shortcomings of biologically inspired neural network algorithm in the path planning of robots, such as high computational complexity, long path planning time etc Glasius Bio-inspired Neural Network (GBNN) algorithm is proposed to improve the algorithm, and applied to the complete coverage path planning of autonomous underwater vehicle (AUV). Firstly, the grid map is constructed by discretizing the two-dimensional underwater environment. Secondly, the corresponding dynamic neural network is built on the grid map. Finally, complete coverage path of AUV is planned based on the GBNN strategy and the path of AUV at the edge of obstacles is optimized by some typical path templates. The simulation results show that the AUV can completely cover the entire workspace and immediately escape from deadlocks without any waiting. Meanwhile, the efficiency of complete coverage path planning is high with short path planning time and low overlapping coverage rate by using the algorithm proposed in this paper.

Gravel drift under the hydrodynamic effect is a significant problem during gravel dumping operations in coastal areas, which has a great impact on construction efficiency. Based on the Zhangpu submarine pipeline project, this paper investigated the drift distance and underwater distribution characteristics of gravel during the process of submarine trench gravel dumping under the influence of hydrodynamics by using the computational fluid dynamics (CFD) method. The results show that the greater the water depth and current speed is, the farther the drift distance of gravel along the current direction is. The water current has the most significant effect on the underwater distribution of gravel. The larger the current velocity is, the larger the underwater distribution width of gravel after sinking to the bottom is, and the larger the loss rate of gravel which has not been thrown to the required range is. The construction work should be avoided under high current speed conditions when carrying out gravel dumping.

In-situ measurement for large-scale underwater equipment has been confronted with many challenges in measuring distance and accuracy. Existing methods can only detect small equipment with meter level dimensions. Inspired by indoor global positioning system (IGPS) measurement technology of large-scale equipment on land, we propose a underwater dehazing imaging three-dimensional measurement method based on digital micro-mirror device (DMD) sparse sensing to settle above issues. Specifically, polarization dehazing imaging involves modulating conjugated scattering field to eliminate background scattered light from water propagation. The multi frequency sonar locator builds underwater IGPS by obtaining the distances of spherical transmitters. The experiments demonstrate that the accuracy of combined measurement reaches 1mm with a measurement distance of 100 meters. This method is suitable for measuring the deformation of large underwater equipment such as dam gates, ships, and pipelines

Components and structures working in the marine environment are exposed to high stresses attributable to the action of wind, waves, and tides. Moreover, they have to face hostile and severe environmental conditions during their lifetime, being placed in the splash zone if not even submerged in saltwater. The application of polymer composites in marine systems has been the focus of intensive studies in the last decades, highlighting potential benefits given by the replacement of several components, such as ship hulls, propeller blades, wind, and tidal turbine blades, to cite but a few. The present paper reports the latest advances in this area, addressing the applications of advanced composites in ships and ship components, offshore oil and gas composites, marine renewable energy and underwater repairing.