Underwater salient object detection (USOD) attracts increasing interest for its promising performance in various underwater visual tasks. However, USOD research is still in its early stages due to the lack of large-scale datasets within which salient objects are well-defined and pixel-wise annotated. To address this issue, this paper introduces a new dataset named USOD10K. It consists of 10,255 underwater images, covering 70 categories of salient objects in 12 different underwater scenes. In addition, salient object boundaries and depth maps of all images are provided in this dataset. The USOD10K is the first large-scale dataset in the USOD community, making a significant leap in diversity, complexity, and scalability. Secondly, a simple but strong baseline termed TC-USOD is designed for the USOD10K. The TC-USOD adopts a hybrid architecture based on an encoder-decoder design that leverages transformer and convolution as the basic computational building block of the encoder and decoder, respectively. Thirdly, we make a comprehensive summarization of 35 cutting-edge SOD/USOD methods and benchmark them over the existing USOD dataset and the USOD10K. The results show that our TC-USOD obtained superior performance on all datasets tested. Finally, several other use cases of the USOD10K are discussed, and future directions of USOD research are pointed out. This work will promote the development of the USOD research and facilitate further research on underwater visual tasks and visually-guided underwater robots. To pave the road in this research field, all the dataset, code, and benchmark results are publicly available: https://github.com/LinHong-HIT/USOD10K.

This paper conducts a numerical investigation on the hydrodynamic performance of a portable autonomous underwater vehicle (AUV). The portable AUV is designed to cruise and perform some tasks autonomously in the underwater world. However, its dynamic performance is strongly affected by hydrodynamic effects. Therefore, it is crucial to investigate the hydrodynamic performance of the portable AUV for its accurate dynamic modeling and control. In this work, based on the designed portable AUV, a comprehensive hydrodynamic performance investigation was conducted by adopting the computational fluid dynamics (CFD) method. Firstly, the mechanical structure of the portable AUV was briefly introduced, and the dynamic model of the AUV, including the hydrodynamic term, was established. Then, the unknown hydrodynamic coefficients in the dynamic model were estimated through the towing experiment and the plane-motion-mechanism (PMM) experiment simulation. In addition, considering that the portable AUV was affected by wave forces when cruising near the water surface, the influence of surface waves on the hydrodynamic performance of the AUV under different wave conditions and submerged depths was analyzed. Finally, the effectiveness of our method was verified by experiments on the standard models, and a physical experiment platform was built in this work to facilitate hydrodynamic performance investigations of some portable small-size AUVs.

This paper presents the development of a portable autonomous underwater vehicle (AUV) named Shark, along with the design of its hovering control system for vision-based underwater inspection. Firstly, the mechanical structure design, electrical system configuration, and software system development of the Shark AUV are introduced, highlighting its cost-effectiveness, compact size, and streamlined torpedo shape to enhance the flexibility of underwater inspections. Secondly, the dynamic model of the Shark AUV is established, and the hydrodynamic coefficients are numerical estimated utilizing computational fluid dynamics (CFD) simulations. Thirdly, considering that the developed Shark AUV is underactuated in the sway degree of freedom, a novel heading control model is developed that reasonably tackles the motion coupling between sway and yaw. This model facilitates the design of a robust $\mathcal {H}_{\infty }$ controller to regulate the heading angle of the Shark AUV for vision-based underwater inspections. Finally, the effectiveness of the designed hovering control method and vision-based underwater inspection system are validated in both a 3D simulation platform and a laboratory test pool. The experimental results demonstrate that the Shark AUV prototype can achieve satisfactory vision-based underwater inspection performance within a pixel error of 5 × 5, and the proposed $\mathcal {H}_{\infty }$ heading controller consistently provides superior performance in handling motion coupling, parametric uncertainty, and external disturbances.

Hydrodynamic coefficient estimation is crucial to the shape design, dynamic modeling, and control of underwater vehicles. In this paper, we conduct a numerical study on the hydrodynamic coefficient estimation of an underactuated underwater vehicle (actuated only in the surge, heave, and yaw degrees of freedom) by adopting the computational fluid dynamics (CFD) approach. Firstly, the mechanical structure of an underactuated underwater vehicle is briefly introduced, and the dynamic model of the underwater vehicle with hydrodynamic effects is established. Then, steady and unsteady Reynolds Averaged Navier–Stokes (RANS) simulations are carried out to numerically simulate the towing test, rotating arm test, and Planar Motion Mechanism (PMM) test of the underwater vehicle numerically. To simulate unsteady motions of the underactuated underwater vehicle, a sliding mesh model is adopted to simulate flows in the computational fluid domain that contain multiple moving zones and capture the unsteady interactions between the underwater vehicle and the flow field. Finally, the estimated hydrodynamic coefficients of the underwater vehicle are validated in a physical experiment platform, and the results show that the numerical estimates are in good agreement with the experimental data.