This article introduces methods for path-specific beamforming and adaptive compensation of nonuniform Doppler drifts in single-carrier broadband underwater acoustic communications. We focus on scenarios where different propagation paths experience varying Doppler drifts, which can significantly degrade conventional receivers. The proposed method employs broadband beamforming to separate the multipath components. Each path is then individually time-aligned and Doppler-synchronized before being processed by a multichannel fractionally spaced decision-feedback equalizer (DFE). By time-aligning the signals before equalization, the DFE filters need only cover the dispersion of each isolated path rather than the entire multipath spread, which leads to an overall reduction in the equalizer size. To account for time compression and dilation, we incorporate a delay-locked loop alongside a phase-locked loop to perform adaptive online resampling or delay tracking, thus eliminating the need for front-end resampling even in high-Doppler scenarios. Simulation and experimental results demonstrate that the proposed approach operates successfully under conditions that cause conventional receivers to fail. In cases where the conventional receiver performs well, our proposed algorithm achieves comparable performance with significantly fewer training symbols, yielding excellent performance in terms of data detection mean squared error and bit error rate.

This article concentrates on the autonomous navigation issue of a six-degree-of-freedom (6-DoF) underactuated uncrewed surface vessel (USV) in the context of limited observation conditions. In light of the prevalence of unknown obstacles in marine environments and the limited detection range of the radar installed on the USV, traditional methods are inadequate for effective navigation with obstacle avoidance. A new dual-control-attention (DCA) structure is thus proposed, and the corresponding reinforcement learning (RL) scheme, namely, DCA-soft actor–critic (SAC), is designed to learn the obstacle avoidance strategy from limited distance information only. The state space is devised and a concomitant reward function is incorporated to enhance the efficiency of training process. As such, the autonomous navigation difficulty of USV caused by wind and wave disturbances and unknown obstacles in actual marine surface environment is solved efficaciously. Moreover, the validation simulations compare our method with some existing RL algorithms. It can be found that our DCA-SAC algorithm demonstrates superior capabilities in rapid and effective acquisition of collision-free autonomous navigation scheme for a USV under observation constraints.

In the field of maritime transportation, autonomous collision avoidance is extraordinarily significant in ensuring the safety of navigation. This study proposes a multiple marine autonomous surface ships (MASSs) collision avoidance decision-making method based on improved rollback restriction and gate recurrent unit authentic boundary proximal policy optimization (RG-ABPPO) algorithm. The novelty of the study is: 1) Using the new rollback restriction solves the problem of excessive clipping of PPO algorithm, thereby improving the learning performance; 2) developing an improved gate recurrent unit (GRU) network structure based on auxiliary loss function, which is able to improve the computational efficiency; 3) designing a group of complete reward functions that can ensure the navigation safety of MASSs in the face of extremely complex encounter situations. In the simulation, the analysis of the loss function, average reward curve, collision avoidance success rate, computational efficiency, and navigation time demonstrates that the RG-ABPPO trained network model exhibits superior performance in collision avoidance. Finally, a physical experiment in the real world demonstrates the potential of the proposed method for engineering applications.

Few-shot object detection in sonar images faces several critical challenges, including severe image noise interference, low contrast, and variations in object scales. Dual-branch meta-learning approaches for few-shot object detection typically utilize a support branch to extract class prototypes, which are subsequently fused with query branch features to enhance detection performance. However, existing methods commonly suffer from imprecise class prototype representations, and the fixed receptive field in prototype assignment mechanisms fails to effectively accommodate the scale variability of underwater targets. To address these issues, we propose the Integrated Discriminative Prototype Distillation module, which partitions the support feature maps and employs a set of learnable embeddings to extract integrated class prototypes. This design enables diverse feature queries to focus on distinct local regions within the support features, while incorporating global residual information to achieve a balanced representation between local details and global contextual semantics. Subsequently, the Scale-Aware Prototype Assignment module is employed to perform multiscale matching between the integrated class prototypes and the query feature maps, thereby enhancing the expressiveness of feature representations. Finally, high-level features are fused via an adaptive weighting strategy, effectively enhancing class feature discriminability while suppressing noise-induced bias. Experimental results demonstrate that the proposed method achieves superior performance compared to state-of-the-art approaches on three publicly available sonar data sets, validating its effectiveness in few-shot object detection tasks for sonar images.

Underwater image enhancement (UIE) is crucial for underwater perception tasks but is challenged by complex physical degradations, including backscatter, wavelength-dependent attenuation, scattering, turbidity, and color cast. These factors severely reduce visibility and color fidelity in underwater scenes. This article presents a UIE method called UIE-DDPM, which is based on the conditional denoising diffusion probabilistic model and underwater physical model. UIE-DDPM innovatively enhances underwater images by integrating the Jaffe-McGlamery underwater physical model with the diffusion process and employing optical compensation as a conditional controller to regulate each iteration step with greater specificity. The UIE-DDPM consists of the variational autoencoder–optical compensation prediction network (VCP) and the underwater image semantic enhancement network (UISE). The VCP establishes the analytical relationship between optical compensation levels, performs Gaussian sampling and parameter renormalization, and estimates the distribution of optical compensation losses in the latent space. The UISE effectively enhances the essential semantics of degraded images by utilizing reference color-enhanced images as auxiliary information, thereby improving the understanding of details, contours, and contrasts. Meanwhile, the UIE-DDPM outperforms other baseline methods and generative adversarial network models in UIE, establishing a new state-of-the-art benchmark. In real-world application scenarios, the maximum underwater image quality metric increased by 1.336, and the maximum underwater color image quality evaluation increased by 0.158, demonstrating the effectiveness of the proposed method in enhancing underwater image quality under turbid conditions.

Underwater image enhancement (UIE) can improve the effectiveness of applications, such as underwater object detection. In UIE, synthetic images or pseudoimages are commonly used as enhancement references. However, the synthetic images cannot simulate underwater scenes, and there is interdomain difference between synthetic images and the underwater environment. Since different enhancement methods produce different effects on different semantic regions of the same image, pseudolabels lose valuable information from other enhancement methods. Moreover, different semantic information has different requirements for enhanced effectiveness. If the enhancement reference is provided on the semantic scale instead of the image scale, the advantages of various enhancement methods will be better utilized. To achieve this, this article introduces a method of semantic labels, which uses the results of different enhancement methods to label different semantic regions of the same image to build a more comprehensive reference. At the same time, enhancement images are often restricted by insufficient texture detail in advanced applications. Existing UIE methods employ the encoder–decoder architecture, which is effective in encoding broad contextual information but not reliable in preserving spatial image details. To simultaneously capture spatial information and retain image details, a two-stage spatial and detail network is proposed, which integrates U-Net and original resolution network to enhance the network’s ability to retain details. The experimental results show that the proposed method has better qualitative and quantitative evaluation results than the existing methods. Ablation studies demonstrate the effectiveness of the various components.

In recent years, autonomous docking technology for autonomous surface vessels (ASVs) has attracted increasing research interest, and boat berth detection plays a crucial role in this task. However, common berth detection methods for ASVs adopt specific marks, such as ArUco codes, to implement boat berth detection, which significantly limits their applicability in practical deployments, since most conventional wharfs do not contain such markers. To support tasks involving human-less return to dock and enhance the generalizability of berth detection in real-world wharf scenarios, this article proposes a novel markless berth detection framework based on high-level scene semantics, without relying on artificial markers. Our proposed detection framework, based on the fusion of camera and light detection and ranging (LiDAR), comprises two important components. First, a LiDAR-camera fusion point cloud semantic segmentation model is constructed to generate 3-D semantic point clouds. Second, a berth extraction algorithm is designed to process point cloud segmentation results and detect free berths for ASVs. In addition, to improve the performance of the point cloud semantic segmentation model for ASV scenes, we developed a LiDAR-assisted view transformer module and a LiDAR-camera fusion attention module. Moreover, in our collected point cloud segmentation data set for ASV wharf scenes, our proposed method outperforms other point cloud segmentation baselines. Moreover, we conducted real-world prototype experiments to validate the feasibility and robustness of our markless boat docking detection method. The experimental results demonstrate that our proposed berth detection method has a high potential to support applications involving the autonomous docking of ASVs.

Underwater images often suffer from color distortion and detail loss due to light absorption and scattering, which degrades visual quality and limits practical applications. To address these issues, a novel adaptive algorithm for underwater image color correction and detail enhancement is proposed. The algorithm first applies threshold stretching to adjust the grayscale range, enhancing contrast while mitigating the risk of localized overcompensation. Based on the color distribution, images are categorized into bluish and greenish tones, providing the foundation for the adaptive color compensation method (ACCM). The ACCM is designed to separately compensate different color channels, using the green channel as a reference to restore the most degraded channels while maintaining overall color balance. The compensation process is further constrained by the minimum color loss criterion to ensure consistent color fidelity. Furthermore, an edge detail enhancement method is formulated to recover fine details by amplifying intensity differences between the original image and its smoothed version. Extensive experiments on multiple underwater image data sets demonstrate that the proposed algorithm consistently outperforms state-of-the-art methods, achieving average improvements of 0.0021, 0.0646, 0.3677, and 0.0800 in underwater color image quality evaluation, underwater image quality metric, fog aware density evaluator, and colorfulness contrast fog density index metrics, respectively, underscoring its effectiveness and robustness across diverse underwater environments.