Wind and waves are the main factors of environmental loading on ships and offshore structures. Thus, detailed understanding of wind and wave conditions can improve the design and maintenance of these structures. This paper developed a validated long-term wind and wave hindcast database covering the recent 32 years from 1988 to 2019. The spatial distribution of wind and wave characteristics for the whole Xisha Islands’ domain were analyzed. Frequency and directional distributions of wind speeds and significant wave heights were investigated at several locations around typical islands. Extreme value models were used to estimate the wind speed for 100-year return levels, whereas environmental contour approaches were utilized to establish the extreme sea-state parameters for 50- and 100-year return periods. It was found that the Weibull distribution was better fitted to the significant wave heights of the Xuande Atoll’s sites in the open sea, while the exponential Weibull distribution provided a better fit at the Yongle Atoll’s sites where waves are sheltered.

Fast and accurate ship target detection technology plays an important role in improving driving safety, rescue at sea, marine environmental protection, and sea traffic control. It is also one of the key technologies for the development of ship informatization and intelligence. However, the current ship target detection models used at different scales in multiple scenarios exhibit high complexity and slow inference speed. The trade-off between model detection speed and accuracy limits the deployment of ship target detection models on edge devices. This study proposes a lightweight multi-scale ship target detection model based on the Yolov5s model. In the proposed model, the lightweight EfficientnetV2 and C3Ghost networks are integrated into the backbone and neck networks of the Yolov5s model to compress the computational and parametric quantities of the model and improve the detection speed. The Shuffle Attention mechanism is embedded in the neck network component of the model to enhance the representation of important feature information, suppress irrelevant feature information, and improve the model’s detection performance. The improved method is trained and verified on the dataset collected and labeled by the authors. Compared with the baseline model, the inference speed of the proposed model increased by 29.58%, mAP0.5 improved by 0.1%, and the parameters and floating-point operations decreased by 42.82% and 68.35%, respectively. The file size of the model is 8.02MB, which is 41.46% lower than the baseline model. Compared with other lightweight models, the method proposed in this study is more favored in edge computing.

In complex marine environments, the safety and efficiency of ship navigation face dual challenges from static obstacles, such as shallow waters and islands, and extreme dynamic meteorological threats, such as typhoons. Existing path-planning algorithms often struggle to achieve an optimal balance between computational efficiency and risk-avoidance effectiveness when addressing high-frequency dynamic meteorological changes. To address this limitation, this study proposes a Time-Dynamic Theta* (TDM-Theta*) approach. From an algorithmic perspective, this method extends traditional any-angle path planning by introducing a temporal dimension to the search space. For maritime application, it integrates real-time significant wave height as a spatio-temporal dynamic constraint, thereby dynamically evaluating the actual impact of marine meteorology on ship navigability. Simulation tests were conducted through nine experimental cases designed under three typical navigation scenarios: unrestricted waters, complex terrains, and typhoon transits. The results demonstrate that the TDM-Theta* algorithm not only efficiently generates the shortest paths in statically complex terrains but also achieves a 100% proactive risk avoidance rate within the boundaries of the evaluated extreme weather scenarios with multiple concurrent typhoons, incurring negligible computational overhead and low path costs. This research provides robust theoretical and methodological support for real-time safe route decision-making for intelligent ships in complex and volatile environments.

Detection of targets on sea surfaces is an important area of application that can bring great benefits to the management and control systems in marine environments. However, there are few open-source datasets accessible for the purpose of object detection on seas and rivers. In this paper, a study is conducted on the improved detection algorithms based on the YOLOv5 model. The dataset for the tests contains ten categories of typical objects that are commonly seen in the contexts of seas, including ships, devices, and structures. Multiple augmentation methods are employed in the pre-processing of the input data, which are verified to be effective in enhancing the generalization ability of the algorithm. Moreover, a new form of the loss function is proposed that highlights the effects of the high-quality boxes during training. The results demonstrate that the adapted loss function contributes to a boost in the model performance. According to the ablation studies, the synthesized methods raise the inference accuracy by making up for several shortcomings of the baseline model for the detection tasks of single or multiple targets from varying backgrounds.

Reliable unmanned surface vehicle (USV) recovery requires near-field maritime remote sensing outputs that remain stable during the final approach. Planar fiducial geometry provides metric pose estimates, but its depth channel is sensitive to corner-localization noise, apparent marker shrinkage, glare, reflection, and vessel vibration. We present VARE (Visual-Adaptive Ranging and Estimation), a geometry-anchored perception pipeline that combines ArUco-based Perspective-n-Point pose recovery, dual-path bearing fusion, MiDaS-assisted range stabilization, depth-consistency confidence weighting, and innovation-adaptive temporal filtering. VARE is a system-level integration rather than a new neural architecture, PnP solver, or end-to-end docking controller. The pipeline explicitly separates image-centroid bearing, translation-vector bearing, marker-normal heading, camera-frame horizontal approach range, and lateral offset. Independent RTK-synchronized external references, with measured lever-arm corrections between the RTK antenna, camera optical center, and marker reference point, are used for pool and near-shore evaluation. In controlled land tests, VARE reduced independent-reference angular RMSE by 34.0–49.3% relative to the pixel-only baseline and by 22.0–36.4% relative to a static-filter PnP variant. Across 15 pool-based approach trials, the full vision-only configuration achieved a horizontal bearing RMSE of 0.46 degrees, a range MAE of 0.82 m, and a range RMSE of 0.90 m. Relative to the matched IPPE-square geometry baseline with One-Euro filtering, the corresponding descriptive reductions were 14.8%, 4.7%, and 5.3%; the modest range differences are not presented as universally significant. Trial-level summaries, confidence intervals, and data-availability provisions are added to support reproducibility. The results support VARE as a candidate perception module for RTK-referenced USV recovery guidance, while full six-degree-of-freedom validation, session-level dropout survival, and closed-loop capture success remain future work.