This study aims to develop an enhanced YOLO algorithm to improve the ship detection performance of synthetic aperture radar (SAR) in complex marine environments. Current SAR ship detection methods face numerous challenges in complex sea conditions, including environmental interference, false detection, and multi-scale changes in detection targets. To address these issues, this study adopts a technical solution that combines multi-level feature fusion with a dynamic detection mechanism. First, a cross-stage partial dynamic channel transformer module (CSP_DTB) was designed, which combines the transformer architecture with a convolutional neural network to replace the last two C3k2 layers in the YOLOv11n main network, thereby enhancing the model’s feature extraction capabilities. Second, a general dynamic feature pyramid network (RepGFPN) was introduced to reconstruct the neck network architecture, enabling more efficient multi-scale feature fusion and information propagation. Additionally, a lightweight dynamic decoupled dual-alignment head (DYDDH) was constructed to enhance the collaborative performance of localization and classification tasks through task-specific feature decoupling. Experimental results show that the proposed DRGD-YOLO algorithm achieves significant performance improvements. On the HRSID dataset, the algorithm achieves an average precision (mAP50) of 93.1% at an IoU threshold of 0.50 and an mAP50–95 of 69.2% over the IoU threshold range of 0.50–0.95. Compared to the baseline YOLOv11n algorithm, the proposed method improves mAP50 and mAP50–95 by 3.3% and 4.6%, respectively. The proposed DRGD-YOLO algorithm not only significantly improves the accuracy and robustness of synthetic aperture radar (SAR) ship detection but also demonstrates broad application potential in fields such as maritime surveillance, fisheries management, and maritime safety monitoring, providing technical support for the development of intelligent marine monitoring technology.

Discrete floe ice increases the propulsion resistance of small unmanned surface vehicles (USVs) and generates impulsive bow and side loads. For high-density polyethylene (HDPE) USVs, these loads govern propulsion demand and provide inputs for structural assessment. Existing studies address floe-ice resistance of conventional ships and HDPE material behaviour separately. Using the geometry of an HDPE USV, this study combined the Reynolds-averaged Navier–Stokes (RANS) equations, volume-of-fluid (VOF) method, and discrete element method (DEM). The model computed open-water resistance and longitudinal loads under varying speed, ice concentration, and ice thickness. The numerical method was assessed against KRISO Container Ship (KCS) experiments in open water and floe ice. Open-water resistance increased from 49.2 to 230.7 N between 2 and 4 kn. At a 60% ice concentration and 0.02 m ice thickness, the mean total load increased from 125.6 to 428.9 N over this range. Increasing speed raised both fluid resistance and contact force, whereas higher concentration and thickness primarily increased contact force; the peak load reached 929.2 N at 0.04 m thickness. These fixed-attitude predictions provide comparative load estimates for propulsion assessment and subsequent structural analysis of the HDPE USV.