Dark ships, vessels deliberately disabling their AIS signals, constitute a grave maritime safety hazard, with detection efforts hindered by issues like over-reliance on AIS, inadequate surveillance coverage, and significant mismatch rates. This paper proposes an improved multi-feature association method that integrates satellite remote sensing and AIS data, with a focus on oriented bounding box course estimation, to improve the detection of dark ships and enhance maritime surveillance. Firstly, the oriented bounding box object detection model (YOLOv11n-OBB) is trained to break through the limitations of horizontal bounding box orientation representation. Secondly, by integrating position, dimensions (length and width), and course characteristics, we devise a joint cost function to evaluate the combined significance of multiple features. Subsequently, an advanced JVC global optimization algorithm is employed to ensure high-precision association in dense scenes. Finally, by integrating data from Gaofen-6 (optical) and Gaofen-3B (SAR) satellites, a day-and-night collaborative monitoring framework is constructed to address the blind spots of single-sensor monitoring during night-time or adverse weather conditions. Our results indicate that the detection model demonstrates a high average precision (AP50) of 0.986 on the optical dataset and 0.903 on the SAR dataset. The association accuracy of the multi-feature association algorithm is 91.74% in optical image and AIS data matching, and 91.33% in SAR image and AIS data matching. The association rate reaches 96.03% (optical) and 74.24% (SAR), respectively. This study provides an efficient technical tool for maritime safety regulation through multi-source data fusion and algorithm innovation.

Maritime unmanned aerial vehicle (UAV) ship detection faces challenges including variations in ship pose and appearance under multiple viewpoints, occlusion and confusion in dense scenes, complex backgrounds, and the scarcity of ship datasets from UAV tilted perspectives. To overcome these obstacles, this study introduces a high-quality dataset named Marship-OBB9, comprising 11,268 drone-captured images and 18,632 instances spanning nine typical ship categories. The dataset systematically reflects the characteristics of maritime scenes under diverse scales, viewpoints, and environmental conditions. Based upon this dataset, we propose a novel detection network named YOLO11-UAVShip. First, an oriented bounding box detection mechanism is incorporated to precisely fit ship contours and reduce background interference. Second, a newly designed CK_DCNv4 module, integrating deformable convolution v4 (DCNv4) and a C3k2 backbone structure, is developed to enhance geometric feature extraction under aerial oblique view. Additionally, for ships with large aspect ratios, SGKLD effectively addresses the localization challenges in dense environments, achieving robust position regression. Comprehensive experimental evaluation demonstrates that the proposed method yields a 2.1% improvement in mAP@0.5 and a 2.3% increase in recall relative to baseline models on the Marship-OBB9 dataset. While maintaining real-time inference speed, our approach greatly enhances detection accuracy and robustness. This work provides a practical and deployable solution for intelligent ship detection in UAV imagery.