Ship detection in Synthetic Aperture Radar (SAR) images has garnered widespread attention due to its significant applications. However, few researchers have focused on the challenges posed by the unique limitations of SAR imaging mechanisms. These challenges include issue discontinuity and incompleteness of ship instances caused by internal hollowing or fracturing, the conventional IoU metric possesses limitations in evaluating the similarity between two boxes, and the self-attention mechanism considers only absolute position information. To address these challenges, we propose the Mixed Receptive Field and Multi-Position Encoding for Scale-Sensitive SAR Ship Detection with Transformer (M²S-DETR), which consists of four key components: the Mixed Receptive Field Module (MRFM), Multi-Position Encoding (MPE), Multi-Scale Feature Aggregation Unit (MFAU), and Scale-Sensitive IoU (S2-IoU). The MRFM, based on dilated convolution, complements missing ship structure information and allows for a larger receptive field. To more accurately capture position relationships within the self-attention mechanism, we incorporate learnable relative position encoding in the MPE, which reveals more nuanced relative position information to supplement absolute position encoding. In the multi-scale feature extraction and fusion phase, the MFAU utilizes a dual-path top-down and bottom-up strategy to better represent features across all scales. Additionally, we introduce Scale-Sensitive IoU (S2-IoU) into the classification branch to mitigate the phenomenon of inconsistent prediction pairs, thereby enabling the transformer decoder to perform high-quality initial query selection. Our method surpasses several CNN-based and Transformer-based detectors on the commonly used benchmark datasets SSDD and HRSID, respectively. Code is available at: https://github.com/douling843/M²S-DETR.

The perception of risks is a prerequisite for establishing an intelligent ship navigation system based on ship‐shore cooperation. According to the research conclusions on the ship‐shore collaboration, the technical characteristics of the intelligent ship navigation system, and the analysis of the test results of the ship “ZHI FEI” featured with intelligent navigation, we study and construct the conceptual model and mathematical expression model for risk evolution of the intelligent ship navigation. We further explore the unmanned trend, the general law, and the characteristics of risk evolution based on navigation scenarios and chain effects. The present study provides insight into the risk perception, management, and government governance of intelligent ship navigation and the construction of an intelligent ship navigation system based on ship‐shore collaboration.

Annually, hundreds of individuals tragically lose their lives at sea due to shipwrecks or aircraft accidents. For search and rescue personnel, the task of locating the debris of a downed aircraft in the vastness of the ocean presents a formidable challenge. A primary task these teams face is determining the search area, which is a critical step in the rescue operation. The movement of aircraft wreckage on the ocean surface is extremely complex, influenced by the combined effects of surface winds, waves, and currents. Establishing an appropriate drift motion prediction model is instrumental in accurately determining the search area for the wreckage. This article initially conducts maritime drift observation experiments on wreckage, and based on the results of these experiments, analyzes the drift characteristics and patterns of the debris. Subsequently, employing a wealth of observational experimental data, three types of drift prediction models for the wreckage are established using the least squares method. These models include the AP98 model, the dynamics model, and an improved model. In conclusion, the effectiveness and accuracy of the three models is evaluated and analyzed using Monte Carlo techniques. The results indicate that the probability of positive crosswind leeway (CWL) is 47.4%, while the probability of negative crosswind leeway (CWL) is 52.6%. The jibing frequency is 7.7% per hour, and the maximum leeway divergence angle observed is 40.4 degrees. Among the three drift prediction models, the refined AP98 drift model demonstrates the highest forecasting precision. The findings of this study offer a more accurate drift prediction model for the search of an aircraft lost at sea. These results hold significant guiding importance for maritime search and rescue operations in the South China Sea.

The application potential of unmanned aerial vehicles (UAVs) in marine search and rescue is especially of concern for the ongoing advancement of visual recognition technology and image processing technology. Limited computing resources, insufficient pixel representation for small objects in high-altitude images, and challenging visibility conditions hinder UAVs’ target recognition performance in maritime search and rescue operations, highlighting the need for further optimization and enhancement. This study introduces an innovative detection framework, CFSD-UAVNet, designed to boost the accuracy of detecting minor objects within imagery captured from elevated altitudes. To improve the performance of the feature pyramid network (FPN) and path aggregation network (PAN), a newly designed PHead structure was proposed, focusing on better leveraging shallow features. Then, structural pruning was applied to refine the model and enhance its capability in detecting small objects. Moreover, to conserve computational resources, a lightweight CED module was introduced to reduce parameters and conserve the computing resources of the UAV. At the same time, in each detection layer, a lightweight CRE module was integrated, leveraging attention mechanisms and detection heads to enhance precision for small object detection. Finally, to enhance the model’s robustness, WIoUv2 loss function was employed, ensuring a balanced treatment of positive and negative samples. The CFSD-UAVNet model was evaluated on the publicly available SeaDronesSee maritime dataset and compared with other cutting-edge algorithms. The experimental results showed that the CFSD-UAVNet model achieved an mAP@50 of 80.1% with only 1.7 M parameters and a computational cost of 10.2 G, marking a 12.1% improvement over YOLOv8 and a 4.6% increase compared to DETR. The novel CFSD-UAVNet model effectively balances the limitations of scenarios and detection accuracy, demonstrating application potential and value in the field of UAV-assisted maritime search and rescue.

To address the challenges of sparse point clouds in current MIMO millimeter-wave radar environmental mapping, this paper proposes a dense 3D millimeter-wave radar point cloud environmental mapping algorithm. In the preprocessing phase, a radar SLAM-based approach is introduced to construct local submaps, which replaces the direct use of radar point cloud frames. This not only reduces data dimensionality but also enables the proposed method to handle scenarios involving vehicle motion with varying speeds. Building on this, a 3D-RadarHR cross-modal learning network is proposed, which uses LiDAR as the target output to train the radar submaps, thereby generating a dense millimeter-wave radar point cloud map. Experimental results across multiple scenarios, including outdoor environments and underground tunnels, demonstrate that the proposed method can increase the point cloud density of millimeter-wave radar environmental maps by over 50 times, with a point cloud accuracy better than 0.1 m. Compared to existing algorithms, the proposed method achieves superior environmental map reconstruction performance while maintaining a real-time processing rate of 15 Hz.