Search Results (317)

Accurate and rapid identification of microalgae in ship ballast water is critical for preventing the spread of invasive aquatic species and ensuring ecological security. However, traditional manual microscopic examination is labor-intensive and limited by challenges such as high intra-class morphological variability, frequent cell aggregation, and inter-class similarity among microalgae. This study proposes YOLO11-DBalgae, a specialized end-to-end object detection framework designed for fine-grained microalgae recognition in complex aquatic environments. Two key architectural innovations are introduced into the YOLO11n baseline—a Detail-enhanced Vanishing-prevention Block (DVB), which processes input features through a VoVGSCSP cross-stage aggregation module followed by parallel Conv and DSConv paths, preserving fine-grained boundary signals of morphologically diverse algal cells during repeated downsampling, and a Bidirectional Feature Pyramid Network (BiFPN), which employs learnable cross-scale weighting to optimize multi-scale feature fusion across the extreme size range of co-occurring microalgal targets. Experimental results demonstrate that YOLO11-DBalgae achieves an mAP@0.5 of 97.3%, representing an improvement of 7.0 percentage points over the baseline YOLO11n model. The model sustains an inference speed of 240 FPS with 2.83 M parameters, maintaining a lightweight and deployment-viable profile. Qualitative analysis via per-class precision–recall curves, detection visualization, and Grad-CAM attention maps confirms the model’s robustness in recovering near-invisible weak-feature targets, minimizing false detections within dense cell clusters, and accurately distinguishing morphologically convergent species. The proposed framework provides a practical and deployable solution for automated microalgae monitoring, offering maritime regulatory bodies an efficient and reliable tool for ballast water management. Full article

Instance segmentation accurately extracts the position and outline of ships, serving as the foundation for maritime safety tasks such as multi-object tracking, sensor fusion, and collision warning. This study focuses on single-frame segmentation and aims to address the challenge of multi-scale ship occlusion in congested ports, providing reliable observational data through high-precision recognition to ensure navigation safety. Existing methods suffer from performance degradation in complex maritime environments due to factors such as multi-scale distribution, low resolution of distant targets, and frequent occlusions. Among these, ship occlusion is particularly problematic as it leads to feature confusion between adjacent instances and inaccurate boundary segmentation. To address these challenges, we propose a novel instance segmentation algorithm (MAF-ORDNet) based on Multi-branch Adaptive Feature Fusion and Occluded Region Decoupling. Firstly, a multi-branch adaptive feature fusion module is designed to capture contextual information through different receptive fields and dynamically fuse multi-scale features, thereby restoring occluded semantics and enhancing robustness. Secondly, an occlusion region decoupling module is constructed to accurately localize occluded regions and enhance contour responses via adaptive sampling, achieving refined boundary processing. In addition, we constructed and annotated the Occlusion ShipSeg dataset, which contains 1969 real occlusion images, 2150 simulated occlusion images, and 1132 images under adverse weather conditions, totaling 17,352 fine instance annotations. Experimental results show that, compared with PatchDCT, YOLOv11s, and Mask2Former, our method improves AP by 2.7%, 3.2%, and 2.4%, respectively, while maintaining a comparable inference speed to YOLOv8s. These results confirm that MAF-ORDNet achieves a favorable balance between accuracy and efficiency in multi-scale occluded ship segmentation tasks. Full article

Ship collisions pose substantial risks to maritime safety, causing vessel damage, casualties, and environmental impacts. Efficient extraction and analysis of key navigational and causal information from accident reports are important for risk assessment and decision support. This study proposes a framework for synthetic data generation, DistilBERT-based named entity recognition, and structured dataset construction for ship collision accidents. Using a template-based method, 56,000 annotated sentences were generated, covering navigational elements and causal factor trigger phrases. The fine-tuned DistilBERT model showed good performance on both synthetic and real accident reports. Statistical and co-occurrence analyses further indicated that failure to maintain proper lookout, failure to take effective evasive action, and failure to maintain safe speed were the main contributing factors across different environments and accident severity levels. Based on the extraction results, a standardized structured dataset was constructed to support subsequent causal analysis, dynamic risk modeling, and collision risk prediction. The study shows that combining template-based data synthesis with Transformer-based named entity recognition is a feasible approach for extracting information from maritime accident reports and transforming unstructured text into structured datasets. Full article

The structural safety of polar ships is critically dependent on local ice loads acting in the ship–ice interaction area. Ice conditions and ship speeds play dominant roles in influencing local ice loads. Field measurement serves as a crucial approach for accurately assessing and scientifically understanding local ice loads and ice conditions. The instrumentation for the field measurement on RV Xuelong-2 is discussed in this study. In the 12th Chinese National Arctic Research Expedition, digital processing technologies are employed for image recognition and statistical analysis of ice concentrations and thicknesses. The influence coefficient matrix method is validated by a physical experiment and applied to identify local ice loads from ice-induced strains. Subsequently, the relationship between local ice loads, ice conditions, and ship speeds is statistically analyzed and mechanistically explained. The results show that the coupling effect between ship speeds and ice parameters, along with the competition between ice failure modes, may cause ice load peaks to transition from increasing to decreasing at a specific ship speed and ice thickness. A prolonged ice load duration under high ice concentrations is an important factor contributing to the positive correlation between ice load peaks and ice concentrations. Full article

Conventional heading-keeping autopilot logic exhibits well-known performance limitations under complex route geometry and environmental disturbances. Motivated by this limitation, this paper proposes a line-adhering intelligent navigation framework for disturbance-aware path-following of autonomous ships. The core idea is based on numerical simulation scenarios representing curved inland/coastal routes under wind- and current-disturbance conditions. The addressed gap lies in the limited integration of route-geometry adherence, human-like maneuvering logic, and disturbance-aware controller reconfiguration within conventional heading-centered ship path-following frameworks. Therefore, a rough-set classifier identifies disturbance modes and reconfigures PID, LQR, and MPC controllers in real time. Moreover, a vessel-dynamics constrained Bézier refinement method generates high-resolution reference paths aligned with navigational curvature limits. Mathematical models including the Nomoto and MMG formulations are incorporated to ensure controllability and dynamic feasibility. Results show that the proposed framework improves path-following precision, robustness, and comfort under the considered simulation conditions. Full article

With the continuous expansion of maritime trade scale, ports have put forward increasingly higher requirements for transshipment efficiency. Container twist lock disassembly is a key link in the loading and unloading process, and its automation level has a significant impact on the ship’s berthing time at the port. Aiming at the demand of automated disassembly for high-precision 3D vision, this paper proposes a multi-view point cloud local registration method for twist lock recognition. First, Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) is used to extract the keyhole region with the highest overlap in multi-view point clouds, reducing the interference from non-overlapping structures. Then, a two-stage strategy of “coarse registration + fine registration” is adopted: initial alignment is achieved through Random Sample Consensus (RANSAC), and the Iterative Closest Point (ICP) algorithm is improved by combining adaptive distance threshold and normal consistency constraint to complete fine registration. Experimental results show that the proposed method outperforms the global registration scheme in both accuracy and efficiency: the Root Mean Square Error (RMSE) is reduced to 2.15 mm, the Relative Mean Distance (RMD) is reduced to 1.81 mm, and the registration time is approximately 2.41 s. Compared with global registration, the efficiency is improved by 44.2%, which can meet the real-time requirements of continuous operation at automated terminals for the perception link and the time constraints for subsequent manipulator control. The research results preliminarily verify the application potential of this method in the scenario of automated twist lock disassembly. Full article

With the rapid advancement of deep learning, data acquisition remains a persistent challenge, as model effectiveness heavily relies on the quality and quantity of training data. To address the difficulties of time-consuming and labor-intensive data collection, data augmentation techniques are commonly adopted. In this study, the proposed WACGAN-GP, a Generative Adversarial Network (GAN) architecture, serves as an effective data augmentation tool designed to augment training datasets and bolster model performance. This method integrates the advantages of the Auxiliary Classifier GAN and the Wasserstein GAN with gradient penalty to generate diverse and realistic samples. Experiments were conducted on three image datasets—MNIST, CIFAR-10, and a ship classification dataset—under limited training data conditions. By incorporating WACGAN-GP generated synthetic samples into the original training sets, classification performance was evaluated in both balanced and imbalanced scenarios. The results demonstrate that the proposed GAN-based approach significantly improves recognition accuracy and outperforms conventional augmentation methods, such as horizontal and vertical flipping. Full article

Unmanned surface vehicles (USVs) increasingly rely on vision-based perception for safe navigation and maritime surveillance, while onboard computing is constrained by strict size, weight, and power (SWaP) budgets. Although deep convolutional neural networks (CNNs) offer strong recognition performance, their computational and memory requirements pose significant challenges for deployment on low-cost embedded platforms. This paper presents a hardware–software co-design architecture and deployment study for CNN acceleration on a heterogeneous ARM–FPGA system, targeting energy-efficient near-sensor processing for embedded maritime applications. The proposed approach exploits a fully streaming hardware architecture in the FPGA fabric, based on line-buffered convolutions and AXI-Stream dataflow, while the ARM processing system is responsible for lightweight configuration, scheduling, and data movement. The architecture was evaluated using representative CNN models trained on a maritime ship dataset. Our experimental results on a Zynq-7020 system-on-chip demonstrate that the proposed co-design strategy achieves a balanced trade-off between throughput, resource utilisation, and power consumption under tight embedded constraints, highlighting its suitability as a practical building block for onboard perception in USVs. Full article

For human beings, fine-grained object recognition is a progressive process that proceeds from global outlines to local details. They can determine how to further focus on the distinctive regions based on the overall context, followed by recognition. To enhance the algorithm’s capability to capture critical features, a multi-stage recognition framework, integrated with human-attended key regions for fine-grained ship recognition, is proposed in this manuscript. First, a set of distinctive templates is constructed following human identification logic. On this basis, a supervised attention method, Key Regions Guided Yolo11 (KRGY), with part-to-whole regulation is proposed to help the model focus on critical components, leading to better recognition and location performance. Furthermore, a multi-head joint recognition classification module is proposed, with key regions of ship cropped with the distinctive templates. With the hypothesis and verification framework Key Regions Guided Yolo11-Multi Head Classifier (KRGY-MHC), the accuracy of ship recognition is significantly improved based on a challenging datasets with high inter-class similarity DCL-11. Full article

Typhoon avoidance is critical for ship maneuvering safety under extreme meteo-ocean conditions. This study proposes a data-driven framework that converts AIS trajectories into interpretable course deviation and speed change responses for navigational decision support. After AIS cleaning, temporal resampling, and matching with gridded wind, wave, and current fields, rule-based sliding-window and regression procedures, informed by experienced captains and company staff, automatically generate proxy labels for deviation and speed reduction. Samples are stratified by vessel size to reflect differences in inertia and maneuverability, and XGBoost classifiers are trained with simple resampling to mitigate class imbalance. The framework is demonstrated on a single-event case study of Typhoon Yagi in the South China Sea, covering 8609 vessels and reconstructed sailing fragments. On the test set, the deviation model achieves 89.8% accuracy and high recall for deviation cases, while the speed change model reaches 82% balanced accuracy under the proxy-label setting. Results suggest a scale-dependent response: smaller vessels exhibit more frequent course deviation, whereas larger vessels more often reduce speed under severe wind-wave loading. The framework offers a proof-of-concept approach to derive behavior-based indicators from AIS and environmental data and may support situational assessment under adverse weather. Full article

With the expansion of water transportation networks and increasing traffic intensity, maritime accidents have become frequent, posing significant threats to safety and property. This study presents a knowledge graph-driven framework for maritime accident analysis, addressing the limitations of traditional risk analysis methods in extracting and organizing unstructured accident data. First, a standardized ontology for ship collision accidents is developed, defining core concepts such as event, spatiotemporal behavior, causation, consequence, responsibility, and decision-making. Advanced natural language processing models, including a lexicon-enhanced LEBERT-BiLSTM-CRF and a K-BERT-BiLSTM-CRF incorporating ship collision knowledge triplets, are proposed for named entity recognition and relation extraction, with F1-score improvements of 6.7% and 1.2%, respectively. The constructed accident knowledge graph integrates heterogeneous data, enabling semantic organization and efficient retrieval. Leveraging graph topological features, an accident severity classification model is established, where a graph-feature-driven LSTM-RNN demonstrates robust performance, especially with imbalanced data. Comparative experiments show the superiority of this approach over conventional models such as XGBoost and random forest. Overall, this research demonstrates that knowledge graph-driven methods can significantly enhance maritime accident knowledge extraction and severity classification, providing strong information support and methodological advances for intelligent accident management and prevention. Full article

Uncovering latent structures from complex, degraded data is a central challenge in modern unsupervised learning, with critical implications for downstream tasks. This principle is exemplified in the domain of aerial imagery, where the quality of images captured by drones is often compromised by complex, flight-induced degradations, thereby raising the information entropy and obscuring essential semantic patterns. Conventional super-resolution methods, trained on generic data, fail to restore these unique artifacts, thereby limiting their effectiveness for vessel identification, a task that fundamentally relies on clear pattern recognition. To bridge this gap, we introduce a novel adaptive super-resolution framework for ship images captured by drones. The approach integrates a static stage for foundational feature extraction and a dynamic stage for adaptive scene reconstruction, enabling robust performance in complex aerial environments. Furthermore, to ensure the super-resolution model’s generalizability and effectiveness, we optimize the design of degradation methods based on the characteristics of drone aerial images and construct a high-resolution dataset of ship images captured by drones. Extensive experiments demonstrate that our method surpasses existing state-of-the-art algorithms, confirming the efficacy of our proposed model and dataset. Full article

Offshore oil exploration and the volume of imported crude oil shipping have increased steadily, elevating the risk of oil spills. An advanced offshore oil film identification method is proposed to realize the accurate and robust recognition and segmentation of oil films from marine radar images in offshore oil spill detection. This method integrates feature engineering with an improved Beetle Antennae Search (BAS) optimization algorithm, aiming to address the key issues of low discrimination between oil films and complex marine backgrounds and insufficient spill boundary localization accuracy in radar image analysis. First, the raw radar image was transformed into the Cartesian coordinate system, and a filtering procedure was applied to attenuate interference. Subsequently, the gray distribution and local contrast of the denoised image was further improved. Afterwards, the complexity of the grayscale distribution within each feature map was quantified using Shannon entropy. The Top-K feature maps with the highest entropy values were subsequently used to construct an information-rich subset. The subset was then processed through a pixel-wise averaging strategy to generate a coupled feature image. Then, Otsu threshold was used to refine ocean wave regions. Finally, the oil films were segmented with an improved BAS optimization algorithm. The fitness function of the improved BAS algorithm was augmented through the integration of edge fitting accuracy, and a target-proximity penalization scheme. Through an adaptive step-length modulation paradigm and Perceptual Mechanism, it can achieve a marked improvement in search accuracy and achieving precise segmentation of oil slicks. The detection accuracy of the proposed method is significantly enhanced relative to the traditional BAS algorithm and existing marine radar oil spill detection methods. The IOU, Dice, recall and F1-score reached 81.2%, 89.6%, 85.2%, and 90.1% respectively. This method not only advances the methodological rigor of spill detection but also provides critical data support for the development of more effective control and remediation practices. Full article

We developed a hybrid system combining deep learning-based recognition with fuzzy inference to enhance the detection, recognition, and identification of maritime targets. In the system, deep learning provides strong feature extraction, while fuzzy logic mitigates uncertainty in low-visibility or occluded conditions. The system uses confidence score, screen ratio, and estimated distance as input and processes them through fuzzy inference with triangular membership functions and center of area defuzzification. This integration improves decision robustness and suppresses input noise. Experimental results demonstrate enhanced stability and reduced misjudgment in dynamic maritime environments, highlighting the applicability of a hybrid deep learning–fuzzy inference systems to intelligent ships and unmanned maritime vehicle sensing tasks. Full article

The shipbuilding industry relies heavily on welding, which accounts for approximately 70% of the overall production process. However, the recent decline in skilled workers, together with rising labor costs, has accelerated the automation of shipbuilding operations. In particular, the welding activities are concentrated in the double-bottom region of ships, where collaborative robots are increasingly introduced to alleviate workforce shortages. Because these robots must directly recognize U-shaped weld joints, this study proposes an image-based classification system capable of automatically identifying and classifying such joints. In double-bottom structures, U-shaped weld joints can be categorized into 176 types according to combinations of collar plate type, slot, watertight feature, and girder. To distinguish these types, deep learning-based image recognition is employed. To construct a large-scale training dataset, 3D Computer-Aided Design (CAD) models were automatically generated using Open Cascade and subsequently rendered to produce synthetic images. Furthermore, to improve classification performance, the input images were split into left, right, upper, and lower regions for both training and inference. The class definitions for each region were simplified based on the presence or absence of key features. Consequently, the classification accuracy was significantly improved compared with an approach using non-split images. Full article