Ship Segmentation Research Articles

MLANet: A Robust Ship Segmentation Network Based on Multilevel Multiattention Feature Fusion for Complex Maritime Background Environments

MLANet: A Robust Ship Segmentation Network Based on Multilevel Multiattention Feature Fusion for Complex Maritime Background Environments

Agent-based modeling system for real-time characterization of film thickness in digital twin coating

In the automated spraying workshop of ship segments, poor visibility caused by dust and fog hampers the effectiveness of the video monitoring system. The traditional method used during the automated spraying process fails to provide real-time measurement of film thickness and prediction of spraying quality, resulting in uneven film thickness and high rework rates. Robotic spraying technology also faces challenges, such as the time-consuming and labor-intensive process of building and computing a highly reliable Computational Fluid Dynamics (CFD) based spraying film-forming simulation model, which cannot be reflected in real-time during the spraying process. The digital twin characterization method, based on the agent model, offers a solution to these limitations and challenges, providing new ideas and approaches for improving and optimizing the spray film formation model. This paper presents the development of a real-time characterization system for sprayed film thickness based on digital twin technology. The spraying film thickness under different working conditions is obtained using Ansys-Fluent simulation software by varying the gun height and gun speed. The predictive model for spraying film thickness is then established using the obtained simulation data and the corresponding gun height and gun speed, employing the surrogate modeling method (BP neural network). The real-time characterization system for spraying film thickness is developed by combining C# and Unity3D. Finally, in order to ensure the accuracy of the predictive model, a spraying experimental platform is built to verify the accuracy of the predictive model.

MSCF-Net: Attention-Guided Multi-Scale Context Feature Network for Ship Segmentation in Surveillance Videos

MSCF-Net: Attention-Guided Multi-Scale Context Feature Network for Ship Segmentation in Surveillance Videos

Ship Segmentation via Combined Attention Mechanism and Efficient Channel Attention High-Resolution Representation Network

Ship Segmentation via Combined Attention Mechanism and Efficient Channel Attention High-Resolution Representation Network

Opportunities and Challenges for Malta’s Cruise Tourism and Its Growth Potential

Summary This case study provides an analysis of cruise tourism in Malta for the period from 2002 to 2033, with a specific focus on the year 2023. Malta has experienced a significant growth in cruise tourism over the years, predominantly attributable to the expansion of its home-port function and to the growth in average ship capacity. The comprehensive examination of cruise traffic in 2023 was conducted by employing a range of assessments, including market-related evaluations, and passenger and ship segmentation. A projection of cruise traffic for the ensuing decade was developed. Additionally, a thorough examination was undertaken of the principal tourist attractions in Malta, with attention given to those that are negatively impacted by the problem of overtourism. Furthermore, potential resolutions are proposed with the additional objective of enhancing the destination’s environmental sustainability. Information © The Author 2024

Conceptual design of shore station for an innovative waste collecting vessel

Marine environment protection legislation in the EU requires ships to return waste they generate on voyages to waste-reception facilities in ports. In many harbors there is a need to expand the port infrastructure to enable the operation of Waste Collecting Vessels (WCVs). In addition, these vessels can perform new functions of cleaning port basins and adjacent waterways. A novelty in the presented research on the conceptual design of the shore station is the inclusion of new requirements for an autonomy and modularization of the vessel. The shore station was designed in the form of a floating pontoon, taking into account the various functional requirements addressed in the ship's conceptual design stage. The pontoon consists of modules corresponding to the ship segments moored in them. The conceptual design was intentionally defined in a generalized form to allow for further development and adaptation to local requirements at individual ports.

Correction: Bu et al. A Decomposition-Based Multi-Objective Evolutionary Algorithm for Solving Low-Carbon Scheduling of Ship Segment Painting. Coatings 2024, 14, 368

In the original publication [...]

A Decomposition-Based Multi-Objective Evolutionary Algorithm for Solving Low-Carbon Scheduling of Ship Segment Painting

Ship painting, as one of the three pillars of the shipping industry, runs through the whole process of ship construction. However, there are low scheduling efficiency and excessive carbon emissions in the segmental painting process, and optimizing the scheduling method is an important means to achieve the sustainable development of the ship manufacturing industry. To this end, firstly, a low-carbon scheduling mathematical model for the segmented painting workshop is proposed, aiming to reduce carbon emissions and improve the painting efficiency of the segmented painting workshop. Second, an artificial bee colony algorithm designed based on a decomposition strategy (MD/ABC) is proposed to solve the model. In the first stage, five neighborhood switching methods are designed to achieve the global search employed for each solution. In the second stage, the Technique of Ordering the Ideal Solutions (TOPSIS) improves the competition mechanism through the co-evolution between neighboring subproblems and designs the angle to define the relationship between neighboring subproblems to enhance the localized search and improve population quality. The solution exchange strategy is used in the third stage to improve the efficiency of the algorithm. In addition, a two-stage coding method is designed according to the characteristics of the scheduling problem. Finally, the algorithm before and after the improvement and with other algorithms is analyzed using comparative numerical experiments. The experimental results show the effectiveness of the algorithm in solving the low-carbon scheduling problem of ship segmental painting and can provide reliable guidance for the scheduling program of segmented painting workshops in shipyards.

Numerical Study of Effects of Inhomogeneous Roughness on the Ship Friction Resistance

The cleanliness of a ship hull is crucial for energy saving. Biofouling, which can cause microbiological corrosion, can also increase ship resistance. If left unchecked, this can lead to inefficient energy use and increased emissions, contributing to global warming. Ship resistance is a critical factor in ship design, which affects ship powering. The analysis of friction resistance due to biofouling on a ship hull requires an examination of the distribution of roughness height (ks), which is randomly distributed. In this study, an analysis of friction resistance coefficient (CF) due to inhomogeneous roughness is carried out with the help of CFD simulations with a full-scale model at 19 kn and 24 kn. The roughness of three ship segments, namely aft-hull, midship, and fore-hull, varies with ks values of 125 μm (P), 269 μm (Q), and 425 μm (R), respectively, while maintaining the same wetted surface area (S) in each segment. According to the simulation results, the RQP model produces the highest CF of 2.154 x 10-3, while the PQR model produces the smallest CF of 2.119 x 10-3 each at speed 24 knots. The CF contributes an average of 72.2% CT.

Infrared Ship Segmentation based on Weakly-supervised and Semi-supervised Learning

Infrared Ship Segmentation based on Weakly-supervised and Semi-supervised Learning

DRSNet: Rotated-ROI Ship Segmentation for SAR Images Based on Dual-Scale Cross Attention

DRSNet: Rotated-ROI Ship Segmentation for SAR Images Based on Dual-Scale Cross Attention

GHG emission reduction measures and alternative fuels in different shipping segments and time horizons – A Delphi study

The bodies governing the global maritime industry have set short- and long-term targets for reducing GHG emissions from shipping. Various emission abatement measures exist, but their applicability in different contexts widely varies. The situation is unclear, especially for the so-called alternative fuels. These fuels hold the biggest emission reduction potential. Conversely, they are expensive, and the feasibility of investments in those technologies has high uncertainty. Despite a growing body of knowledge on the characteristics and potential of alternative fuels, no consensus exists as to which fuels would be best for each segment of the maritime industry – in the near future and the long run. We contribute with a Delphi study to fill this gap. Our results pinpoint the differences between the shipping segments and the short- and long-term choices for alternative fuels.

MrisNet: Robust Ship Instance Segmentation in Challenging Marine Radar Environments

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

DANet: Dual-Branch Activation Network for Small Object Instance Segmentation of Ship Images

In maritime scenes, instance segmentation of small object ships is of vital importance. Small ship objects in images have the characteristics of smaller size, lower image cover rate and fewer appearance features. However, existing instance segmentation methods fail to recognize and segment them and can cause missed ship segmentation. To this end, we propose a dual-branch activation network (DANet) for small object instance segmentation of ship images. DANet consists of a Feature Encoding, a Dual Mask Branch, and a Dual Activation Branch. The Feature Encoding adopts feature refinement and a pyramid structure to obtain more fine-grained features. The proposed Dual Mask Branch extracts dual-path mask features for encoding small object information. We propose a Dual Activation Branch to activate more small object regions and generate instance features. Furthermore, we build the Small ShipInsSeg dataset from a total of 5,256 images and 11,612 instances. The experiments show that DANet outperforms the SparseNet baseline and achieves state-of-the-art performance. Additionally, our method achieves a good trade-off between accuracy and speed.

Design and Process Planning of Non-Structured Surface Spray Equipment for Ultra-Large Spaces in Ship Section Manufacturing

Sandblasting and coating constitute a critical phase in ship manufacturing, a process currently predominantly reliant on manual labor. To enhance the efficiency and quality of the coating process for shipbuilding segments, to address the challenges shipbuilding companies face in labor recruitment and shortage, and to simultaneously elevate the level of intelligent manufacturing for ship segment coating, this research investigates equipment suitable for large-scale, non-structural surface coating in shipbuilding segments, considering the unique features of ship segments and the customary techniques employed by shipbuilding companies. The structure, size parameters, and principal components of the coating equipment are determined. Regular workspace with high performance is designated and the coating process is planned based on the working environment and the curvature characteristics of the surface to be coated. The results demonstrate that the proposed coating equipment improved efficiency by 300% compared to manual painting, providing a novel automated solution for the coating of ship segments.

Variable Velocity Coating Thickness Distribution Model for Super-Large Planar Robot Spraying

This study proposed a dynamic optimization method for spray gun flow to address the issue of uneven film thickness in the acceleration and deceleration section of the z-shaped spray trajectory in large plane ship segments. The method takes into account the acceleration and deceleration section of the spray trajectory and improves the film thickness distribution. The study first established a static vertical spray coating growth model of the spray gun without considering the acceleration and deceleration of the spray trajectory. Then, we used an integral method to optimize the coating uniformity and established a film thickness distribution model. The optimization of spray speed and spray spacing is crucial in the use of variable flow spray guns. It is assumed that the acceleration and deceleration sections of the spraying trajectory are linear and symmetrical, which forms the basis for establishing a mathematical model for the variable flow spray gun. To determine the flow of the spray gun at different speeds in the acceleration and deceleration sections, the pattern search method was adopted. A section of a ship was used as an example for this study. In this study, we utilized numerical simulations to compare the uniformity of paint film thickness when using a spray gun with a constant flow versus variable flow. The results indicate that when taking into account the acceleration and deceleration section of the spray trajectory, the film thickness was more uniform with a variable flow. These findings demonstrate the feasibility and effectiveness of the proposed method.

Economics of shore power under different access pricing

Providing shore power to ships at berth is recognized as an effective measure to reduce external costs of maritime transport. However, shore power technology is subject to barriers, part of which relate to insufficient incentives for providers and users. Regulatory proposals in the EU have targeted liner shipping segments to be covered by a shore power mandate. There is much less research focused on non-liner segments of shipping, though these represent a significant share of at-berth emissions. This study uses a relatively simple modelling framework to analyze whether public investments in shore power deployment could be socio-economically beneficial. We find that investing in the provision of shore power in ports can be socio-economically beneficial also when aimed at bulk carriers, tankers and general cargo ships. We also find that the pricing of access affects expected uptake and consequently whether or not shore power investments yield benefits in proportion to costs.

Multi-Scale Similarity Guidance Few-Shot Network for Ship Segmentation in SAR Images

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot learning has the ability to learn quickly from a few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder–decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN, and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-art.

SwinSeg: Swin transformer and MLP hybrid network for ship segmentation in maritime surveillance system

Accurate identification and segmentation of moving ships to ensure maritime traffic safety has become an important task in maritime intelligent transportation system. With the development of artificial intelligence, maritime surveillance system based on computer vision has been widely studied. However, there are still some problems when applied to the actual maritime scene. For example, the degradation of visible image quality caused by rain, haze, and low illumination leads to a significant reduction in segmentation performance. To improve the performance of ship identification and segmentation under adverse weather conditions, we propose SwinSeg, a hybrid network combining Swin Transformer and lightweight multi-layer perceptron (MLP). To address the lack of suitable open-source datasets in the community, we have collected and labeled a semantic segmentation dataset of marine ships, named SeaShipsSeg. It consists of 1200 visible marine ship images and covers six common ship types (bulk cargo carrier, container ship, fishing boat, general cargo ship, ore carrier, and passenger ship). In addition, synthetic degraded images are added to the dataset to increase its diversity and improve the generalization ability of the network. The experimental results show that the performance of our method is significantly better than the state-of-the-art (SOTA) methods in terms of segmentation accuracy, robustness, and efficiency under different weather conditions. The dataset is available at https://github.com/GrimreaperZ-creator/SeaShipsSeg.

Modern Logistics Technology Based Ship Segment Outfitting Scheme

Shipbuilding occupies an important position in national defense and economy, which belongs to a typical large-scale complex production. In the modern shipbuilding mode, the segment outfitting process is the bottleneck of the whole shipbuilding. The outfitting cycle is long, and there are many resource constraints in the process. At present, China’s shipbuilding enterprises adopt the method of storage-yard based segment outfitting, which is relatively extensive in management and low in efficiency. This article points out that storage-yard based segment outfitting depends on complex dynamic scheduling, involving complex theoretical planning problems such as three-dimensional spatiotemporal coordination and flatbed transporter scheduling. Inspired by the segment outfitting line proposed in Germany and the modern logistics technology, the station design of the segment outfitting line was determined, and the centralized distribution with the intelligent logistics mode of outfitting parts is analyzed. The material and personnel coordination framework of the segment outfitting line is established. In the end, an assembly line based collaborative scheme of ship segment outfitting is proposed, with the characteristics of plan oriented, comprehensive perception, and dynamic synergistic.