Benefiting from video surveillance systems that provide real-time traffic conditions, automatic vessel detection has become an indispensable part of the maritime surveillance system. However, high-level vision tasks generally rely on high-quality images. Affected by the imaging environment, maritime images taken under poor lighting conditions easily suffer from heavy noise and colour distortion. Such degraded images may interfere with the analysis of maritime video by regulatory agencies, such as vessel detection, recognition and tracking. To improve the accuracy and robustness of detection accuracy, we propose a lightweight generative adversarial network (LGAN) to enhance maritime images under low-light conditions. The LGAN uses an attention mechanism to locally enhance low-light images and prevent overexposure. Both mixed loss functions and local discriminator are then adopted to reduce loss of detail and improve image quality. Meanwhile, to satisfy the demand for real-time enhancement of low-light maritime images, model compression strategy is exploited to enhance images efficiently while reducing the network parameters. Experiments on synthetic and realistic images indicate that the proposed LGAN can effectively enhance low-light images with better preservation of detail and visual quality than other competing methods.

This study summarises the scenario of maritime traffic anomalies, like the increased congestion and U-turn of ships caused by the ship grounding in the Suez Canal in March 2021. Here, satellite automatic identification system based ship trajectories, and Sentinel-1 and Sentinel-2 images based ship positions are analysed after subdividing the study area into seas, lakes and canals. The results show that the blockage affected the maritime traffic for more than three weeks, waiting ship numbers increased from 5 to 122, and daily one to three ships made a U-turn between 23 and 31 March in the Gulf of Suez. Ship density also increased to more than double in Bitter Lakes with a minimum waiting time of 7 days. Hence, to avoid such prolonged waiting of ships, we propose a warning method based on the sharp speed decrease rate, U-turn and congestion.

The regional ship collision risk assessment for multiple ships in restricted waters is of great significance to the early warning of ship collision risk and the intelligent supervision of maritime traffic. Given the existed method of regional ship collision risk assessment without considering the impact of ship aggregation density, this paper proposes a novel regional ship collision risk assessment method that considers the aggregation density (AD) of the clusters of encounter ships (CES) for intelligent surveillance and navigation. The effectiveness of the proposed method has been examined by the experimental case study in the waters of Xiamen, China, and analysis has been compared with other existed studies to show the advantages of the new proposed algorithm. The results show that the study method can more intuitively and effectively quantify the temporal and spatial distribution of regional collision risks in the restricted sea area. The proposed method can improve the efficiency of traffic management when monitoring the ship collision risks in macroscopic view, and assist the safety of manned and unmanned ship navigation.

A ship's perception of risk is an important basis for collision avoidance. To improve such perception, several risk measurement parameters on the ship domain are determined, including the approach factor, the time to domain violation (TDV) and the possible collision domain. Then, a risk hierarchy prewarning (RHP) model based on the violation detection of a ship domain is proposed, in which a two-level alarm scheme is adopted accordingly. A low-intensity alarm will be activated by reaching the minimum approach factor and the TDV threshold, and a high-intensity alarm will be activated by the factor of the possible collision domain and the TDV threshold. Subsequently, a novel guard zone in ARPA radar utilising the RHP model has been developed to establish a ship's risk perception system for officers on watch at sea. The model proposed in this paper can not only enhance the veracity of risk assessment around our own ship, but also be used as a decision support system for collision avoidance.

Automatic ship reporting systems (AIS – Automatic identification System, LRIT – Long Range Identification and Tracking, VMS – Vessel Monitoring System) today allow global tracking of ships. One way to display the results is in a map of current ship positions over an area of interest, the Maritime Situational Picture (MSP). The MSP is dynamic and must be created by fusing the reporting systems' messages, constructing ship tracks and predicting ship positions to correct for latency especially in the case of AIS received by satellite which forms the bulk of the data. This paper discusses the completeness of the resulting MSP and the accuracy of its positions, quantifying the additional value of the individual data sources.