Recognizing ship behavior is important for maritime situation awareness and intelligent transportation management. Some scholars extracted ship behaviors from massive trajectory data by statistical analysis. However, the meaning of the behaviors, i.e., semantic meanings of behaviors and their relationships, are not explicit. Ship behaviors are affected by navigational area and traffic rules, so their meanings can be obtained only in specific maritime situations. The work establishes the semantic model of ship behavior (SMSB) to represent and reason the meaning of the behaviors. Firstly, a semantic network is built based on maritime traffic rules and good seamanship. The corresponding detection methods are then proposed to identify basic ship behaviors in various maritime scenes, including dock, anchorage, traffic lane, and general scenes. After that, dynamic Bayesian network (DBN) is used to reason potential ship behaviors. Finally, trajectory annotation and semantic query of the model are validated in the different scenes of harbor. The basic behaviors and potential behaviors in all typical scenes of any harbor can be obtained accurately and expressed conveniently using the proposed model. The model facilitates the ships behavior research, contributing to the semantic trajectory analysis.@en

The special SOX Emission Control Areas (ECAs) had been established to reduce pollution in coastal region. Real-time ship emissions monitoring should be strengthened in SECA. The mainstream remote measurements of gas concentrations are the optical or sniffer monitoring methods. Exhaust emissions location and intensity could not be acquired by methods of remote measurements. Based on monitoring multiple sensors, this paper presents a new inversion method for characteristics of single ship emissions. The Gaussian plume diffusion model (GPDM) and Genetic Algorithm (GA) to calculate the position and concentration of single ship emissions. Simultaneous measurements of CO2, SO2 and NOX concentrations can be achieved by several monitoring stations on the wharf. Multiple solutions of the ship emissions location and intensity have been calculated by the selection, crossover and mutation of GA. As parameters of Gaussian plume diffusion model, those solutions are employed to calculate the gas concentrations on the location of the monitoring stations. The optimal one can be acquired by comparing the measurement and the calculation. The presented algorithm is verified by the real practice for Yantian harbor in Shenzhen.@en

With the booming of marine industry, occurrence of maritime oil spills will not only loss of life and property, but also has brought about a long-term and bad influence to ocean environment and ecosystem system. This paper introduces a platform architecture for marine oil spill response capacity visualization, and elaborates the visualization of oil spill emergency elements, emergency resources dynamic interconnection and regional oil spill response capability with marine oil spill accidents. The platform is based on the B/S (browser/server) framework along with the tools of Baidu map API and MapV visualization system to realize the oil spill emergency resources visualization, oil spill emergency capability visualization and oil spill emergency response. The successful running of the platform provides scientific support for the decision-making in handling the oil spill emergency.@en