Detection of Abnormal Vessel Behaviour Based on Probabilistic Directed Graph Model

Abstract

To detect the abnormal behaviour of ships in the waters of any jurisdiction and to improve the safety of maritime navigation, the meshing-based method is adopted to obtain discrete trajectory data and a probabilistic directed graph model is established to obtain historical data from ships' AIS (automatic identification systems). The state statistical characteristics of each node in the ship probability map are obtained to detect the navigation state of the ship in real time. By predicting the normal navigation trajectory of the ship, it can be judged whether the ship has the potential to behave abnormally at some moment in the future. Simulation experiments were designed based on a maritime simulator platform. The experimental results indicate that the model can correctly predict abnormal behaviour by ships, including excessive speed and deviation from the channel or normal sailing mode.

Clustering of Marine Vessel Trajectory Data for Routes Planning through Water Areas with Heavy Traffic

“…The objects of clustering are data on the coordinates, speeds, and courses of ships. The work [10] also considers the problem of identifying abnormally moving vessels, the signs are their coordinates, courses and speeds. The water area is divided by a rectangular grid, the routes of ships are represented by the rules of passage between the grid cells.…”

“…The mentioned method [10], based on the determination of traffic rules by statistical methods, is the closest to the approach proposed in this paper, where it is proposed to use clustering methods. This makes it possible to reliably identify the motion parameters and does not require large amounts of initial data.…”

Планирование Маршрутов Судов На Основе Кластеризации Ретроспективных Данных Трафика Акватории

“…В статье [30] рассматривается похожая задача, объектами кластеризации являются данные о координатах, скоростях и курсах судов. В работе [24] также рассмотрена задача идентификации аномально движущихся судов, признаками являются их координаты, курсы и скорости. Акватория разбивается прямоугольной сеткой, маршруты судов представляются правилами перехода между клетками сетки.…”

“…Упомянутый метод [24], основанный на определении правил движения методами статистики, наиболее близок к подходу, предложенному в настоящей работе, где предлагается использовать методы кластеризации. Это позволяет достоверно идентифицировать параметры движения и не требует больших массивов исходных данных.…”

Ship Trajectory Prediction Based on Bi-LSTM Using Spectral-Clustered AIS Data

“…The navigation patterns that were recognized by their work can be applied for providing navigation plans in a confined area. Tang et al showed the ship trajectory obtained from the AIS data on a grid plane and predicted the future path of the ship based on the probabilistic directed graph model and the extrapolation method [15]. The neural network, which is an artificial intelligence model in the form of a neuron in a biological brain, was also used to predict the trajectory of the ship.…”