Maritime anomaly detection is a key technique in intelligent vessel traffic surveillance systems and implementation of maritime situational awareness. In this paper, we propose a method which combines vessel trajectory clustering and Naive Bayes classifier to detect anomalous vessel behaviour in the maritime surveillance system. A similarity measurement between vessel trajectories is designed based on the spatial and directional characteristics of Automatic Identification System (AIS) data, then the method of hierarchical and k-medoids clustering are applied to model and learn the typical vessel sailing pattern within harbour waters. The Naive Bayes classifier of vessel behaviour is built to classify and detect anomalous vessel behaviour. The proposed method has been tested and validated on the vessel trajectories from AIS data within the waters of Xiamen Bay and Chengsanjiao, China. The results indicate that the proposed method is effective and helpful, thus enhancing maritime situational awareness in coastal waters.

https://www.cambridge.org/core/services/aop-cambridge-core/content/view/650D7D7672E0053FA532D9294A734F09/S0373463316000850a.pdf/div-class-title-maritime-anomaly-detection-within-coastal-waters-based-on-vessel-trajectory-clustering-and-naive-bayes-classifier-div.pdf

Maritime Anomaly Detection within Coastal Waters Based on Vessel Trajectory Clustering and Naïve Bayes Classifier

A novel analytic framework of real-time multi-vessel collision risk assessment for maritime traffic surveillance

A novel ship trajectory reconstruction approach using AIS data

A novel method for restoring the trajectory of the inland waterway ship by using AIS data

A novel MP-LSTM method for ship trajectory prediction based on AIS data

The problem of analysing a single vessel's behaviour from real but incomplete Automatic Identification System (AIS) data received by satellite has been investigated. The main objective was to infer the route of any single vessel of interest, utilising the dynamic information decoded from AIS messages. A complete process of route inference using position, speed, course over ground and time stamp information is proposed in this paper. Due to the incompleteness of satellite AIS messages, an algorithm incorporating random deviations is also presented to account for the missing sections of obtained vessel routes. Analysis results from a set of real AIS data have demonstrated the applicability of the proposed algorithms in various scenarios.

https://www.cambridge.org/core/services/aop-cambridge-core/content/view/0A1E582FAC5837D556A405CBF5E64E5E/S0373463313000374a.pdf/div-class-title-inference-of-single-vessel-behaviour-with-incomplete-satellite-based-ais-data-div.pdf

Inference of Single Vessel Behaviour with Incomplete Satellite-based AIS Data

Global analysis of vessel motion patterns has become possible using satellite-based Automatic Identification System (AIS). The concept of space-based AIS needs several satellites to provide complete coverage and high detection probability. However, in early development stages, often only one satellite is launched and due to its limitation of orbit and footprint, received AIS messages are discontinuous. In this paper, we have analysed real AIS data obtained by satellite to form a global maritime surveillance picture. Furthermore, we propose to take advantage of the tensor CANDECOMP/PARAFAC (CP) decomposition to analyse three mode characteristics of the data, which are location, vessel and time. For incomplete data, we exploit the link prediction technique based on tensor factorisation to recover vessel tracks in a specified area. A variant of temporal link prediction based on CP is presented. We illustrate the usefulness of exploiting the three-mode structure of AIS data by simulation, and demonstrate that the track recovery result has acceptable precision.

Changqing Liu

Papers

Inference of Single Vessel Behaviour with Incomplete Satellite-based AIS Data

Vessel Track Recovery With Incomplete AIS Data Using Tensor CANDECOM/PARAFAC Decomposition