Detecting motion anomalies

Maritime anomaly detection: A review

“…They consider that four‐feature variable as constituting a single data vector and statistically model it using a joint probability density function (pdf); in Mascaro, Korb, and Nicholson () and Mascaro, Nicholson, and Korb () different anomalies are searched. The positional ones are somehow data‐related such as “travel over land”; in Willems, van de Wetering, and Van Wijk (), Willems, van Hage, de Vries, Janssens, and Malaisé () and Willems, Scheepens, van de Wetering, and van Wijk () the authors highlight anomalies caused by vessels which sail outside of the designated shipping lanes, such as a cargo vessel which goes off‐route to resupply ocean platforms in the area under investigation; in Lane, Nevell, Hayward, and Beaney () and Lane () deviations from a standard route are detected as a sign of positional anomalies; in Zor and Kittler () anomalous ferry tracks are highlighted; contextual anomalies , for example, vessels whose deviating behavior is directly correlated to the context: for example, Hayes and Capretz () discuss anomalies correlated to time‐related concepts such as seasons, days of the week, workdays versus holidays; for example, a tanker traveling on a ferry route; kinematic anomalies : vessels showing a wrong or unusual course over ground such as sailing in the opposite direction on an established route, as in Kazemi et al (), Mascaro et al (, ) and Anneken, Fischer, and Beyerer () high‐ or low‐speed vessels as in Laxhammar et al () and Laxhammar (); course, velocity and U‐turn anomalies as discussed in Keane (); instantaneous stops and turns as described in Patroumpas et al (); complex anomalies whose detection requires an ensemble of anomaly detectors to capture specific behaviors: in Kowalska and Peel (), complex anomalies such as vessels engaged in drug smuggling, people smuggling and terrorism are classified; loitering vessels whose detection relies on the use of speed gating algorithms (comparing the actual and the estimated future subsequent displacements of vessels) as discussed in Cazzanti and Pallotta (); spoofing behavior as in Katsilieris, Braca, and Coraluppi () and Mazzarella et al (); data‐related anomalies : in Dobrkovic, Iacob, and van Hillegersberg (), incomplete trajectory data are classified as anomalies. …”

“…• vessels showing a wrong or unusual course over ground such as sailing in the opposite direction on an established route, as in Kazemi et al (2013), Mascaro et al (2010Mascaro et al ( , 2014 and Anneken, Fischer, and Beyerer (2015) • high-or low-speed vessels as in Laxhammar et al (2009) and Laxhammar ( 2008); • course, velocity and U-turn anomalies as discussed in Keane (2017);…”

Maritime Anomaly Detection for Vessel Traffic Services: A Survey

“…The anomaly-types route deviation and kinematic deviation are covered by the commonly applied techniques descriptive statistics, clustering or NN-based classification. Most detection techniques which are based on descriptive statistics consider, somehow, outliers in the (spatio-temporal) distribution of the vessels' attributes [27,32,33,46,59,72]. Outliers can be defined with, e.g., distance to the mean or standard deviations.…”

Detection of maritime traffic anomalies using Satellite-AIS and multisensory satellite imageries: Application to the 2021 Suez Canal obstruction

“…(Liu, 2015). Scientists have also mentioned U-turn of vessels as an anomaly (Kowalska and Peel, 2012;Handayani et al, 2013;le Guillarme and Lerouvreur, 2013;Pallotta et al, 2013;Obradović et al, 2014;Keane, 2017;Boztepe, 2019;Rong et al, 2019;Nguyen et al, 2021).…”