GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection

Duong Nguyen (1) , Rodolphe Vadaine (2) , Guillaume Hajduch (3) , René Garello (4) , Ronan Fablet (5)

1 IMT Atlantique - SC - Département Signal et Communications
2 GEVES Station nationale d'essais de semences
3 CLS - Collecte Localisation Satellites
4 IMT Atlantique - ITI - Département lmage et Traitement Information
5 Lab-STICC_TB_CID_TOMS

Representing maritime traffic patterns and detecting anomalies from them are key to vessel monitoring and maritime situational awareness. We propose a novel approach-referred to as GeoTrackNet-for maritime anomaly detection from AIS data streams. Our model exploits state-of-the-art neural network schemes to learn a probabilistic representation of AIS tracks, then uses a contrario detection to detect abnormal events. The neural network helps us capture complex and heterogeneous patterns in vessels' behaviors, while the a contrario detection takes into account the fact that the learned distribution may be location-dependent. Experiments on a real AIS dataset comprising more than 4.2 million AIS messages demonstrate the relevance of the proposed method.

Mots clés: AIS; maritime surveillance; deep learning; anomaly detection; variational recurrent neural networks; a contrario detection; Index Terms-AIS

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Duong Nguyen, Rodolphe Vadaine, Guillaume Hajduch, René Garello, Ronan Fablet. GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection. 2019. ⟨hal-02388260v2⟩