Autoencoder-Based Maritime Anomaly Detection
A model capable of detecting anomalous ship behavior for a given geographical region.
Main Characteristic
This model is trained on a region surrounding the Horten-Moss crossing in the Oslo fjord in Norway. The base model architecture is a recurrent autoencoder.
Using an input ship trajectory, the model will identify if the ship behavior is anomalous or normal, based on historical data in the region.
The model has support for dockerization to function as a REST API.
Business Categories
Maritime Sector
Last updated
26.01.2024 - 21:45