Abstract
Ship trajectory prediction is a key requisite for maritime navigation early warning and safety, but accuracy and computation efficiency are major issues still to be resolved. The research presented in this paper introduces a deep learning framework and a Gate Recurrent Unit (GRU) model to predict vessel trajectories. First, series of trajectories are extracted from Automatic Identification System (AIS) ship data (i.e., longitude, latitude, speed, and course). Secondly, main trajectories are derived by applying the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. Next, a trajectory information correction algorithm is applied based on a symmetric segmented-path distance to eliminate the influence of a large number of redundant data and to optimize incoming trajectories. A recurrent neural network is applied to predict real-time ship trajectories and is successively trained. Ground truth data from AIS raw data in the port of Zhangzhou, China were used to train and verify the validity of the proposed model. Further comparison was made with the Long Short-Term Memory (LSTM) network. The experiments showed that the ship’s trajectory prediction method can improve computational time efficiency even though the prediction accuracy is similar to that of LSTM.
Highlights
Automatic Identification System (AIS) data provide real-time trajectory data which can be used to monitor ship’s navigation status and trigger alert mechanisms for ship collision avoidance, maritime monitoring, trajectory clustering, ship traffic flow predicting, and maritime accident investigations [1]
The research presented in this paper introduces a deep learning theoretical framework and a Gate Recurrent Unit (GRU) model to predict vessel trajectories
Figure trajectory and predicted trajectory thatthat usesuses the the GRU. This a ship trajectory prediction framework based based on a recurrent neural network
Summary
AIS data provide real-time trajectory data which can be used to monitor ship’s navigation status and trigger alert mechanisms for ship collision avoidance, maritime monitoring, trajectory clustering, ship traffic flow predicting, and maritime accident investigations [1]. To improve the safety of ships sailing in the environment of complex and changeable seas, it is necessary to provide trajectory prediction and danger warning functions to a ship’s intelligent navigation system. A Bayesian probability trajectory prediction model based on a Gaussian process is introduced. The research presented in this paper introduces a deep learning theoretical framework and a Gate Recurrent Unit (GRU) model to predict vessel trajectories. A recurrent neural network is applied to predict and train real-time ship trajectories.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have