WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
(IEEE Transactions on Aerospace and Electronic Systems)

This is a Pytorch Implementation of WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory.
Due to data confidentiality, we can only offer the code of our proposed methodology and model training framework.

Overall model architecture of WAY

Environment Supports & Python Requirements

• We recommend you to visit Previous Versions (v1.7.1) for instructions to install PyTorch with torchvision==0.8.2.

Use the requirements.txt to install the rest of Python dependencies.

$ pip install -r requirements.txt

Experimental Results

The trajectory begins from the red marker 🔴 (departure port), and progresses to the blue marker 🔵 (destination port). Spatial grids are colored green 🟩 if the model estimated the correct destination at the corresponding phase of the ship operation, else orange 🟧.

The visualization of estimation correctness on a single test example between each comparison model along the ship trajectory progression

Citation

J. S. Kim, et al., “WAY: Estimation of vessel destination in worldwide AIS trajectory,” IEEE Transactions on Aerospace and Electronic Systems, Vol. 59, no. 5, pp. 5961-5977, 2023.

@article{kim2023way,
  title={WAY: Estimation of vessel destination in worldwide AIS trajectory},
  author={Kim, Jin Sob and Park, Hyun Joon and Shin, Wooseok and Park, Dongil and Han, Sung Won},
  journal={IEEE Transactions on Aerospace and Electronic Systems},
  volume={59},
  number={5},
  pages={5961--5977},
  year={2023},
  publisher={IEEE}
}

License

This repository is released under the MIT license.