Anomaly Detection Methods for Maritime Search and Rescue

Ryan Sime, Rohan Loveland

2025

Abstract

Anomaly detection methods are employed to find swimmers and boats in open water in drone imagery from the SeaDronesSee dataset. The anomaly detection methods include variational autoencoder-based reconstruction loss, isolation forests, and the Farpoint algorithm. These methods are used with both the original feature space of the data and the encoded latent space representation produced by the variational autoencoder. We selected six images from the dataset and break them into small tiles, which are ranked by anomalousness by the various methods. Performance is evaluated based on how many tiles must be queried until the first positive tile is found compared to a random selection method. We find that the reduction of tiles that must be queried can range into factors in the thousands.

Paper Citation

in Harvard Style

Sime R. and Loveland R. (2025). Anomaly Detection Methods for Maritime Search and Rescue. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 764-770. DOI: 10.5220/0013263000003905

in Bibtex Style

@conference{icpram25,
author={Ryan Sime and Rohan Loveland},
title={Anomaly Detection Methods for Maritime Search and Rescue},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={764-770},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013263000003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Anomaly Detection Methods for Maritime Search and Rescue
SN - 978-989-758-730-6
AU - Sime R.
AU - Loveland R.
PY - 2025
SP - 764
EP - 770
DO - 10.5220/0013263000003905
PB - SciTePress