[Poster] Aircraft Detection and State Estimation in Satellite Images

Authors

  • Peder Heiselberg Technical University of Denmark

DOI:

https://doi.org/10.59490/joas.2023.7215

Abstract

Unidentified flying objects are aircraft that do not continuously broadcast ADS-B. They pose a risk to air traffic safety. In this study, we introduce a method for detecting and estimating the state of aircraft in Sentinel-2 multispectral satellite images. We construct a dataset of 579 ADS-B annotated aircraft from 69 Sentinel-2 images. A CNN is trained on the dataset to aircraft state vector i.e. position, velocity, heading, and altitude. This work allows real-time monitoring of flying objects in satellite images.

Metrics

Metrics Loading ...

Downloads

Published

2023-10-30

How to Cite

Heiselberg, P. (2023). [Poster] Aircraft Detection and State Estimation in Satellite Images. Journal of Open Aviation Science, 1(2). https://doi.org/10.59490/joas.2023.7215