Citation¶
If you use this software, please cite the software and the paper. Both entries are generated from CITATION.cff, which GitHub also offers under "Cite this repository".
Journal article¶
Preferred for any use of the framework. The article is open access.
Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery. Transportation Research Part C: Emerging Technologies 178, 105205 (2025). doi:10.1016/j.trc.2025.105205
@article{fonod2025advanced,
title = {Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery},
author = {Fonod, Robert and Cho, Haechan and Yeo, Hwasoo and Geroliminis, Nikolas},
journal = {Transportation Research Part C: Emerging Technologies},
volume = {178},
pages = {105205},
year = {2025},
publisher = {Elsevier},
doi = {10.1016/j.trc.2025.105205},
url = {https://doi.org/10.1016/j.trc.2025.105205}
}
Software archive¶
When referencing or building on the code itself. The Zenodo DOI 10.5281/zenodo.12119542 always resolves to the latest release; the entry below records version 1.6.0.
@software{fonod2026geo-trax,
author = {Fonod, Robert},
title = {Geo-trax: A Comprehensive Framework for Georeferenced Vehicle Trajectory Extraction from Drone Imagery},
year = {2026},
month = oct,
version = {1.6.0},
license = {MIT},
doi = {10.5281/zenodo.12119542},
url = {https://github.com/rfonod/geo-trax}
}
Datasets¶
Released on Zenodo alongside the article:
- Songdo Traffic: about 700,000 georeferenced vehicle trajectories produced with geo-trax, doi:10.5281/zenodo.13828383.
- Songdo Vision v1: the annotated aerial images the default detector was trained on, doi:10.5281/zenodo.13828408.
- Songdo Vision v2: an annotation-quality release of the same images, doi:10.5281/zenodo.21728430.