Exploiting the Earth's Spherical Geometry to Geolocate Images

Abstract

Existing methods for geolocating images use standard classification or image retrieval techniques. These methods have poor theoretical properties because they do not take advantage of the earth’s spherical geometry. In some cases, they require training data sets that grow exponentially with the number of feature dimensions. This paper introduces the Mixture of von-Mises Fisher (MvMF) loss function, which is the first loss function that exploits the earth’s spherical geometry to improve geolocation accuracy. We prove that this loss requires only a dataset of size linear in the number of feature dimensions, and empirical results show that our method outperforms previous methods with orders of magnitude less training data and computation.

Cite

Text

Izbicki et al. "Exploiting the Earth's Spherical Geometry to Geolocate Images." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019. doi:10.1007/978-3-030-46147-8_1

Markdown

[Izbicki et al. "Exploiting the Earth's Spherical Geometry to Geolocate Images." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019.](https://mlanthology.org/ecmlpkdd/2019/izbicki2019ecmlpkdd-exploiting/) doi:10.1007/978-3-030-46147-8_1

BibTeX

@inproceedings{izbicki2019ecmlpkdd-exploiting,
  title     = {{Exploiting the Earth's Spherical Geometry to Geolocate Images}},
  author    = {Izbicki, Mike and Papalexakis, Evangelos E. and Tsotras, Vassilis J.},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2019},
  pages     = {3-19},
  doi       = {10.1007/978-3-030-46147-8_1},
  url       = {https://mlanthology.org/ecmlpkdd/2019/izbicki2019ecmlpkdd-exploiting/}
}