Leveraging cross-view geo-localization with ensemble learning and temporal awareness

A car with drone on top of it Read the paper at PLOS ONE!

Our ensemble model achieves a recall accuracy R@1 of 97.74% on the CVUSA dataset and 91.43% on the CVACT dataset (surpassing the current state-of-the-art). Our temporal awareness mechanism converges to R@1 of ~100% by looking at a few steps back in the trip history.

Read the paper at PLOS ONE!
A car with drone on top of it

The Dataset

Part Size (GB) DOI
bdd-trajectories-p1 104.64 10.34740/kaggle/dsv/4993782
bdd-trajectories-p2 5.99 10.34740/kaggle/dsv/4993793
Creative Commons License

This work is licensed under a
Creative Commons Attribution 4.0 International License.