TOPO-EPFL/CrossLoc-Benchmark-Datasets

[CVPR'22] CrossLoc benchmark datasets setup and helper scripts.

30
/ 100
Emerging

This project provides organized datasets for researchers working on improving the accuracy of aerial drone localization. It takes raw multimodal synthetic data and real drone-captured images with precise geo-tags and prepares them into training, validation, and testing sets, following established conventions. Scientists and engineers focused on computer vision, robotics, or autonomous systems would use this to develop and benchmark new localization algorithms.

No commits in the last 6 months.

Use this if you are developing or evaluating algorithms for drone localization and need carefully prepared datasets that combine synthetic and real-world aerial imagery with ground truth.

Not ideal if you are looking for a complete, off-the-shelf drone localization solution, as this project focuses solely on providing the data for research.

drone-navigation aerial-robotics computer-vision-research geospatial-localization synthetic-data-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

22

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TOPO-EPFL/CrossLoc-Benchmark-Datasets"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.