AI & ML interests

None defined yet.

Recent Activity

Organization Card

AI Drone Map

Every machine, one command.

AIDroneMap builds open source drone photogrammetry. Its engine, AIDM, turns drone images into orthophotos, elevation models, point clouds and textured 3D models, and is built to spread one job across many CPUs and GPUs. The code is on GitHub.

This organisation hosts the open datasets we use to test and benchmark the engine. They are real surveys at the size AIDM is built for: 20 megapixel images, RTK-corrected positions, exactly as the drone recorded them.

Datasets

Dataset Images Size Drone Used for
aidm-vineyard-small 73 0.8 GiB DJI Mavic 3M Every test on real images, in CI and in development
aidm-vineyard 145 1.6 GiB DJI Mavic 3M Matching on repetitive vegetation
aidm-industrial-rtk 503 2.4 GiB DJI Matrice 4E The default benchmark: oblique 3D and accuracy, at the size of a normal job
aidm-solar-park 905 7.9 GiB DJI Mavic 3M The large benchmark: repetitive panels, reflections, densification and meshing

Each dataset has:

  • every image with EXIF and XMP intact;
  • a manifest.json with the size and SHA-256 of every file;
  • a stored zip you can send as is to the AIDM task API or any NodeODX-compatible node.

Every speed or accuracy claim AIDroneMap makes names the dataset and the commit it used.

Using them

Pin a dataset by commit hash, not by branch, so your results can be reproduced:

hf download AIDroneMap/aidm-vineyard-small --repo-type dataset --revision <commit> --local-dir aidm-vineyard-small

Licence

CC BY 4.0, with the attribution "AIDroneMap, provided by ITALDRONI". The maintainer flew every set with his own drones, for flight plan testing under EU open category rules, with no customer involved.

Links

AIDroneMap is maintained by Dimitri Albino and sponsored by ITALDRONI. It is an independent project, not affiliated with or endorsed by WebODM or OpenDroneMap.

models 0

None public yet