Data checked 2026-08-13. Data may be stale - beyond the review cycle.
Review cycles are documented on the Methodology page. Methodology
montefiore-institute/midair-dataset
Dataset Tier A perception_ai MIT
Example and utiliy scripts for the Mid-Air dataset
Engineering Snapshot
Use cases & tasks 5
- Best suited for
-
- UAV perception researchers
- engineers evaluating synthetic data pipelines
- Primary tasks
-
- Training/evaluating visual odometry models
- Training/evaluating depth estimation models
- Navigation algorithm development using ground-truth positions
Stack & ecosystem
- Resource type
- Dataset
- Ecosystem
- perception_ai
License & compliance
- License
-
MIT(Inferred)
Lifecycle & freshness Show
- Maintenance
- Active
- Latest version
- Not recorded
- Last activity
- 2026-06-19
- Last checked
- 2026-08-13
- Verification
- Official confirmed
What It Solves
Provides example and utility scripts for the Mid-Air synthetic UAV dataset to support perception tasks (visual odometry, depth estimation, navigation).
Primary use cases
- Training/evaluating visual odometry models
- Training/evaluating depth estimation models
- Navigation algorithm development using ground-truth positions
Secondary use cases
- Testing data loaders for HDF5 and float16 PNG formats
When to Use
Consider when
- Need synthetic labeled UAV data with ground-truth pose and depth
- Working with HDF5 or float16 PNG modalities
Verify before adopting
- License is inferred MIT, confirm in repo
- Dataset size and access method not specified
Start Here
Adoption Checklist
- Needs verification License is inferred MIT, confirm in repo
- Needs verification Dataset size and access method not specified
Each check stays "needs verification" until an official source confirms it; unconfirmed items are never marked verified.
Known Limitations & Unknowns
Known limitations
- Synthetic data may not reflect real-world distribution
- License inferred not confirmed in dataset metadata
Not publicly verified
- Exact dataset size
- Capture/simulation method
- Access instructions
- Benchmark usage
Alternatives & Related Tools
Alternatives
- uavid — Alternative to
- aeroscapes — Alternative to
How is it used?
Start from the recorded entry points below, then validate against the technical checklist.
- Official site https://github.com/montefiore-institute/midair-dataset
- Repository https://github.com/montefiore-institute/midair-dataset
- Documentation https://github.com/montefiore-institute/midair-dataset
Technical checklist
- OK License identified Recorded: MIT
- OK Maintenance signal Active
- OK Verification status Official confirmed
- OK Source evidence attached 1 source record(s)
- NEEDS REVIEW Latest version recorded Not recorded
Official Links
Metadata & Governance
| License | MIT — Inferred |
|---|---|
| Commercial model | Unknown |
| Maintenance status | Active |
| Verification status | Official confirmed — Confirmed via the official repository API responses in SourceRefs below. |
| Latest version | Not recorded |
| Latest release | Not recorded |
| Last activity | 2026-06-19 |
| Last checked | 2026-08-13 |
| First seen | Not recorded |
Dataset facts
| Task | visual odometry, depth estimation, navigation |
|---|---|
| Modality | synthetic RGB image, synthetic depth, ground-truth drone position |
Facts above come from the official dataset card only; unconfirmed fields stay unknown.
Related Resources & Dependencies
- uavid — alternative to (verified)
- aeroscapes — alternative to (verified)
Recent Activity
New resource: montefiore-institute/midair-dataset
New repository resource added by the sprint promote pipeline.
Related Knowledge
Collections
- Aerial Mapping and Survey Stack — An open-source stack for aerial mapping work from imagery and datasets through photogrammetry processing.
- Aerial Perception Models and Datasets — Source-backed aerial dataset and model repositories for detection and tracking research and prototyping.
- Edge AI Perception Starter — A starting stack for prototyping aerial perception models before edge deployment work.
- Visual Perception Models and Data — Indexed model and dataset repositories for aerial visual perception research and prototyping.