Data checked 2026-08-13. Data may be stale - beyond the review cycle.
Review cycles are documented on the Methodology page. Methodology
dronefreak/Aeroscapes
Dataset Tier A perception_ai cc-by-sa-4.0
Aeroscapes: Aerial Semantic Segmentation Dataset Unofficial redistribution of the AeroScapes dataset under the original CC BY-SA 4.0 license. Disclaimer This repository is not an official release of the AeroScapes dataset. The AeroScapes dataset was created by Ishan Nigam, Chen Huang, and Deva Ramanan, with dataset collection and manual annotation supported by Autel Robotics. They retain all copyr
Engineering Snapshot
Use cases & tasks 6
- Best suited for
-
- Semantic segmentation model training
- UAV perception algorithm development
- Aerial image analysis research
- Primary tasks
-
- Training semantic segmentation models for UAV navigation and obstacle detection
- Evaluating segmentation algorithms on aerial imagery
- Developing scene understanding for low-altitude autonomous systems
Stack & ecosystem
- Resource type
- Dataset
- Ecosystem
- perception_ai · semantic-segmentation · aerial-imagery · uav · drone · remote-sensing
License & compliance
- License
-
cc-by-sa-4.0(Inferred)
Lifecycle & freshness Show
- Maintenance
- Active
- Latest version
- Not recorded
- Last activity
- 2026-08-01
- Last checked
- 2026-08-13
- Verification
- Official confirmed
What It Solves
Provides an aerial semantic segmentation dataset for training and evaluating computer vision models on UAV-captured imagery.
Primary use cases
- Training semantic segmentation models for UAV navigation and obstacle detection
- Evaluating segmentation algorithms on aerial imagery
- Developing scene understanding for low-altitude autonomous systems
Secondary use cases
- Transfer learning for remote sensing applications
- Augmenting datasets for drone-based monitoring systems
- Benchmarking vision models on real-world aerial data
When to Use
Consider when
- You need real-world UAV imagery for semantic segmentation
- Your project requires understanding land cover, buildings, or vegetation from aerial views
- You are developing perception systems for low-altitude autonomous flight
Verify before adopting
- Confirm the exact dataset size and class definitions match your needs
- Check the annotation format compatibility with your training pipeline
- Verify the 'unofficial redistribution' status and any restrictions from the original authors
Start Here
Adoption Checklist
- Needs verification Confirm the exact dataset size and class definitions match your needs
- Needs verification Check the annotation format compatibility with your training pipeline
- Needs verification Verify the 'unofficial redistribution' status and any restrictions from the original authors
Each check stays "needs verification" until an official source confirms it; unconfirmed items are never marked verified.
Known Limitations & Unknowns
Known limitations
- Unofficial redistribution; original dataset is by Nigam et al.
- Specific size is categorized as 1K<n<10K; exact count not provided
Not publicly verified
- Exact number of images or annotations
- Specific class taxonomy details
- Geographic locations or flight conditions of the data
Alternatives & Related Tools
Alternatives
- inria-aerial — Alternative to
Related tools
- ultralytics — Used for
How is it used?
Start from the recorded entry points below, then validate against the technical checklist.
- Official site https://huggingface.co/datasets/dronefreak/Aeroscapes
- Documentation https://huggingface.co/datasets/dronefreak/Aeroscapes
Technical checklist
- OK License identified Recorded: cc-by-sa-4.0
- 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 | cc-by-sa-4.0 — 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 | 2026-08-01 |
| Last checked | 2026-08-13 |
| First seen | Not recorded |
Dataset facts
| Task | semantic-segmentation |
|---|---|
| Modality | image, text, geospatial |
| License (dataset card) | cc-by-sa-4.0 |
| Size category | 1K<n<10K |
| Downloads | 884 |
Facts above come from the official dataset card only; unconfirmed fields stay unknown.
Related Resources & Dependencies
- ultralytics — used for (confirmed)
- inria-aerial — alternative to (verified)
Recent Activity
New resource: dronefreak/Aeroscapes
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.