suojiashun/HIT-UAV-Infrared-Thermal-Dataset

What It Solves

Need for high-altitude infrared thermal imagery to develop and evaluate UAV-based object detection algorithms.

Primary use cases

• Training and benchmarking object detection models (standard and oriented bounding boxes) on UAV thermal video
• Evaluating domain adaptation from visible to thermal spectra
• Developing real‑time detection pipelines for surveillance, inspection, and SAR

Secondary use cases

• Cross‑modality dataset fusion studies
• Benchmarking oriented bounding box detectors
• Testing robustness to altitude variations (60‑130 m)

When to Use

Consider when

• Your application requires thermal infrared imagery
• You need annotations in XML or JSON format (standard or oriented boxes)
• Your operating altitude falls within 60‑130 m
• You are limited to the four provided classes (Person, Bicycle, Car, OtherVehicle)

Verify before adopting

• ? Confirm that the CC‑BY‑4.0 license fits your distribution requirements
• ? Check that your hardware can handle 4 347 0 frames (~2898 images) for training
• ? Validate that the provided annotation types match your model’s expected format
• ? Ensure the altitude range matches your flight profile

Where It Fits

Stack layer data

Start Here

Adoption Checklist

• Needs verification Confirm that the CC‑BY‑4.0 license fits your distribution requirements
• Needs verification Check that your hardware can handle 4 347 0 frames (~2898 images) for training
• Needs verification Validate that the provided annotation types match your model’s expected format
• Needs verification Ensure the altitude range matches your flight profile

Each check stays "needs verification" until an official source confirms it; unconfirmed items are never marked verified.

Known Limitations & Unknowns

Known limitations

• Only four object classes (Person, Bicycle, Car, OtherVehicle)
• Flight altitude limited to 60‑130 m
• Modality limited to infrared thermal imagery (no RGB or multispectral)

Alternatives & Related Tools

Alternatives

• dronevehicle — Alternative to
• anti-uav — Alternative to

How is it used?

Start from the recorded entry points below, then validate against the technical checklist.

• Official site https://github.com/suojiashun/HIT-UAV-Infrared-Thermal-Dataset
• Repository https://github.com/suojiashun/HIT-UAV-Infrared-Thermal-Dataset
• Documentation https://github.com/suojiashun/HIT-UAV-Infrared-Thermal-Dataset

Technical checklist

• OK License identified Recorded: CC-BY-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

Dataset facts

Facts above come from the official dataset card only; unconfirmed fields stay unknown.

Related Resources & Dependencies

• dronevehicle — alternative to (verified)
• anti-uav — alternative to (verified)

Recent Activity

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.