Other

EV-UAV

event-based tiny object detection

Tripod event-camera recordings of tiny flying UAV targets with approximate event-level labels.

Metadata: Complete Metadata source documented Released 2025

Quick facts

Vehicle type
Other
Environment
Outdoor
Data origin
Real-world
Sensor count
1
Ground truth
Not reported
Calibration
Not reported
Annotations
Available

Sensor overview

High-level sensor availability before the detailed sensor records below.

Ground truth

Reference scope, method, rate, coverage, and provenance.

Not reported

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Not reported
Processed parameters
Not reported
Raw calibration data
Not reported
Calibration targets
Not reported

Calibration data

Calibration reproducibility details are not reported.

Notes

Not reported

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

A tripod observer records UAV targets; this is not a UAV-mounted navigation collection. The 147 sequences have a 99/24/24 train/validation/test split; event and label totals use different units.

Labels are approximate and targets are tiny. XYT point clouds encode pixel position and time, not metric 3D geometry; asynchronous streams have no fixed image frame rate.

APS imagery, native IMU, camera calibration and achieved timing accuracy remain unknown. Refer to the original access terms: README license wording includes restrictions alongside its Apache claim.

Cameras

Camera 1

Model
DAVIS346
Setup
Mono
Count
1
Effective cameras
1
Modality
Event
Resolution
346 x 260
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
One ground-mounted DAVIS346 observer releases asynchronous events. README NPZ timestamps are milliseconds; hardware microsecond capability does not define frames or delivered timestamp units. APS/IMU releases are unestablished.

IMUs

Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Additional sensors

Not reported

Annotations

Reported annotation availability and task support.

Availability
Available
Format
NPZ event records with pixel x/y, millisecond t, polarity, binary target/background label and target identity, plus normalized XYT variants. Approximate event-space boxes/masks are not metric 3D object poses.
Class count
Not reported
Semantic segmentation Not reported
Instance segmentation Not reported
Object detection Not reported
Optical flow Not reported
Depth ground truth Not reported

Citation

Citation key and BibTeX kept at the end of the page for reference.

Citation key
chen2025evuav

BibTeX

@misc{chen2025evuav,
  author = {{Nuo Chen} and {Chao Xiao} and {Yimian Dai} and {Shiman He} and {Miao Li} and {Wei An}},
  title = {Event-based Tiny Object Detection: A Benchmark Dataset and Baseline},
  year = {2025},
  eprint = {2506.23575},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.23575v1}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy