AU-AIR Dataset

Multi-modal UAV Dataset for Low Altitude Traffic Surveillance

What is AU-AIR?

AU-AIR dataset is the first multi-modal UAV dataset for object detection.

It meets vision and robotics for UAVs having the multi-modal data from different on-board sensors, and pushes forward the development of computer vision and robotic algorithms targeted at autonomous aerial surveillance.

AU-AIR has several features:

Object detection in aerial images

>2 hours raw videos

32,823 labelled frames

132,034 object instances

8 object categories related to traffic surveillance

Frames are also labelled with time, GPS, IMU, altitude, linear velocities of the UAV

Download

You are free to use AU-AIRdataset and all empirical data and metadata under the CC-BY licence, requesting appropriate credit if you do.

Frames (2.2 GB) Annotations (3.9 MB) Paper

If you have used AU-AIR dataset in a scientific publication, we would appreciate citations to the following paper:

Bozcan, Ilker, and Erdal Kayaan. "AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance." IEEE International Conference on Robotics and Automation (ICRA), 2020, to appear.

Tools

We have prepared a Python package that provides an API to access data and annotations in AU-AIR dataset:
https://github.com/bozcani/auairdataset

Contact

The dataset, website, and API is still under development, and being maintained by Ilker Bozcan. Please contact me via e-mail if you have any questions:
ilker@eng.au.dk

-->