30.134

KILOMETERS

30

HOURS OF RECORDING

12

LOCATIONS

The free AUTOMATUM DATASET

Recent innovation in highly automated driving in industrial and scientific domains has created a growing demand for logical description of statistically meaningful real-world motion data. On one hand this data supports learning-based probabilistic methods in software development while on the other it allows validation and testing.


The AUTOMATUM DATA dataset is a new dataset which was generated initially using 12 characteristic highway-like scenes from 30 hours of drone videos. The processing pipeline for determining the object trajectories was validated with reference vehicles, where the relative speed error was less than 0.2 percent. 

Watch the video

The presented dataset is freely available for future research and development-based endeavors.

 (Creative Commons license model CC BY-ND)

Publication
IEEE IV 2021

Read our paper from the 32nd IEEE Intelligent Vehicles Symposium to get all the insights around the processing pipeline and the dataset.

 

Publication

Python
utility

Get the free Python utility to open and visualize the dataset. Don't miss the details documentation on GitHub. 

A "hello-world"-dataset is already included in the Python package. 

Git Repository

 

Dataset
download

To get the complete dataset of 30 h, please fill out the short survey and get the download link.

 

 

Get the Dataset

cite AUTOMATUM DATA

@inproceedings{AutomatumDataSet,
              title={AUTOMATUM DATA: Drone-based highway dataset for the development and 
                        validation of automated driving software for research and commercial applications},
              author={Spannaus, Paul and Zechel, Peter and Lenz, Kilian},
              booktitle={2021 32st IEEE Intelligent Vehicles Symposium (IV)},
              pages={},
              year={2021},
              }

© Copyright. All rights reserved.