The Event-Based Space Situational Awareness (EBSSA) Dataset

Authors
-------
Saeed Afshar, Andrew P Nicholson, Andre van Schaik and Gregory Cohen
The International Centre for Neuromorphic Systems (ICNS)
The MARCS Institute for Brain, Behaviour and Development
Western Sydney University
Penrith, Australia 2751

Email: s.afshar@westernsydney.edu.au

What is it?
-----------
The EBSSA dataset is a collection of event-based recordings of resident space objects, planets and stars. Further information on the dataset contents can be found in the paper available at arXiv preprint arXiv:1911.08730.


Formats
-------
The dataset is provided in two formats:
1.) One ".mat" file per recording. 
2.) One ".h5" file for all the recordings combined.  

Dataset Summary
---------------
A short summary of the dataset is provided below:

The labelled section of the dataset contains 84 recordings.
The unlabelled section of the dataset contains 153 recordings in folders marked "Unlabelled".
 
Please refer to the 'Readme.txt' files in "./Labelled Data/" and "./Labelled Data/HDF5_Format/" folders for instructions on how to read the MAT files and the HDF5 file. 


How to cite
-----------
Please cite the following paper when using or referencing the dataset:

Afshar, Saeed, et al. "Event-based Object Detection and Tracking for Space Situational Awareness." arXiv preprint arXiv:1911.08730 (2019).